Server and method for facilitating supply chain finance using digital twin model

Abstract

Aspects concern a server comprising: a memory for storing instructions; and a processor for executing the stored instructions and configured to: obtain at least one digital twin model of one or more entities relating to a supply chain; configure a virtual structure of the one or more entities using the obtained digital twin model; compare information about the virtual structure with information about an actual object relating to the one or more entities, to confirm the virtual structure to be included in a digital twin for a supply chain finance; obtain an application including financial information in relation to the supply chain; determine one or more performance indices relating to a performance of the virtual structure using the digital twin; and generate information about the supply chain finance based on the financial information and the one or more performance indices.

Description

SERVER AND METHOD FOR FACILITATING SUPPLY CHAIN FINANCE USINGDIGITAL TWIN MODELTECHNICAL FIELD

[0001] Various embodiments relate to a server and a method for facilitating supply chain finance using a digital twin model.BACKGROUND

[0002] Mass customisation may be challenging to manufacturers that may need to be nimble in manufacturing products in small volumes with a shorter production life cycle. Due to rapidly changing products, a past performance and a past success may not be a reliable indicator or a yardstick of a future performance.

[0003] In a supply chain, several simulators for supply chain optimisations that may mainly be based on a mathematical model and solved as a linear programming problem may be available. The mathematical model may represent relations among various stages in the supply chain by defining certain parameters such as a cost, delivery time, and a yield. However, the mathematical model may not be sufficient in capturing information about physical characteristics of a product or an item, a machine, a worker, and their interactions. Measurement of a product quality, for example, a defect of the product, may require physicsbased modelling and may not sufficiently be addressed by a statistical model.

[0004] This limitation may often be solved by a technology based on a digital twin (DT) including at least one digital twin model (DTM). Currently, the application of the digital twin may be limited to a device level, and to some extent, a system level. The digital twin may be made available online, for example, in the form of a CAD file. Most of the use cases of the digital twin may be in areas of asset monitoring and maintenance in several industries such as manufacturing, transportation, and building. On the other hand, there may be limited attempts to utilise the digital twin in a supply chain finance, as most of the attempts may rely on data- driven optimisations and may not rely on physics-based optimisations.

[0005] The impact of the mass customisation may also be far-reaching even in finance. It may require an accurate and fast verification of capabilities of the manufacturers. A financier, forexample, a bank or a loan providing a financial unit, may need to assess a manufacturing performance and a risk in the supply chain. An insurer may determine an appropriate premium with respect to the manufacturing performance and the risk. However, these assessments of a loan and an insurance may be difficult in a long supply chain including multiple suppliers. Certain risks from manufacturing processes and / or parts of products may not easily be identified. A relation between a cost of failure and a cost of preventing failure may be difficult to establish. This difficulty may also arise in terms of costs of replacing raw materials, modifying a machine, upskilling workers with respect to the product quality. One of the problems with respect to a credit assessment may be that a credit score may just be a proxy for knowing if a supplier or a manufacturer has a capacity to pay a right amount at a right time. The evaluation of the credit score may highly depend on documentation and reports, which may be lagging (trailing) indicators and may not be indicative of a recent performance.

[0006] Therefore, there exists a need to provide an improved solution to facilitate supply chain finance using a digital twin model.SUMMARY

[0007] Various embodiments seeks to provide a financing solution for manufacturers which may be based on manufacturing operations parameters as current and leading indicators, and which may not rely on credit scores as a proxy for a capacity to pay of a supplier.

[0008] According to various embodiments, there is a server for facilitating supply chain finance using a digital twin model, the server comprising: a memory for storing instructions; and a processor for executing the stored instructions and configured to: obtain at least one digital twin model of one or more entities relating to a supply chain; configure a virtual structure of the one or more entities using the obtained digital twin model; compare information about the virtual structure with information about an actual object relating to the one or more entities, to confirm the virtual structure to be included in a digital twin for the supply chain finance; obtain an application including financial information in relation to the supply chain; determine one or more performance indices relating to a performance of the virtual structure using the digital twin; and generate information about the supply chain finance based on the financial information and the one or more performance indices.

[0009] In some embodiments, the processor is connectable to the actual object to obtain data for analysis; and the processor is configured to check if an output of the digital twin modelconfiguring the virtual structure is consistent with the obtained data of the actual object, and to confirm the virtual structure to be included in the digital twin.

[0010] In some embodiments, the processor is configured to confirm the virtual structure to be included in the digital twin, after confirming the digital twin model to be included in the virtual structure.

[0011] In some embodiments, if the output of the digital twin model is not consistent with the obtained data, retrieve another digital twin model or adjust accuracy of the digital twin model.

[0012] In some embodiments, the processor is configured to configure the virtual structure of the one or more entities using the digital twin model by defining the supply chain.

[0013] In some embodiments, the processor is configured to receive the application including the financial information from an applicant or a financier, and the financial information includes at least one of an expectation of a loan term, an insurance and an investment.

[0014] In some embodiments, the processor is configured to generate a contract for the supply chain finance based on the financial information and the one or more performance indices.

[0015] In some embodiments, the one or more performance indices include at least one of manufacturing operations efficiency and financial operations efficiency.

[0016] In some embodiments, the manufacturing operations efficiency includes at least one of a production cost, processing time and a manufacturing capacity; and the financial operations efficiency includes at least one of a revenue, a goods cost, a gross margin and a cash conversion cycle.

[0017] In some embodiments, the processor is further configured to simulate the digital twin for one or more plans by changing one or more manufacturing resource factors to determine the performance indices.

[0018] In some embodiments, the processor is further configured to, for each plan of the one or more plans, calculate the financial operations efficiency based on derivation of the manufacturing operations efficiency using the virtual structure and statistical analysis of historical data of financial operations efficiency' and manufacturing operations efficiency.

[0019] In some embodiments, the digital twin model is constructed by a designer based on an actual object, and the processor is configured to receive the digital twin model from the designer.

[0020] In some embodiments, the processor is configured to retrieve the digital twin model from a supplier model database.

[0021] According to various embodiments, there is a method for facilitating supply chain finance using a digital twin model, the method comprising: obtaining at least one digital twin model of one or more entities relating to a supply chain; configuring a virtual structure of the one or more entities using the obtained digital twin model; comparing information about the virtual structure with information about an actual object relating to the one or more entities, to confirm the virtual structure to be included in a digital twin for the supply chain financing; obtaining an application including financial information in relation to the supply chain; determining one or more performance indices relating to a performance of the virtual structure using the digital twin; and generating information about the supply chain finance based on the financial information and the one or more performance indices.

[0022] In some embodiments, the method further comprises connecting to the actual object to obtain data for analysis; checking if an output of the digital twin model configuring the virtual structure is consistent with the obtained data of the actual object; and confirming the virtual structure to be included in the digital twin.

[0023] In some embodiments, the method further comprises confirming the virtual structure to be included in the digital twin, after confirming the digital twin model to be included in the virtual structure.

[0024] In some embodiments, the method further comprises if the output of the digital twin data is not consistent with the obtained data, retrieving another digital twin model or adjusting accuracy of the digital twin model.

[0025] In some embodiments, the configuring the virtual structure comprises configuring the virtual structure of the one or more entities using the digital twin model by defining the supply chain.

[0026] In some embodiments, the obtaining the application including financial information comprises receiving the application including the financial information from an applicant or a financier, and the financial information includes at least one of an expectation of a loan term, an insurance and an investment.

[0027] In some embodiments, the generating the information about the supply chain finance comprises generating a contract for the supply chain finance based on the financial information and the one or more performance indices.

[0028] In some embodiments, the one or more performance indices include at least one of manufacturing operations efficiency and financial operations efficiency.

[0029] In some embodiments, the method further comprises the manufacturing operations efficiency includes at least one of a production cost, processing time and a manufacturing capacity; and the financial operations efficiency includes at least one of a revenue, a goods cost, a gross margin and a cash conversion cycle.

[0030] In some embodiments, the method furflier comprises simulating the digital twin for one or more plans by changing one or more manufacturing resource factors to determine the performance indices.

[0031] In some embodiments, the method furflier comprises, for each plan of the one or more plans, calculating the financial operations efficiency based on derivation of the manufacturing operations efficiency using the virtual structure and statistical analysis of historical data of financial operations efficiency and manufacturing operations efficiency.

[0032] In some embodiments, the digital twin model is constructed by a designer based on an actual object, and the obtaining the digital twin model comprises receiving the digital twin model from the designer.

[0033] In some embodiments, the obtaining the digital twin model comprises retrieving the digital twin model from a supplier model database.

[0034] According to various embodiments, a computer program product, comprising instructions to cause the server of any one of the above embodiments to execute the steps of the method of any one of the above embodiments is provided.

[0035] According to various embodiments, a computer-readable medium having stored thereon the above computer program product is provided.

[0036] According to various embodiments, a data processing apparatus configured to perform the method of any one of the above embodiments is provided.

[0037] According to various embodiments, a computer program element comprising program instructions, which, when executed by one or more processors, cause the one or more processors to perform the method of any one of the above embodiments is provided.

[0038] According to various embodiments, a computer-readable medium comprising program instructions, which, when executed by one or more processors, cause the one or more processors to perform the method of any one of the above embodiments is provided. The computer-readable medium may include a non-transitory computer-readable medium.BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In the drawings, like reference characters generally refer to the same parts throughout the different views. The drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the invention. In the following description, various embodiments are described with reference to the following drawings, in which:

[0040] FIG. 1 is a block diagram illustrating a server for facilitating supply chain finance using a digital twin model according to various embodiments.

[0041] FIG. 2A is a block diagram illustrating a concept of a digital twin according to various embodiments.

[0042] FIG. 2B is a block diagram illustrating a system for a digital twin for a supply chain finance structure according to various embodiments.

[0043] FIG. 3 is a data flow diagram illustrating interactions between players in a supply chain finance according to various embodiments.

[0044] FIG. 4A is an exemplary diagram illustrating features of supply chain finance with a digital twin according to various embodiments.

[0045] FIG. 4B is an exemplary diagram illustrating financial aspects and corresponding digital twin considerations according to various embodiments.

[0046] FIG. 5 is a data flow diagram illustrating an API (Application Programming Interfaces) design to connect various systems according to various embodiments.

[0047] FIG. 6 is a data flow diagram illustrating connections via API (Application Programming Interfaces) among digital twin models (DTMs) and digital twin systems (DTS) from various locations according to various embodiments.

[0048] FIG. 7 is a data flow diagram illustrating interactions between a designer, a model construction and product / process / system models according to various embodiments.

[0049] FIG. 8 is a data flow diagram illustrating a basic digital twin model (DTM) according to various embodiments.

[0050] FIG. 9 A is a flow diagram illustrating a basic digital twin model (DTM) according to various embodiments.

[0051] FIG. 9B is a flow diagram illustrating an improved digital twin model (DTM) according to various embodiments.

[0052] FIG. 10 is a data flow diagram illustrating a supply chain finance (SCF) configuration according to various embodiments.

[0053] FIG. 11 A is a data flow diagram illustrating a supply chain network according to various embodiments.

[0054] FIG. 1 IB is a data flow diagram illustrating a generated digital twin systems (DTS) after a supply chain finance (SCF) configuration according to various embodiments.

[0055] FIG. 12 is a block diagram illustrating an implementation of service evaluation according to various embodiments.

[0056] FIG. 13 is a flow diagram illustrating a method of service evaluation according to various embodiments.

[0057] FIG. 14A is an exemplary diagram illustrating a plan according to various embodiments.

[0058] FIG. 14B is an exemplary diagram illustrating a result after evaluating a plan according to various embodiments.

[0059] FIG. 14C is an exemplary' diagram illustrating a plan with manufacturing operations efficiency and financial operations efficiency according to various embodiments.

[0060] FIG. 15 is a block diagram illustrating components of contract generation according to various embodiments.

[0061] FIG. 16 is a flow diagram illustrating a method of generating a contract according to various embodiments.

[0062] FIG. 17 is a flow diagram illustrating a method for facilitating supply chain finance using a digital twin model according to various embodiments.DESCRIPTION

[0063] Embodiments described below in context of the method are analogously valid for the server, and vice versa. Furthermore, it will be understood that the embodiments described below may be combined, for example, a part of one embodiment may be combined with a part of another embodiment.

[0064] It will be understood that any property described herein for a specific device may also hold for any device described herein. Furthermore, it Mall be understood that for any device described herein, not necessarily all the components described must be enclosed in the device, but only some (but not all) components may be enclosed.

[0065] It should be understood that the terms “on”, “over”, “top”, “bottom”, “down”, “side”, “back”, “left”, “right”, “front”, “lateral”, “side”, “up”, “down” etc., when used in the following description are used for convenience and to aid understanding of relative positions or directions, and not intended to limit the orientation of any device, structure or any part of anydevice or structure. In addition, the singular terms “a”, “an”, and “the” include plural references unless context clearly indicates otherwise. Similarly, the word “or” is intended to include “and” unless the context clearly indicates otherwise.

[0066] The term “coupled” (or “connected”) herein may be understood as electrically coupled or as mechanically coupled, for example attached or fixed, or just in contact without any fixation, and it will be understood that both direct coupling or indirect coupling (in other words: coupling without direct contact) may be provided.

[0067] In order that the invention may be readily understood and put into practical effect, various embodiments will now be described by way of examples and not limitations, and with reference to the figures.

[0068] FIG. 1 is a block diagram illustrating a server 10 for facilitating supply chain finance using a digital twin model according to various embodiments.

[0069] In some embodiments, the server 10, for example, implemented by a server computer, may include a communication interface 11, a processor 12, and a memory 13.

[0070] In some embodiments, the memoty 13 (also referred to as a “database (DB)” or a “storage”) may store input data and / or output data temporarily or permanently. In some embodiments, the memoty 13 may store program code which allows the server 10 to perform a method (as will be described with reference to FIG. 17). In some embodiments, the program code may be embedded in a Software Development Kit (SDK). The memory 13 may include an internal memory of the server 10 and / or an external memory. The external memory may include, but is not limited to, an external storage medium, for example, a memory card, a flash drive, and a web storage.

[0071] In some embodiments, the communication interface 11 may allow one or more external systems to communicate with the processor 12 via a network. In some embodiments, the communication interface 11 may transmit signals to the external systems, and / or receive signals from the external systems via the network.

[0072] In some embodiments, the processor 12 may include, but is not limited to, a microprocessor, an analogue circuit, a digital circuit, a mixed-signal circuit, a logic circuit, an integrated circuit, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), or any combination thereof. Any other kind of implementation of the respective functions, which will be described below in further detail, may also be understood as the processor 12.

[0073] In some embodiments, the processor 12 may be connectable to the communication interface 11. In some embodiments, the processor 12 may be arranged in data or signal communication with the communication interface 11.

[0074] In some embodiments, the processor 12 may obtain at least one digital twin model (DTM) of one or more entities relating to a supply chain. In some embodiments, the digital twin model may be a virtual model of an actual object (also referred to as a “physical object”). The digital twin model may replicate the actual object. The actual object may include, but is not limited to, an actual product, an actual device, an actual process, an actual asset and / or an actual system. For example, the actual object may include a supplier’s actual object. As an example, the actual object may include an equipment and a machine owned by the supplier. In some embodiments, the supplier may be a party that manufactures products. For example, the supplier may include a company. The digital twin model may span the actual object’s lifecycle. The digital twin model may reflect real-time data collected from the actual object, for example, a sensor of the actual object, and be simulated by a behaviour and / or be monitored by an operation of the actual object using the real-time data In some embodiments, the entities relating to the supply chain may include, but is not limited to, a supplier of the supply chain. In some embodiments, the one or more entities may include a plurality of suppliers of the supply chain. In some other embodiments, the one or more entities may include a single supplier of the supply chain.

[0075] In some embodiments, the digital twin model may be constructed by a designer based on an actual object. In some embodiments, the processor 12 may receive the digital twin model from the designer via the communication interface 11. In some other embodiments, the processor 12 may retrieve the digital twin model from a supplier’s product, process and system model database (also referred to as a “supplier model database”) (as will be described with reference to FIG. 2B) via the communication interface 11.

[0076] In some embodiments, the processor 12 may configure a virtual structure of the entities using tiie obtained digital twin model. In some embodiments, the processor 12 may configure the virtual structure of the entities using the obtained digital twin model by defining the supply chain. In some embodiments, the virtual structure may include a combined digital twin models representing the supply chain finance. In some embodiments, the virtual structure may further include at least one of as-is information of the digital twin models and processed data relating to information relating to finance (also referred to as “financial information”), for example, manufacturing operations efficiency (MOE) and financial operations efficiency (FOE). In someembodiments, to configure the virtual structure, the processor 12 may communicate with the supplier model database 112 (as will be described with reference to FIG. 2B), a supplier database 122 (as will be described with reference to FIG. 2B) and an actual object, for example, a physical system 123 (as will be described with reference to FIG. 2B) relating to the entities. In some embodiments, the supplier model database 112 may include digital twin models of the actual object, for example, the actual system, the actual product, the actual process, etc. In some embodiments, the supplier database 122 may include information about the suppliers), including, but not limited to, name, provided products and services, and information relating to the supplier’s physical assets such as machines, factory, worker, etc. In some embodiments, the supplier database 122 may further include identifiers that may associate the supplier’s physical assets to digital twin or digital twin model equivalent.

[0077] In some embodiments, the processor 12 may compare information about the virtual structure with information about the actual object, for example, the physical system relating to the entities, to confirm the virtual structure to be included in a digital twin for the supply drain finance. In some embodiments, the digital twin for the supply chain financing may include the virtual structure and the physical system (equivalent to the digital twin model(s) included in the virtual structure). In some embodiments, the processor 12 may be connectable to the physical system. The processor 12 may obtain data from the physical system for analysing the obtained data. In some embodiments, the information about the virtual structure may include an output of the digital twin model configuring the virtual system. In some embodiments, the information about the physical system may include the obtained data of the physical system. For example, the obtained data of the physical system may include an output of the physical system. In some embodiments, the processor 12 may check if the output of the obtained digital twin model is consistent with the obtained data of the physical system. If it is determined that the output of the obtained digital twin model is not consistent with the obtained data of the physical system, the processor 12 may retrieve another digital twin model (for example, from the supplier model database 112), or adjust accuracy of the digital twin model. The processor 12 may check all the digital twin models in the above-described manner, and then terminate the process of configuration of the virtual structure (as will be described with reference to FIG. 10). In some embodiments, the processor 12 may confirm the virtual structure to be included in the digital twin, after confirming the digital twin model to be included in the virtual structure.

[0078] In some embodiments, the processor 12 may obtain an application including financial information in relation to the supply chain. In some embodiments, the processor 12 may receivethe application including the financial information from an applicant. For example, the applicant may include, but is not limited to, at least one of an investor and an insurer of the supply chain finance. In some embodiments, the financial information may include at least one of an expectation of a loan term, an insurance and an investment.

[0079] In some embodiments, the processor 12 may determine one or more performance indices relating to a performance of the virtual structure. The performance indices may be produced by the virtual structure. The performance indices may be indices that the entities, for example, the suppliers or financiers, will check upon. In some embodiments, the processor 12 may calculate the one or more performance indices using the digital twin including the virtual structure and the physical system. In some embodiments, the performance indices may include, but are not limited to, at least one of the manufacturing operations efficiency (MOE) and the financial operations efficiency (FOE). In some embodiments, the manufacturing operations efficiency may include, but is not limited to, at least one of a production cost, processing time and a manufacturing capacity. In some embodiments, the financial operations efficiency may include, but is not limited to, at least one of a revenue, a goods cost, a gross margin and a cash conversion cycle.

[0080] In some embodiments, the processor 12 may generate information about the supply chain finance based on the financial information included in the application and the calculated performance indices. In some embodiments, the information about the supply chain finance may include information about a contract for the supply chain finance. In some embodiments, the processor 12 may generate the contract for the supply chain finance based on the financial information and the calculated performance indices. For example, the processor 12 may generate the contract based on amounts and terms determined based on the financial information and the calculated performance indices and agreed with the investor, including insurance terms agreed with the insurer.

[0081] In some embodiments, the processor 12 may simulate the digital twin for one or more plans by changing one or more manufacturing resource factors (as will be described with reference to FIGS. 14A to 14C). In some embodiments, the processor 12 may simulate the digital twin to determine the performance indices.

[0082] As described above, various embodiments seeks to provide a financing solution for manufacturers which may be based on manufacturing operations parameters as current and leading indicators, and which may not rely on credit scores as a proxy for a capacity to pay of a supplier. According to various embodiments, die applicant may configure a supply chainfinance (SCF) structure by integrating the digital twin model of the supplier’s actual object, for example, the supplier’s actual products, processes and / or systems. The configuration may represent a virtual (digital) equivalent of the supply chain of the supplier. The evaluation of a loan application for the SCF may be based on the digital twin of the SCF structure. The various embodiments may utilise the digital twin to configure and evaluate the manufacturing operations efficiency and the financing operations efficiency relating to the supply chain. Based on the efficiency measurements, a contract may be generated based on amounts and terms agreed with the investor, including insurance terms agreed with the insurer. Advantageously, the various embodiments may allow a high accuracy of evaluation of manufacturing supply chain performance and a lower risk of defaults on financial products by accurate generation of the contract between the applicant and the financier.

[0083] FIG. 2A is a block diagram illustrating a concept of a digital twin according to various embodiments.

[0084] As shown in FIG. 2A, a digital twin may include a virtual structure and an actual object which is equivalent to the virtual structure. The actual object, for example, includes a physical system. The virtual structure may be a virtual object in a virtual (digital or software) world, and tiie actual object, for example, the physical system, may be an object (system) in a physical (real) world. The virtual structure may be configured using at least one digital twin model. In some embodiments, multiple sets of the virtual worlds and the physical worlds may be included in one digital twin. In some embodiments, the virtual structure may include a group, collection or combination of digital twin models representing the supply chain finance. In other words, the virtual structure may include a combined digital twin models representing the supply chain finance. In some embodiments, the virtual structure may further include at least one of as-is information of the digital twin models and processed data relating to information relating to finance (also referred to as “financial information”), for example, manufacturing operations efficiency (MOE) and financial operations efficiency (FOE). Although not shown, in some embodiments, a digital twin system (DTS) may refer to a group, collection or combination of digital twins (which are the virtual structure and the actual object equivalent). Although not shown, in some embodiments, a DTS (digital twin system) network may refer to a combination of the digital twin system (DTS) (for example, a DTS belonging to one stakeholder and another DTS of another stakeholder). Although not shown, in some embodiments, the DTS by itself may be a network of digital twins.

[0085] FIG. 2B is a block diagram illustrating a system 100 for a digital twin for a supply chain finance structure according to various embodiments.

[0086] In some embodiments, the system 100 may include, but is not limited to, a model construction module 110, a supply chain finance (SCF) configuration module 120, a service evaluation module 130, and a contract generation module 140.

[0087] In some embodiments, the model construction module 110 may receive a digital twin model of one or more entities relating to supply chain fields which may include, but is not limited to, a supplier’s actual product, process and / or system. For example, the model construction module 110 may receive the digital twin model from a designer 111. As another example, the model construction module 110 may retrieve the digital twin model from a supplier’s product, process and system model database 112 (also referred to as a “supplier model database 112”). In some other embodiments, the model construction module 110 may receive the digital twin model and information that enables such as a creation of a digital twin and checking of the digital twin model (e.g., connection to a physical device or system).

[0088] In some embodiments, the SCF configuration module 120 may configure a virtual structure of the one or more entities relating to the supply chain fields using the at least one digital twin model of the one or more entities by defining the supply chain. In some embodiments, an applicant 121 may select digital twin models from the supplier model database 112, and organise a supply chain using a supplier database 122. The SCF configuration module 120 may compare information about the virtual structure and information about an actual object, for example, a physical system 123 relating to the one or more entities.

[0089] In some embodiments, the supplier model database 112 may include the digital twin models of the actual object, for example, the actual product, tiie actual process, etc. In some embodiments, the supplier database 122 may include information about the suppliers), including, but not limited to, name, provided products and services, and information relating to the supplier’s physical assets such as machines, factory, worker, etc. In some embodiments, the supplier database 122 may further include identifiers that may associate the supplier’s physical assets to digital twin model equivalent.

[0090] In some embodiments, the service evaluation module 130 may receive an application including information relating to finance (also referred to as “financial information”) from the financier 131. For example, the financial information may include, but is not limited to, at least one of an expectation of a loan term, an insurance and an investment. In some other embodiments, the applicant 121 may be able to provide the application for the financialinformation to the service evaluation module 130. In some embodiments, the service evaluation module 130 may determine at least a set of performance indices relating to finance in relation to a performance of the virtual structure. For example, the service evaluation module 130 may calculate at least a set of performance indices.

[0091] In some embodiments, the contract generation module 140 may generate at least a contract 143 according to the set of performance indices. For example, the performance indices may include, but are not limited to, at least one of manufacturing operations efficiency (MOE) and financial operations efficiency (FOE).

[0092] FIG. 3 is a data flow diagram illustrating interactions between players in supply chain finance according to various embodiments.

[0093] In some embodiments, the players may include, but are not limited to, an applicant 121, a designer 111, an SCF digital twin system 100, an anchor (financier) 131, an investor 141 and an insurer 142.

[0094] In some embodiments, the designer 111 may construct a digital twin model according to a supplier’s actual product, process and / or system (step 112.1).

[0095] In some embodiments, the applicant 121 may be at least one of a buyer and a seller. For example, the applicant 121 may be either the buyer or the seller. In some embodiments, the applicant 121 may select digital twin models from a supplier model database 112, and organise a virtual structure using obtained digital twin models using a supplier database 122 (step 121.1) (as described with reference to FIG. 2B). The digital twin for the supply chain finance may be configured (set up), by including the virtual structure and an actual object, for example, a physical system.

[0096] In some embodiments, the financier 131 may raise funds for loans. In some embodiments, the investor 141 may provide funds to the financier 131 in exchange of interests, for example, note payments. In some embodiments, the insurer 142 may require a premium from the buyer or the seller in exchange of loss payments.

[0097] In some embodiments, the digital twin configured in the step 121.1 may include either a digital twin model or a representation with a tagged digital twin model. For example, the representation may include, but is not limited to, at least one of a block, a text label and an image of the actual object. In some embodiments, the designer 111 may tag the digital twin model with the representation.

[0098] In some embodiments, the financier 131 may check whether the digital twin of the supply chain finance is created based on at least one predetermined criterion. For example, thecriterion may include, but is not limited to, whether the buyer and the seller are represented in the digital twin model (configuring the virtual structure), a clarity on a process flow in transforming raw materials to final products, whether the digital twin models are connected, whether the digital twin models are connected to the physical system, and a validation from a third party, for example, an expert, who is knowledgeable in the process flow of manufacturing the products. In some embodiments, after the financier 131 confirms, a validation may be sent out (step 131.1). In some embodiments, the system 100 may be capable of validation by using information and data accumulated in previously created similar digital twin model and / or digital twin system.

[0099] In some embodiments, an application (step 121.2) of the applicant 121 may contain information about a loan application. For example, the information about the loan application may include, but is not limited to, information about a product for purchase, a quantity, a total amount, a buyer and a seller (for example, a name or an identification). Optionally, the information about the loan application may include a payment period.

[0100] In some embodiments, a digital twin system (DTS) may be a combination of the digital twins. In some embodiments, the digital twin or DTS with an interest proposal may be sent to file investor 141 (step 112.3). For example, the digital twin or DTS with the interest proposal may be a digital twin or DTS with a calculated value of a set of interests and a loan period after considering the loan application of the step 121.2. In some other embodiments, a validation, instead of the digital twin or DTS, with the interest proposal may be sent to the investor 141. In some embodiments, a fund and an interest rate (step 141.1) may indicate the fund for the loan and the interest rate after the decision of the investor 141 based on the interest proposal of the step 112.3 and his / her own judgement (for example, a risk appetite, a recent knowledge, and a subjective judgement). In some embodiments, the digital twin or DTS with a premium proposal may be sent to the insurer 142 (step 112.4). For example, the digital twin or DTS with the premium proposal may indicate a set of premiums after considering the loan application, optionally considering the interest proposal of the step of 112.3 and / or the fund and the interest rate of the step 141.1. In some other embodiments, the validation, instead of the digital twin or DTS, with the premium proposal may be sent to the insurer 142. In some embodiments, a premium rate (step 142.1) may be a selected premium rate of the insurer 142 after considering the loan applications, proposals, optionally together with the interest proposal of the step 112.3 and / or the fund and the interest rate of the step 141.1.

[0101] In some embodiments, once the applicant 121 agrees with the loan amount (or the fund) and the interest rate (step 142.1), a contract (step 112.5) may be made. The contract may indicate at least one of the loan amount, the interest rate, the loan period, the premium rate.

[0102] In some embodiments, the payment (step 121.3) may be an agreed amount to be made by the applicant 121 based on the contract of the step 112.5. In some embodiments, the system 100 may facilitate the payment of the interest together with a fraction of a principal (step 112.6) to the investor 141, and the premium of the step 112.7 to the insurer 142. According to the fraction of the principal, for example, if there is a principal amount of 10,000, it makes up 100%. The payment may be amortised so a fraction depending on the interest and payment period may be <100%, say 5% of the principal. If a default occurs, the system 100 may facilitate a transfer of pay-out (step 142.1) from the insurer 142, and a transfer of remaining pay-out (step 112.8) to the investor 141, considering transaction fees and other fees.

[0103] FIG. 4A is an exemplary diagram illustrating features of supply chain finance with a digital twin according to various embodiments.

[0104] In some embodiments, the representation shows that, based on an equipment 311, a person 312, a process 313, an inventory 314, and a contract 315, this disclosure according to various embodiments may combine a “supply chain with a digital twin 320” and a “supply chain finance with simulation 330”. In the supply chain with a digital twin 320, digital twin models may be used to represent physical assets such as the equipment 311 and the inventory 314 including a flow of information, material and money. In the supply drain finance with simulation 330, generic simulation tools using mathematical and statistical models may be commonly used. However, this disclosure according to various embodiments may provide the supply chain finance with the digital twin which may utilise digital twin technologies using physics-based and data-driven models. In generating and executing contracts that may include manufacturing, a delivery and financing 345, this disclosure according to various embodiments may utilise these digital twin models using the physical and data-driven models. For example, the digital twin models may be implemented and evaluated based on the corresponding digital twin models of supply chain elements and process. Advantageously, this may result in a more accurate measurement of a supply chain and a financial performance.

[0105] FIG. 4B is an exemplary' diagram illustrating financial aspects and corresponding digital twin considerations according to various embodiments.

[0106] In various embodiments, the financial aspects of a supplier, a buyer and other players in a supply chain may be considered in a digital twin design, as these considerations may have corresponding effect in the digital twin design. By using the digital twin in the supply chain finance, it may allow physics-based modelling and measuring of cost impact if certain changes were made on the digital twin models.

[0107] In some embodiments, for the supplier, the financial aspects may include capital and operational expenditures. For example, the capital expenditures may normally be fixed, assuming that the factory is already built and no additional amount will be sent for an equipment purchase or facility renovations. Therefore, some parameters in generating the digital twin model may be fixed. As an example, the parameters may include, but are not limited to, at least one of dimensions of a factory shop, an area of other workspace, and the number of machines. On the other hand, the operational expenditures may be variable. Therefore, when the digital twin models for the supply chain finance are created, at least one of the following considerations may need to be made:Creating a digital twin model that allows to vary the machine / equipment setting, and correspondingly monitors and measures costs of wear and tear as well as electrical consumptions;Creating a digital twin model, or a set of models, of several types of raw materials and that correspondingly measures the product quality and costs of defects or missed opportunity;Creating a digital twin model of operators that allows to modify (for example, add or remove) the number of operators and change skills of the operators (for example, novice, expert, special skills) and correspondingly measures product quality, processing time and operating costs due to the changes in the number and the skills of the operators; andCreating a digital twin model of a process flow, that modifies the process flow and correspondingly measures queuing time, processing time and costs of delay.

[0108] In some embodiments, for the buyer, a primary financial aspect may be the payment term which may comprise the amount and the time due of the payment. For a certain payment term, the product delivery may differ in terms of volume, time and quality. Therefore, at least one of the following considerations in the digital twin design may need to be made:Creating a connection of the digital twin models that configures the digital twin model of raw materials which may determine a work-in-progress and eventually a product volume of completed or finished goods; andCreating a connection of the digital twin models that may schedule a production based on expected delivery time and product quality.

[0109] In some embodiments, for the other players in supply chain finance, such as financiers, relevant financial aspects may include, but are not limited to, at least one of production costs, a sales target, and a cash conversion cycle. In creating the digital twin model, a maximum capacity of a machine and a process line may be considered, and the production costs and processing time may then be measured. The cash conversion cycle may subsequently be measured after determining the processing or production time and considering the payment term. If there is a certain sales target, a production schedule and a delivery schedule may be generated as a part of the digital twin model creation.

[0110] FIG. 5 is a data flow diagram illustrating an API (Application Programming Interfaces) design to connect various systems according to various embodiments. In some embodiments, the API may be a part of an SDK (Software Development Kit) to connect an application (app) to the system 100.

[0111] In some embodiments, a digital twin system (DT system or DTS) may be a combination of the digital twins. As shown in FIG. 5, the API design to connect the various systems may be provided in order to ensure a consistent and unified way, and secure a form of data exchanges between digital twins which may enable a reliable delivery of large amount of data in an efficient way. In some embodiments, the key API interfaces may include, but are not limited to the following: a DT system and a DT system interface (DTS-DTS) 410 which may be a connection of same, compatible or connectable types of a digital twin system 413; a DT model and a DT system interface (DTM-DTS) 420 which may be a connection of DT models 421 and the digital twin system 413; a DT system and a physical system interface (DTS-PS) 430 which may be a connection of the digital twin system 413 and with one of a physical system 441 and physical devices 442; a DT model and a physical system interface (DTM-PS) 440 which may be a connection of the DT models 421 and with one of a physical system 441 and physical devices 442;a DT system and an IT system interface (DTS-ITS) 450 which may be a connection of the digital twin system 413 and with an IT system, such as a database system 451, an inventory system 452, a manufacturing system 453, a delivery system 454, systems for other services 455, a client-side web application 411 and a client mobile application 412; and a DT model and an IT system interface (DTM-ITS) 460 which may be a connection of the DT models 421 and with the IT system, such as tire database system 451, the inventory system 452, the manufacturing system 453, the delivery' system 454, the systems for other services 455, the client-side web application 411 and the client mobile application 412.

[0112] In some embodiments, in tire API design, data definitions may be articulated clearly, for instance, between a designer and a domain expert in tire supply chain and IT system design. It may support various formats, for example, XML, ISON, REST, GraphQL and other formats for mobile and w eb applications.

[0113] In some embodiments, the IT system may include, but is not limited to, the database system 451, the inventory system 452, the manufacturing system 453 such as a manufacturing execution system (MES), the delivery system 454 such as a transport management system (TMS), the systems for other services 455 such as a WMS, a financial system 456 such as a payment system 457, a simulation system 458, and simulation models 459. In some embodiments, the IT system may also include the client-side web application 411 and tire client mobile application 412. The DT system may include tire simulation system 458 as a data-driven DT system, and the digital twin system 413. The DT model may include the simulation models 459 as a data-driven DT model, and the DT models 421 as a set of physicsbased DT models.

[0114] FIG. 6 is a data flow diagram illustrating connections via API (Application Programming Interfaces) among digital twin models (DTMs) and digital twin systems (DTS) from various locations to conduct a supply chain-wide simulation, according to various embodiments.

[0115] In some embodiments, a process line DTS 510 may represent a digital representation of a process line, which may be made up of processes, such as a process DTS 520. The process line DTS 510 and the process DTS 520 may be linked through a DTS-DTS API 410.

[0116] In some embodiments, a physical device 540, an IT system such as a database system 560, and an actual object, for example, a physical system 580 may be connected through their corresponding physics-based or data-driven digital twin models comprising a DT model 530, a data-drivai simulation model 550 and a DTS model 570, respectively.

[0117] In some embodiments, the APIs may include a DTM-PS API 414 to collect sensing data and / or control data from the physical device 540, a DTM-ITS API 415 to fetch and / or store data in a database and create a model from data in the database system 560, and a DTS-PS API 416 to gather operations data, which may be processed data and / or raw' data, and / or to control or configure the physical system 580. These DTMs and DTSs may be connected to other models and systems to mimic, model, control and / or configure a behaviour of an actual process or process line. For example, the process DTS 520 may be connected to the digital twins through the DTM-DTS API 411 to connect to the DT Model 530, the DTM- DTS API 413 to connect to the data-driven simulation model 550, the DTS-DTS API 412 to connect to the DTS model 570, and the DTS-DTS API 410 to connect to the process line DTS 510. The DT representation of the process line, for example, the process line DTS 510 may be connected to another DT process line to generate a digital twin of a production system.

[0118] FIG. 7 is a data flow diagram illustrating interactions between a designer 111, a model construction 110 and a product, process and system model database 112 (also referred to as a “supplier model database 112”) according to various embodiments.

[0119] In some embodiments, the designer 111 may construct a digital twin model according to an actual product, process or system. In some embodiments, the model construction 110 may allow creation of new DT models 620, an import of DT models from other platforms and update of the DT models 630, a retrieval of the DT models 640 from the supplier model database 112, visualisation of the DT models 610, and saving the DT models 650 in the supplier model database 112. In some embodiments, the model construction 110 may further allow to define API connections and implement API interfaces for digital twin models (DTMs) as described with reference to FIGS. 5 and 6.

[0120] FIG. 8 is a data flow diagram illustrating a basic digital twin model (DTM) according to various embodiments.

[0121] In some embodiments, the basic digital twin model (DTM) according to various embodiments may facilitate simulated processing using digital twins and / or digital twin models for part(s), operators and machines and conduct measurements such as measuring processing performance in generating a product in normal mode and an improvement mode.

[0122] In some embodiments, a DT system may be a combination of digital twins, wherein each digital twin is a virtual structure (which may be a combination of DTMs) and an actual object, for example, a physical system. As the DT system may be relevant to the combination of DTMs, DTM may have functions to represent at least one of a business process, a manufacturing shop floor, a machine / equipment, raw materials, operators, and methods in a digital world. The DTM may be connected to a previous process 710 and a succeeding (next) process 770. As the DTM may be simulated by business and manufacturing processes, a basic DTM may reflect a part DTM 720 which may represent raw materials and / or part(s) as a process input, which may be a physics-based representation and / or a data-representation including a material property 721 such as quantity, a shape and a location of inspection points to assess quality. It may be a set of models of the raw materials and part components.

[0123] In some embodiments, an operator DTM 730 may represent an operator that may have configurable skills (for example, novice, normal, and expert) represented by an operator action 732, which may be a series of actions in a form of a human movement, human arm kinematic angles, a human body position and / or angular kinematics.

[0124] In some embodiments, a performance processor 750 may configure the skill of the operator DTM 730 by setting and / or selecting a value of skill 751. In some embodiments, a machine DTM 740 may represent an actual machine or a set of machines that may be configured through a machine setting 752 by the performance processor 750. The machine setting 752 together with the operator action 732 may transform the part DTM 720 to a product DTM (output) 760. The performance processor 750 may allow measurement of the state in manufacturing processes (for example, an operator state 731, amachine state 741 andaproduct property 761) to monitor progress and determine quality at various manufacturing levels (for example, an equipment, a process, a shop floor and a factory) at specific time.

[0125] FIG. 9 A is a flow diagram illustrating a basic digital twin model (DTM) according to various embodiments. FIG. 9B is a flow diagram illustrating an improved digital twin model (DTM) according to various embodiments.

[0126] In some embodiments, there may be two modes in using a DTM as described with reference to FIG. 8. The two modes may include a normal mode and an improvement (simulation) mode. For example, the normal mode may be selected by default. As another example, if a quantity is within a range of a target, for example, a production volume, the normal mode may be selected. For example, the improvement mode may be selected if a desired number of products of acceptable quality' is not achieved.

[0127] As shown in FIG. 9A illustrating the basic DTM in the normal mode, after receiving a part DTM 720 (raw materials and / or part(s)) from a previous process (step 811), a performance processor 750 may set a skill of an operator based on a pre-set value determined by a skill of an actual operator, and generate an operator action (step 812).

[0128] After configuring a corresponding machine setting, the performance processor 750 may trigger to start the processing of the part DTM 720 in a machine DTM 740 with an operator DTM 730 following the operator action of the step 812. Then, the performance processor 750 may monitor the action and machine states until all the actions are completed (step 813).

[0129] Furflier, the performance processor 750 may conduct a product quality' check through inspection points, store the measurement (for example, quantity of passed quality, a skill, a machine setting, processing time, processing costs) (step 814). As it is in the normal mode, the performance processor 750 may proceed to send a product DTM (output) 760 (step 816) to the next process (step 817).

[0130] FIG. 9B illustrates the improved DTM in the improvement mode which may be carried out automatically or manually, for example, by an applicant 121 or a financier 131, if during an assessment it turns out that the current configuration is not within an acceptable range of manufacturing operations efficiency and / or financial operations efficiency. The performance processor 750 may retrieve the available skills of the operator DTM 730. For each of the skill set, the performance processor 750 may generate actions (step 821). For each skill set, the performance processor 750 may generate applicable machine settings, and using corresponding actions, the performance processor 750 may carry out the processing of the part DTM 720 in the machine DTM 740 following the corresponding operator actions (step 822). Furflier, the performance processor 750 may evaluate the performance of each pair of actions and machine setting. The performance processor 750 may rank each pair of actions and machine setting based on the product quality, processing time, and processing cost (step 823). The performance processor 750 may select the setting based on the target output quality, quantity and costs (step 824) and signal the end of improvement mode (step 825).

[0131] FIG. 10 is a data flow diagram illustrating a supply chain finance (SCF) configuration according to various embodiments.

[0132] As shown in FIG. 10, an applicant 121, who may be either a buyer or a seller, may select digital twin models and organise a virtual structure to be included in a digital twin for a supply chain finance using information received from a supplier database 122 (step 910).For example, the information received from the supplier database 122 may include, but is not limited to, a company name and corresponding items of a DTM. In some embodiments, if available, a supplier network of a company may be retrieved, as a basis for creating the virtual structure for the supply chain finance (step 920). For example, DT models corresponding to the supplier systems / process may be retrieved in die supplier network. In some embodiments, if available, the DTM may be connected to its corresponding physical device or a physical device system of a supplier system or a process to gather data for analysis (step 930).

[0133] In some embodiments, data analysis may be conducted to confirm if the DTM matches with the physical device or the physical device system (step 940). An identification number for matching may be made first. Further matching may be conducted to confirm if the model (for example, the DTM) generates the same, comparable or similar output as that of its physical equivalent. It may be conducted by comparing measurements from the outputs of the DTM and the physical equivalent. If it is not consistent, another model (for example, a physicsbased model is unavailable and a statistical or approximate model can be used readily) may be retrieved. Based on a type of models used, an appropriate accuracy may be set (adjusted) based on the measurement comparison made. The accuracy may also be aggregated with the evaluation of the model from its previous usage, by the applicant 121 or the financier 131, or based on comments from designer 111. After all the models are checked and the supplier or the supply chain network is created, the SCF configuration may be terminated (step 950). At this stage, the virtual structure with model accuracy may be generated (step 951).

[0134] FIG. 11 A is a data flow diagram illustrating a supply chain network according to various embodiments. FIG. 1 IB is a data flow diagram illustrating a generated digital twin systems (DTS) after a supply chain finance (SCF) configuration (i.e. after configuring the virtual structure for the supply chain finance as shown in FIG. 10) according to various embodiments.

[0135] As shown in FIG. 11 A, the supply chain network 1010 may comprise a supplier 1020, a transporter 1040 and a manufacturer 1050 that may be retrieved from a supplier database 122. FIG. 1 IB illustrates an example of the generated virtual structure 1011 after the SCF configuration. For digital twin models connected to an actual object, for example, a DT model of the supplier 1021 connected to a physical system of the supplier 1023, it may be considered to have higher accuracy if the model and physical system measurements are within tolerance levels. If deviations are higher than a threshold, setting of the digital twin model may be adjusted, or a more appropriate digital twin model may be looked for to fit the datameasurements. Further, physics-based models may be rated to be higher than data-driven models. For digital twin models which are not connected to the physical system, for example, a DT model of the transporter 1041 that may have no DTM connected, the model may be compared to input and output of preceding and succeeding processes, for example, a product of the supplier 1022 and a product of the supplier after delivery 1042, to compare a behaviour of the model with the input and output values and estimate accuracy. In some embodiments, in this case, a statistical model may be generated automatically after an enough amount of data is collected.

[0136] FIG. 12 is a block diagram illustrating an implementation of service evaluation according to various embodiments.

[0137] FIG. 12 shows an implementation of a service evaluation module 130 which may use a virtual structure generated from an SCF configuration 120. In some embodiments, the service evaluation module 130 may use a DTS (digital twin system) network which is a combination of digital twin systems (DTS) (for example, a DTS belonging to one stakeholder and another DTS of another stakeholder). The digital twin system (DTS) is a group, collection or combination of digital twins (which are the virtual structure and an actual object equivalent). In the processing for the service evaluation, only the virtual structure (without the actual object) of the digital twin of the DTS of the DTS network may be utilised, as the processing may mainly involve simulation. In some embodiments, in the DTS, the actual object may not be present or may not exist during the simulation, evaluation or other processing. In some embodiments, the service evaluation module 130 may aggregate performance measurement data from every measurements conducted and stored by a performance measurement 753 of every DTM, as shown in FIG. 8. In some embodiments, it may cover functions to estimate the production volume in a production plan estimator 1110, a manufacturing efficiency calculator 1120, and a financial efficiency calculator 1130. In these calculations, machine settings may be adjusted in a machine setting adjustor 1140, a raw material adjustor 1150, an operation condition adjuster 1160, and a worker skill adjuster 1170. For example, the manufacturing efficiency calculator 1120 may calculate lead time, a production volume output, a yield rate of a process line by considering process time, a throughput rate, and the yield rate of each process based on the measurements made by the performance processor 750 from the DTM of each process.

[0138] In some embodiments, the production plan estimator 1110 may process these calculated values for each process to estimate manufacturing capacity, identify bottlenecks,and determine a reasonable level of a production plan. In some embodiments, the machine setting adjustor 1140 may set an applicable setting of machines in a production system or a production line to achieve a desired production plan. In some embodiments, the raw material adjustor 1150 may set the applicable setting for the raw materials in the production system or the production line to achieve a desired production plan. In some embodiments, the operating condition adjustor 1160 may set an applicable environmental setting condition (for example, an air conditioning unit for temperature control) in the production system or the production line to achieve the desired production plan. In some embodiments, the worker skill adjustor 1170 may set the applicable setting for the worker skill in the production system or the production line to achieve the desired production plan. In some embodiments, die settings in the machine setting adjustor 1140, the raw material adjustor 1150, the operation condition adjuster 1160, and the worker skill adjuster 1170 may be sent out to the corresponding performance processor 750 of the DTM of each process. A proper combination of die setting of machines, raw materials, operating conditions, worker skills may be determined by simulation (for example, following the improvement mode described with reference to FIG. 9B).

[0139] Normally, depreciation of machines may be modelled linearly with time. In a service evaluation module 130 as shown in FIG. 2B, a depreciation calculator 1180 may calculate the depreciation based on the degradation of the system observable and measured in the DTM of machines (for example, the measurements from the performance processor 750 from the DTM of each process). In the service evaluation, other data, for example, data for measuring industry benchmarks from an industry benchmark database 1101, data for determining changes in production from a production history database 1102, data for determining financial events from a financial history database 1103, and data for funds from a fund database 1104 may be taken into consideration.

[0140] In some embodiments, the financier 131 based on information from the DTS may measure manufacturing operations efficiency (MOE) and financial operations efficiency (FOE). The MOE may be measured by costs of production, processing time, and manufacturing capacity. The FOE may be measured by revenue, costs of goods, a gross margin, and a cash conversion cycle. The DTM and the DTS may be used to simulate various plans by varying and adjusting manufacturing resources, including, but not limited to, skills, machine settings, raw materials, and other operating conditions.

[0141] FIG. 13 is a flow diagram illustrating a method of senice evaluation according to various embodiments.

[0142] In some embodiments, a set of production plans may be generated based on a fund amount from financiers 131 (for example, a production mix) (step 1210). Each plan may be fed into a DTS network for processing. In the processing for the service evaluation, only a virtual structure (without an actual object) of a digital twin of a DTS of the DTS network may be utilised, as the processing may mainly involve simulation. In some embodiments, in the DTS, the actual object may not be presort or may not exist during the simulation, evaluation or other processing. A service evaluation module 130 as shown in FIG. 2B may measure values of an MOE and a FOE (step 1210).

[0143] In some embodiments, for each plan, the MOE may be calculated by varying resource settings such as expenses. A worker skill may be changed from novice to expert level, and thus a corresponding change in the product quality and in the operation costs due to a change of a salary of the worker may happen. Raw materials may be varied as a premium or an alterative which may similarly affect the product quality and the operation costs. A machine may be scheduled for a regular maintenance or may be maintained only during failure. An operating condition of the machine in a shop floor such as an air conditioning unit may also be adjusted up to a limit that the environmental temperature is appropriate to an ongoing process (step 1220).

[0144] In some embodiments, for each plan, tire service evaluation module 130 may estimate FOE measurements using historical data from a production history database 1102 and a financial history database 1103 as shown in FIG. 12, and measure financial performance considering the MOE from a DTS result (step 1230). In some embodiments, the production history database 1102 may include, but is not limited to, at least one of a production volume, production date, production lead time and a yield rate. In some embodiments, the financial history database 1103 may include, but is not limited to, at least one of accounts in a balance sheet such as assets, debts and retained earnings, items in income statements such as a revenue, costs of goods, financial ratio and indicators such as a cash conversion cycle, and ledger accounts indicating a customer name, transaction date, an account type and an account value.

[0145] In some embodiments, for each plan, the financial operation efficiency values may be calculated to estimate a gross profit margin (for example, (revenue - costs of goods) / revenue, cash conversion cycle, costs of goods / total production volume, day of sales inventory / cash conversion cycle), a return on capital, and a return on equity (step 1240).

[0146] In some embodiments, the MOE may be a single or multiple measurements that may indicate one or more KPIs including, but not limited to, manufacturing performanceindices such as quantity, production costs, quality, and delivery or lead time. These KPIs may be aggregated to a single value to represent an MOE. In some embodiments, the FOE may be a single or multiple measurements that may indicate one or more financial performance measurements including, but not limited to, a profit margin, a cash conversion cycle, a revenue per production unit, a return on capital, a return on equity, etc. These financial performance measurements may be aggregated to a single value to represent a FOE. The current FOE may be calculated by applying statistical analysis and machine learning algorithms on the financial history and previous FOEs. Alternatively, the previous measurements of MOEs and the previous measurements of FOEs may be processed to estimate the current FOE. Alternatively, the previous production history and the previous measurements of FOEs may be processed to estimate the current FOE. The processing of the data may be performed through statistical analysis and / or applying the machine learning algorithms. Alternatively, a physics-based simulation using DTS may be made, and the measurement results of the MOE from the simulation may be gathered. From tire production history database 1102 and tire financial history database 1103 as shown in FIG. 12, a pair of MOE and FOE (both of which may be single or multiple measurements) may be calculated. This MOE result from the DTS simulation may be compared with the previous MOEs (single or multiple measurements) to find the closest matching MOE. The corresponding FOE of the closest MOE may be determined as the FOE estimate. The results of the above estimations may be compared based on precision and recall accuracy, from which the estimation model with the highest model may be used to estimate the FOE.

[0147] FIG. 14A is an exemplary diagram illustrating a plan according to various embodiments.

[0148] FIG. 14A shows an example of a plan 1320. In some embodiments, an ID 1310 may identify a specific plan. In some embodiments, a volume 1321 may be the number of a manufacturing target output or a production volume, which may be varied or fixed according to the plan 1320. For example, as shown in FIG. 14A (and FIG. 14C), a worker skill 1322 may be indicated as “100% to 0%”, wherein 100% may refer to normal-skilled workers and 0% may refer to highly skilled workers. As another example, as shown in FIG. 14A (and FIG. 14C), tire worker skill 1322 may be indicated as “50% to 50%”, which means an equal percentage of normal and highly-skilled workers. In some embodiments, a work shift 1323 may be adjusted based on the number of hours per shift and the number of shifts per day. In some embodiments, machine capacity 1324 may measure a planned number of outputs of a certain machinecompared to a maximum capacity of the machine. In some embodiments, a utility usage 1325 may measure a usage of certain utilities, for example, electricity or water resource. For example, 100% may refer to all resources such as electricity and / or water being designated or planned for a specific plan. In some embodiments, the number of plans may be numerous as combinations of parameter plans may increase exponentially. Therefore, fewer plans may be examined and adjusted accordingly based on previous production plans in a production history database 1102 as shown in FIG. 12. In examining these plans, a search algorithm using metaheuristics (for example, Simulated Annealing, Tabu search (TS), steepest descent search, etc.) and hyper-heuristics algorithms may be applied to improve a result of examining the plans with desired, improved or better values for the MOE and the FOE.

[0149] FIG. 14B is an exemplary diagram illustrating a result after evaluating a plan according to various embodiments. FIG. 14C is an exemplary diagram illustrating a plan with manufacturing operations efficiency and financial operations efficiency according to various embodiments.

[0150] FIGS. 14B and 14C show examples of the result after evaluating the plan 1320 and calculating MOE 1330 and FOE 1340. In some embodiments, the MOE 1330 may comprise costs of production 1331 and processing time 1332. hi some embodiments, the FOE 1340 may comprise a revalue 1341, costs of goods 1342, a gross margin 1343, and a cash conversion cycle 1344. The results measured in the costs of production 1331 and the processing time 1332 may utilise a physics-based DTS to simulate the varying manufacturing settings in the plan 1320, including, but not limited to, a worker skill 1322, a work shift 1323, a machine capacity 1324 and a utility usage 1325. Further, the measurements in the cost of goods 1342, the gross margin 1343, and the cash conversion cycle 1344 may be determined based on a result of simulations utilising the physics-based and data-driven DTS.

[0151] FIG. 15 is a block diagram illustrating components of contract generation according to various embodiments.

[0152] In some embodiments, an input for a contract generation module 140, as shown in FIG. 2B, may be a fund or a production plan, measurement of efficiency (for example, an MOE and a FOE) and current market rates (for example, a loan interest rate and a premium).

[0153] In some embodiments, a contract value calculator 1410 may determine a loanable amount based on an available fund and production that may be feasible to a supplier according to FOE measurement. In calculating a length of a payment period, one of key metrics that is checked in FOE may be a cash conversion cycle which may allow predictability of thesupplier to collect cash and pay an amount at the right time. Then, an annual payment rate (APY) or the payment value, for example, depending on the appropriate period (for example, monthly), may be determined in an APY estimator 1420 after considering interest rates and other fees. These other fees may include charges and premiums if the financier 131 deems that an insurance premium is required to absorb certain risks in a premium value estimator 1440. The premium value estimator 1440 may calculate the premium based on at least one of a risk model (for example, probability of default or likelihood that the terms in the contract will be used), the current market rate, and a financial history of a customer.

[0154] In some embodiments, an industry market rates database 1401 may store previous and current market rates (for example, loan rate and interest rate) from several industries such as manufacturing, construction, logistics, etc. A contract history database 1402 may store previous and current contracts including contract terms, a customer profile, and an associated industry. A financial history database 1403 may store data relating to significant events that may cause large market fluctuations such as company default, recession, etc.

[0155] In some embodiments, a contract performance evaluator 1450 may create a comparison table comparing the previous contracts (for example, in a tabular format with columns indicated as follows) based on the customer profile (for example, ID, demographic, etc.), the contract terms (for example, a premium and a payment period), the used contract terms (for example, default or not, by when), and the evaluation after the end of the contract (for example, good, defaulted or not good). An industry market rate comparator 1460 may compare the market rates from various industries. The industry market rate comparator 1460 may further cluster the industries in different market rate bands and identify contracts that belong to the same band.

[0156] In some embodiments, in the contract value calculator 1410, a risk model maybe created based on the result of contract performance evaluation in the contract performance evaluator 1450 (for example, the comparison table), a market rate band cluster, the contract history- database 1402 and the financial history database 1403. The risk model may provide a quantitative or qualitative assessment of risks. Then, the risk value of the previous contracts may be calculated based on the risk model. In the premium value estimator 1440, a premium value model may be generated using the previous premium in the previous contracts as a dependent variable; and the risk values and the previous measurements of the FOE and / or the MOE may be used as independent variables for the premium value model. In the payment period calculator 1430, a payment period model may be generated using the previous paymentperiods from the contract history database 1402, the previous risk model values, and the measurements of the FOE and / or the MOE. Alte atively, in the APY estimator 1420, a payment period model may be generated using the previous APY from the contract history database 1402, the previous risk model values, and the measurements of the FOE and / or the MOE. The values calculated in the APY estimator 1420 and the payment period may be checked for consistency with the contract value calculated in the contract value calculator 1410. Overall, the contract value, the payment period, a regular payment amount and the premiums may be decisions taken together to determine the performance of the contract in the contract history database 1402 based on the evaluation of the FOE and the MOE.

[0157] FIG. 16 is a flow diagram illustrating a method of generating a contract according to various embodiments.

[0158] In some embodiments, a contract generation module 140 as shown in FIG. 2B may receive an expected loan amount from an applicant 121. The contract generation module 140 may determine plans and measures corresponding to an MOE and a FOE (step 1510).

[0159] In some embodiments, a profit value of a plan may need to exceed the loan amount or within some range. In some embodiments, for each plan, the contract generation module 140 may calculate a contract value by considering a profit, a revenue, and a loan amount (for example, ratio), and then calculate an APY and terms based on a cash conversion cycle and a contract value (step 1520).

[0160] In some embodiments, the contract generation module 140 may retrieve an available fund from financiers 131 and select an individual fund or a pooled fund that may match the contract value with corresponding APY and terms (step 1530).

[0161] In some embodiments, for each draft contract with the matching fund, it is sent to a funder to confirm the payment period as well as the interest (step 1540). These confirmed contracts may constitute the contract 143 which may be offered to the applicant 121. These contracts may be ranked based on certain measurements.

[0162] Although not shown, in some embodiments, the above-mentioned measurements may be based on risk values calculated by the contract value calculator 1410 as shown in FIG. 15, and information provided in a UI (user interface) to the applicant 121 as a decision guide. Another measurement in the UI may be provided to show a market rate applied in a loan proposal and together with rates from other market rates across industries to inform the applicant 121 of attractiveness of the loan proposal. As the (loan) applicant 121 may have previous loans (active or completed contracts), the UI may provide information about theprevious loan and the loan proposals by plotting on a graph whereby a graph (a single or multiple axis) may be provided to show the contract value, time when the loan is made or the contract is completed, the APY, and the premium. Further, the UI may be provided to show an active and completed loan of customers with a similar profile as an applicant. For example, these customers may be anonymised. The similarity of profiles may be based on a demographic (for example, age, gender, etc.), a contract value, and a payment term. The similarity of profiles may also be determined automatically based on clustering algorithms (for example, PCA (Principal Component Analysis) method) and may be made interactively or guided by provided selection buttons and drop-down boxes in the UI, and through prompts from the contract generation module 140 that may provide guidance or additional information on the generated graph. The guidance or additional information may be generated by a generative Al (artificial intelligence) technology that may be connected to the SCF digital twin system 100. For example, the generative Al may generate queries based on a graph which is generated or to be generated, determine the measurement required based on the generate queries, analyse the output of the DTM or DTS, and create a report of the output.

[0163] FIG. 17 is a flow diagram illustrating a method for facilitating supply chain finance using a digital twin according to various embodiments.

[0164] In some embodiments, the method may include a step 1610 of obtaining at least one digital twin model of one or more entities relating to a supply chain.

[0165] In some embodiments, the method may include a step 1620 of configuring a virtual structure of the one or more entities using the obtained digital twin model.

[0166] In some embodiments, the method may include a step 1630 of comparing information about the virtual structure with information about an actual object relating to the one or more entities, to confirm the virtual structure to be included in a digital twin for the supply chain financing. In some embodiments, the digital twin for tire supply chain financing may include the virtual structure and the actual object (for example, a physical system equivalent to the digital twin model(s) included in tire virtual structure).

[0167] In some embodiments, the method may include a step 1640 of obtaining an application including financial information in relation to the supply chain.

[0168] In some embodiments, the method may include a step 1650 of determining one or more performance indices relating to a performance of the virtual structure using the digital twin.

[0169] In some embodiments, the method may include a step 1660 of generating information about the supply chain finance based on the financial information and the one or more performance indices. In some embodiments, the step 1660 may further include generating a contract for the supply drain finance based on the financial information and the one or more performance indices.

[0170] As described above, various embodiments may assess manufacturing operations efficiency and financial operations efficiency based on product quality, cost, and other factors by evaluating digital twin models under various settings (for example, machine settings, operator skills, a material type). The evaluation of the manufacturing operations efficiency and the financial operations efficiency may further be extended to measuring factors relating to sustainability such as carbon emission, re-use of materials and resources, energy consumption, minimal use of manufacturing resources such as machines, human operators, and raw materials. These measurements of the manufacturing operations efficiency and the financial operations efficiency may apply to various industries not only in manufacturing but also in the field of transportation, health, and service industries such as hospitality and retail. Furflier, the contract generation according to digital twin systems may be applicable to various financial solutions including loans, insurance, and investments such as options.

[0171] While embodiments of the invention have been particularly shown and described with reference to specific embodiments, it should be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. The scope of the invention is thus indicated by the appended claims and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced. It will be appreciated that common numerals, used in the relevant drawings, refer to components that sen e a similar or the same purpose. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof’ include any combination of A, B, and / or C,and may include multiples of A, multiples of B, or multiples of C. Specifically, combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof’ may be A only, B only, C only, A and B, A and C, B and C, or A and B and C, where any such combinations may contain one or more member or members of A, B, or C. All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the claims. The words “module,” “mechanism,” “element,” “device,” and the like may not be a substitute for the word “means.” As such, no claim element is to be construed as a means plus function unless the element is expressly recited using the phrase “means for.”

Claims

CLAIMS1. A server for facilitating supply chain finance using a digital twin model, the server comprising: a memory for storing instructions; and a processor for executing the stored instructions and configured to: obtain at least one digital twin model of one or more entities relating to a supply chain; configure a virtual structure of the one or more entities using the obtained digital twin model; compare information about the virtual structure with information about an actual object relating to the one or more entities, to confirm the virtual structure to be included in a digital twin for the supply chain finance; obtain an application including financial information in relation to the supply chain; determine one or more performance indices relating to a performance of the virtual structure using the digital twin; and generate information about the supply chain finance based on the financial information and the one or more performance indices.

2. The server according to claim 1, wherein the processor is connectable to the actual object to obtain data for analysis; and die processor is configured to check if an output of the digital twin model configuring the virtual structure is consistent with the obtained data of the actual object, and to confirm the virtual structure to be included in the digital twin.

3. The server according to claim 1 or claim 2, wherein if the output of the digital twin model is not consistent with the obtained data, retrieve another digital twin model or adjust accuracy of the digital twin model.

4. The server according to any one of claims 1 to 3, wherein the processor is configured to configure the virtual structure of the one or more entities using the digital twin model by defining the supply chain.

5. The server according to any one of claims 1 to 4, wherein the processor is configured to receive the application including the financial information from an applicant or a financier, and the financial information includes at least one of an expectation of a loan term, an insurance and an investment.

6. The server according to any one of claims 1 to 5, wherein the processor is configured to generate a contract for the supply chain finance based on the financial information and the one or more performance indices.

7. The server according to any one of claims 1 to 6, wherein the one or more performance indices include at least one of manufacturing operations efficiency and financial operations efficiency.

8. The server according to claim 7, wherein the manufacturing operations efficiency includes at least one of a production cost, processing time and a manufacturing capacity; and the financial operations efficiency includes at least one of a revenue, a goods cost, a gross margin and a cash conversion cycle.

9. The server according to claim 7 or claim 8, wherein the processor is further configured to simulate the digital twin for one or more plans by changing one or more manufacturing resource factors, to determine the performance indices.

10. The server according to claim 9, wherein the processor is further configured to, for each plan of the one or more plans, calculate the financial operations efficiency based on derivation of the manufacturing operations efficiency using the virtual structure and statistical analysis of historical data of financial operations efficiency and manufacturing operations efficiency.

11. A method for facilitating supply chain finance using a digital twin model, the method comprising: obtaining at least one digital twin model of one or more entities relating to a supply chain; configuring a virtual structure of the one or more entities using the obtained digital twin model;comparing information about the virtual structure with information about an actual object relating to the one or more entities, to confirm the virtual structure to be included in a digital twin for the supply chain financing; obtaining an application including financial information in relation to the supply chain; determining one or more performance indices relating to a performance of the virtual structure using the digital twin; and generating information about the supply chain finance based on the financial information and the one or more performance indices.

12. The method according to claim 11 further comprising connecting to the actual object to obtain data for analysis; checking if an output of die digital twin model configuring the virtual structure is consistent with the obtained data of the actual object; and confirming the virtual structure to be included in the digital twin.

13. The method according to claim 11 or claim 12 further comprising if the output of the digital twin data is not consistent with the obtained data, retrieving another digital twin model or adjusting accuracy of the digital twin model.

14. The method according to any one of claims 11 to 13, wherein the configuring the virtual structure comprises configuring the virtual structure of the one or more entities using the digital twin model by defining the supply chain.

15. The method according to any one of claims 11 to 14, wherein the obtaining the application including financial information comprises receiving the application including the financial information from an applicant or a financier, and the financial information includes at least one of an expectation of a loan term, an insurance and an investment.

16. The method according to any one of claims 11 to 15, wherein the generating the information about the supply chain finance comprises generating a contract for the supply chain finance based on the financial information and the one or more performance indices.

17. The method according to any one of claims 11 to 16, wherein the one or more performance indices include at least one of manufacturing operations efficiency and financial operations efficiency.

18. The method according to claim 17, wherein the manufacturing operations efficiency includes at least one of a production cost, processing time and a manufacturing capacity; and the financial operations efficiency includes at least one of a revenue, a goods cost, a gross margin and a cash conversion cycle.

19. The method according to claim 17 or claim 18 further comprising simulating the digital twin for one or more plans by changing one or more manufacturing resource factors, to determine the performance indices.

20. The method according to claim 19 further comprising, for each plan of the one or more plans, calculating the financial operations efficiency based on derivation of the manufacturing operations efficiency using the virtual structure and statistical analysis of historical data of financial operations efficiency and manufacturing operations efficiency.

Images