An intelligent inventory control management method and system based on a supply chain coordination mechanism

Abstract

The application provides an intelligent inventory control management method and system based on a supply chain cooperation mechanism, applied to the technical field of supply chain management, preliminary demand prediction of a downstream partner is received, demand intention information containing customization component possibility weight and potential demand range is generated according to the prediction, after the upstream supplier receives the demand intention information, the influence of the demand intention information on future production resources is further evaluated, an evaluation result is obtained, finally, according to the evaluation result, the method performs flexible preparation in advance, including production window soft reservation, upstream material pre-communication and special mold preparation, effectively coping with the supply uncertainty of the customized components, avoiding the dilemma of standard component overstock and customized component shortage, realizing lean production and on-time delivery, and bringing significant economic benefits and competitive advantages to enterprises.

Description

Technical Field

[0001] This application relates to the technical field, and in particular to an intelligent inventory control and management method and system based on a supply chain collaboration mechanism. Background Technology

[0002] In modern supply chain management, enterprises commonly adopt collaborative inventory management systems that utilize information sharing and automated processing to improve efficiency and reduce costs. However, when products are highly customized and downstream partners can only provide preliminary demand forecasts with vague or placeholder codes in the early stages of a project, existing systems often struggle to accurately understand these non-granular demands. This frequently leads to the system incorrectly mapping vague demands to standard products, resulting in structural material discrepancies, stockpiling of standard components while experiencing shortages of customized parts, ultimately impacting production delivery and increasing operating costs. Therefore, effectively addressing this inconsistency in demand information granularity is a significant challenge currently facing collaborative inventory management in the supply chain.

[0003] For example, in the field of high-end industrial automation equipment manufacturing, core manufacturers have established a supply chain collaborative inventory management system based on information sharing with their upstream key component suppliers and downstream system integrators. This system aims to achieve lean manufacturing and just-in-time delivery. However, the industrial control modules produced by core manufacturers are highly customized, with each specific configuration corresponding to a unique bill of materials (BOM). In the early stages of actual projects, downstream system integrators often find it difficult to immediately provide such detailed material requirements, typically using placeholder codes such as "general-purpose control module" or "module with undetermined configuration," along with preliminary quantity estimates.

[0004] After receiving preliminary demand forecasts from downstream system integrators, the core manufacturer's collaborative inventory management system, in the absence of clear historical matching data or detailed technical parameters, automatically maps the forecasts to the closest "standard" control module configurations with the highest inventory turnover rates, based on preset default rules. The system's internal logic considers this a "safe" default approach, ensuring at least some common materials are in stock before the final demand is determined. Therefore, based on this "standardized" interpretation, the core manufacturer's system generates preliminary purchase orders for upstream suppliers, primarily focusing on common ICs and connectors used in the standard control modules.

[0005] Ultimately, the core manufacturer's inability to obtain the required customized components in a timely manner prevented it from delivering the customized control modules to the system integrator on time. The system integrator faced project delays, substantial breach of contract penalties to end customers, and potentially lost customer trust and future cooperation opportunities. More seriously, this delay not only affected individual projects but also exposed deep-seated flaws in the entire supply chain collaboration system's ability to handle complex, variable, and inconsistent information granularity demands. The core manufacturer faced a large backlog of standard components and a severe shortage of customized parts, hindering cash flow and severely damaging its reputation as a core supplier. The entire supply chain, due to initial misinterpretations of demand information, fell into a multi-faceted predicament of material mismatch, production stagnation, delivery delays, and soaring costs, severely undermining the efficiency and resilience that collaborative management should provide.

[0006] To address the aforementioned issues, existing technologies urgently need improvement. Summary of the Invention

[0007] In view of the shortcomings of the prior art, this application provides an intelligent inventory control management method and system based on the supply chain collaboration mechanism. It aims to solve the problem that when products have highly customized characteristics and downstream partners can only provide preliminary demand forecasts with fuzzy or placeholder codes, the existing system is unable to accurately understand non-refined demand, resulting in structural deviations in materials, backlog of standard parts, and shortage of customized parts, which ultimately affects production delivery and increases operating costs.

[0008] Firstly, an intelligent inventory control and management method based on a supply chain collaboration mechanism, the method comprising the following steps:

[0009] S1: Receive preliminary demand forecasts from downstream partners, and generate demand intention information including the probability weights of customized components and the potential demand range based on the preliminary demand forecasts;

[0010] S2: Synchronize the aforementioned demand intention information with the upstream supplier's production planning system in real time;

[0011] S3: After receiving the demand intention information from the upstream supplier's production planning system, assess the impact of the demand intention information on future production resources and obtain the assessment result;

[0012] S4: Based on the assessment results, make flexible preparations in advance, including soft reservation of production windows, pre-communication with upstream materials, and preparation of special molds.

[0013] Furthermore, step S1 includes:

[0014] S11: Receive preliminary demand forecasts from downstream partners and continuously monitor changes in the probability weight and potential demand range of customized components in the preliminary demand forecasts.

[0015] S12: Aggregate the monitored changes over a time window to obtain the aggregated probability weights and potential demand ranges for customized components;

[0016] S13: Based on the aggregated probability weights and potential demand range of customized components, analyze the logical relationships between customized components and form demand scenarios from the intention signals of the interrelated customized components.

[0017] S14: Assign a comprehensive probability weight and a total demand range to the aforementioned demand scenario;

[0018] S15: Based on the comprehensive probability weight, fluctuation range, and expected demand refinement time point, assign maturity level to the demand scenario, thereby generating the demand intention information.

[0019] Furthermore, step S13 includes:

[0020] S131: Construct a knowledge graph of customized components, wherein the nodes and edges between the nodes of the knowledge graph represent the customized components and the relationships between the customized components, and the relationships include at least the compatibility, dependency or mutual exclusion between the customized components;

[0021] S132: Based on the aggregated probability weights and potential demand ranges of customized components, and using the knowledge graph, identify component clusters with related relationships among the aggregated probability weights and potential demand ranges of customized components;

[0022] S133: Form the component cluster into a demand scenario.

[0023] Furthermore, step S15 includes:

[0024] S151: Pre-configure a business rule set, which at least defines a priority sequence and condition thresholds. The priority is defined as follows: comprehensive probability weight assessment takes precedence over fluctuation amplitude assessment, and fluctuation amplitude assessment takes precedence over the expected demand refinement time point assessment. The condition thresholds are defined as follows: when the comprehensive probability weight is higher than 0.7, the judgment result is "high potential"; when the fluctuation amplitude is lower than 0.1, the judgment result is "stable"; when the expected demand refinement time point is 30 days earlier than the current date, the judgment result is "urgent".

[0025] S152: The comprehensive probability weight, fluctuation range and expected demand refinement time points are logically judged according to the priority and condition thresholds defined in the business rule set to obtain the judgment result;

[0026] S153: Based on the judgment result, assign a maturity level to the demand scenario, thereby generating the demand intention information.

[0027] Furthermore, step S3 includes:

[0028] S31: After receiving the demand intention information from the upstream supplier's production planning system, identify long-cycle customized materials provided by key second- or third-tier suppliers based on the demand intention information.

[0029] S32: Transform the demand intention information into the demand quantity and delivery time of the long-cycle customized materials;

[0030] S33: Send the query command for the required quantity and the delivery time to the key second- or third-tier supplier;

[0031] S34: Receive production capacity and delivery cycle information from key Tier 2 or Tier 3 suppliers in accordance with query instructions;

[0032] S35: Based on the production capacity and delivery cycle, assess the potential bottlenecks of the long-cycle customized materials, and generate a supply assurance report as the assessment result based on the potential bottlenecks.

[0033] Furthermore, step S35 includes:

[0034] S351: Pre-configure the supply shortage judgment rule set and the delivery delay judgment rule set;

[0035] S352: Compare the production capacity with the demand for the long-cycle customized materials to obtain a production capacity comparison result;

[0036] S353: Compare the delivery cycle with the required delivery time of the long-cycle customized material to obtain a delivery cycle comparison result;

[0037] S354: Based on the production capacity comparison results and the delivery cycle comparison results, and in conjunction with the supply shortage judgment rule set and the delivery delay judgment rule set, determine whether there is a supply shortage or delivery delay.

[0038] S355: If there is a supply shortage or delivery delay, analyze the impact of the supply shortage or delivery delay on the overall product delivery cycle and cost, identify long-lead-time customized materials with a high degree of impact as key potential bottlenecks, and generate a supply assurance report as the assessment result.

[0039] Furthermore, in step S354,

[0040] The production capacity comparison result includes at least a first difference between the production capacity and the demand for the long-cycle customized materials, and a capacity satisfaction status, wherein the capacity satisfaction status is sufficient or insufficient, and the capacity satisfaction status is determined based on the first difference.

[0041] The delivery cycle comparison result includes at least a second difference between the delivery cycle and the required delivery time of the long-cycle customized material, and a cycle compliance status, wherein the cycle compliance status is compliant or delayed, and the cycle compliance status is determined based on the second difference.

[0042] The supply shortage judgment rule set includes at least the rule that if the capacity is insufficient, it is judged as a supply shortage; the delivery delay judgment rule set includes at least the rule that if the cycle is delayed and the expected completion date is later than the customer's required date by more than a preset threshold, it is judged as a delivery delay.

[0043] Furthermore, in step S4, the assessment results at least include information on the supply risk level of long-cycle customized materials and corresponding suggested countermeasures. Step S4 includes:

[0044] S41: Pre-configure flexible preparation strategy rule sets;

[0045] S42: Combining the flexible preparation strategy rule set, the supply risk level information and the suggested response measures are mapped into a production window soft reservation plan, an upstream material pre-communication plan, and a special mold preparation plan;

[0046] S43: Execute the flexible preparation according to the production window soft reservation plan, the upstream material pre-communication plan, and the special mold preparation plan.

[0047] Furthermore, step S42 includes:

[0048] S421: Configure parameter templates for production window soft reservation, upstream material pre-communication, and special mold preparation respectively;

[0049] S422: When mapping the supply risk level information and the suggested response measures, adjust each parameter template according to the flexible preparation strategy rule set; the flexible preparation strategy rule set includes at least the rules for adjusting the parameter values ​​in the parameter templates according to the supply risk level information and the suggested response measures;

[0050] S423: Based on the adjusted parameter templates, instantiate and generate the production window soft reservation plan, the upstream material pre-communication plan, and the special mold preparation plan.

[0051] Secondly, an intelligent inventory control and management system based on a supply chain collaboration mechanism is provided for implementing any of the above methods, the system comprising:

[0052] Generation module: Receives preliminary demand forecasts from downstream partners and generates demand intention information that includes the probability weights of customized components and the potential demand range based on the preliminary demand forecasts;

[0053] Synchronization module: Synchronizes the demand intention information with the upstream supplier's production planning system in real time;

[0054] Evaluation module: After receiving the demand intention information from the upstream supplier's production planning system, the module evaluates the impact of the demand intention information on future production resources and obtains the evaluation results.

[0055] Collaborative adjustment module: Based on the assessment results, make flexible preparations in advance, including soft reservation of production windows, pre-communication with upstream materials, and preparation of special molds.

[0056] Beneficial Effects: This application proposes an intelligent inventory control and management method and system based on a supply chain collaboration mechanism. By receiving preliminary demand forecasts from downstream partners and generating demand intention information that includes the probability weights of customized components and the potential demand range, it solves the problem of inconsistent granularity of demand information caused by the ambiguity of preliminary demand forecasts in existing technologies. This method synchronizes the demand intention information to the production planning system of upstream suppliers in real time, enabling upstream suppliers to obtain potential downstream demand in advance, overcoming the drawbacks of information lag and asymmetry. After receiving the demand intention information, the method further assesses its impact on future production resources, obtaining evaluation results that identify potential production bottlenecks and supply risks, avoiding blind production and material mismatch. Finally, based on the evaluation results, the method makes flexible preparations in advance, including soft reservation of production windows, pre-communication with upstream materials, and preparation of dedicated molds, effectively addressing the uncertainty of customized component supply and avoiding the dilemma of standard component backlog and customized component shortage. Through the above technical solutions, this application can significantly improve the collaborative efficiency of the supply chain and the ability to cope with uncertainties. It effectively solves the problems of material structural deviation, production and delivery obstruction and increased operating costs caused by ambiguous demand in the existing technology, realizes lean production and just-in-time delivery, and brings significant economic benefits and competitive advantages to enterprises. Attached Figure Description

[0057] Figure 1 This is a flowchart of an intelligent inventory control and management method based on a supply chain collaboration mechanism proposed in this application.

[0058] Figure 2This is a structural diagram of an intelligent inventory control and management system based on a supply chain collaboration mechanism proposed in this application.

[0059] Figure 3 This is a framework diagram of an intelligent inventory control and management system based on a supply chain collaboration mechanism proposed in this application.

[0060] Labeling Explanation: 201, Generation Module; 202, Synchronization Module; 203, Evaluation Module; 204, Collaborative Adjustment Module. Detailed Implementation

[0061] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and marked in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0062] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0063] Please refer to Figure 1 A smart inventory control and management method based on supply chain collaboration mechanism, the method includes the following steps:

[0064] S1: Receive preliminary demand forecasts from downstream partners and generate demand intention information that includes the probability weights of customized components and the potential demand range based on the preliminary demand forecasts;

[0065] S2: Synchronize demand intention information with the upstream supplier's production planning system in real time;

[0066] S3: After receiving demand intention information from the upstream supplier's production planning system, assess the impact of the demand intention information on future production resources and obtain the assessment results.

[0067] S4: Based on the assessment results, make flexible preparations in advance, including soft reservation of production windows, pre-communication with upstream materials, and preparation of special molds.

[0068] In practice, downstream partners can submit preliminary demand forecasts in various ways. For example, they can manually enter the project name, expected start time, and a preliminary description of the required customized products through a web-based collaborative platform. These descriptions may include placeholder codes such as "general-purpose control module" or "configuration module to be determined," along with a preliminary quantity estimate. Alternatively, the downstream partner's ERP system can automatically send preliminary demand data to the inventory management system of this application via an API interface, periodically or when triggered by specific events. This data may be transmitted in unstructured text, semi-structured XML, or JSON format. Upon receiving these preliminary demand forecasts, the system of this application initiates an internal processing flow. This flow first performs preliminary parsing and standardization of the received data, for example, mapping different placeholder codes to internally predefined categories of customized components. Subsequently, the system analyzes these preliminary demands according to preset rules to assess the probability weight and potential demand range of the customized components included. For example, for a requirement described as a "general-purpose control module", the system may determine, based on historical data or preset business logic, that the probability of it containing specific customized interfaces is 0.6, and the number of potential requirements is between 50 and 100.

[0069] After generating demand intention information, the system in this application needs to synchronize it with the upstream supplier in a timely manner. One approach is for the system to establish a direct data link with the upstream supplier's production planning system, for example, using a message queue service (such as Kafka or RabbitMQ), to encapsulate the demand intention information into standardized data packets and push them to the upstream supplier's system in near real-time. The upstream supplier's system continuously listens for these messages and processes them immediately upon receipt. Another approach is for the system to periodically (e.g., hourly or daily) batch-package all newly added or updated demand intention information and send it to a designated directory of the upstream supplier via a secure file transfer protocol (such as SFTP). The upstream supplier's production planning system will be configured with a scheduled task to automatically pull files from this directory and import them into its internal database. This real-time synchronization mechanism ensures that the upstream supplier can obtain potential demand signals from downstream suppliers as early as possible, providing a basis for its subsequent production planning.

[0070] Upon receiving demand intention information, the upstream supplier's production planning system initiates a resource impact assessment process. One implementation involves the system first matching the probability weights and potential demand range of customized components in the demand intention information with its own Bill of Materials (BOM) to identify potentially critical raw materials, semi-finished products, and required production processes and equipment. Subsequently, the system runs a simulation analysis module, overlaying these potential demands onto the existing production plan and resource load. For example, the system analyzes whether fulfilling the demand for a customized component would lead to capacity bottlenecks on a specific production line, overloading of critical equipment, or insufficient inventory of specific raw materials. The assessment results can be a detailed report, including potential resource conflict points, capacity gaps, material shortage risks, and the potential impact on the existing production plan.

[0071] After obtaining the assessment results, upstream suppliers will take corresponding flexible preparation measures based on these results. One approach is that if the assessment results indicate that the demand for a customized component may lead to capacity constraints on a specific production line, the system will suggest "softly reserving" a portion of the production window in future production plans. This soft reservation is not a rigid scheduling, but rather marking a period of flexible time in the production plan that can be used to cope with potential customized demands, preventing this period from being completely occupied by other fixed orders. Simultaneously, for critical long-lead-time customized materials identified in the assessment, the system will trigger an "upstream material pre-communication" process. For example, the purchasing department will proactively contact second- or third-tier suppliers to inform them of their potential demand intentions, understand their current production capacity and delivery cycles, and explore the possibility of advance stockpiling or signing flexible supply agreements. Furthermore, if the assessment results indicate that a customized component requires a dedicated mold, and the mold's manufacturing cycle is long, the system will suggest initiating a "dedicated mold preparation" process in advance. This may include preliminary design communication with mold suppliers, obtaining quotations, and even initiating partial mold design or procuring key materials before the demand is fully determined, in order to shorten the final mold manufacturing cycle.

[0072] Compared with existing technologies, the advantages of this application are as follows: First, by introducing the concept of "demand intention information," this application can effectively handle vague or non-refined demands provided by downstream partners, avoiding the problem of traditional systems incorrectly mapping vague demands to standard products. Second, this application achieves real-time synchronization of demand intention information, ensuring that upstream suppliers can obtain potential demand signals as early as possible, thus having more time for planning. Third, this application emphasizes the importance of upstream suppliers conducting resource impact assessments of demand intention information, enabling potential bottlenecks and risks to be identified in advance. Most importantly, this application proposes a "flexible preparation" mechanism, including soft reservation of production windows, pre-communication with upstream materials, and preparation of dedicated molds. These measures enable upstream suppliers to allocate resources and mitigate risks in advance even when demand uncertainty is high, thereby significantly improving the overall flexibility and responsiveness of the supply chain and effectively avoiding problems such as material mismatch, production delays, and increased costs.

[0073] Furthermore, step S1 includes:

[0074] S11: Receive preliminary demand forecasts from downstream partners and continuously monitor changes in the probability weight and potential demand range of customized components in the preliminary demand forecasts.

[0075] S12: Aggregate the monitored changes over a time window to obtain the aggregated probability weights and potential demand ranges for customized components;

[0076] S13: Based on the aggregated probability weights and potential demand range of customized components, analyze the logical relationships between customized components and form demand scenarios from the intention signals of the interrelated customized components.

[0077] S14: Assign comprehensive probability weights and total demand ranges to demand scenarios;

[0078] S15: Based on the comprehensive probability weight, fluctuation range, and the detailed time point of expected demand, assign maturity levels to demand scenarios to generate demand intention information.

[0079] Specifically, step S11 continuously acquires the latest demand forecast data provided by downstream partners and tracks the demand probability weight and potential demand range of customized components involved in the data in real time or near real time. The aim is to promptly capture changing trends in market demand and provide dynamic data support for subsequent decision-making.

[0080] Step S12 summarizes and processes the demand change data monitored over a period of time. To eliminate short-term fluctuations, a moving average filter based on a sliding window can be set. When demand change data enters this moving average filter, the filter calculates the average of the current data point and its N preceding data points, and outputs this average as the smoothed value for the current data point. The value of N can be adjusted according to the actual data characteristics and the required smoothing degree. For example, if the demand change data is updated hourly, N can be set to 24 to eliminate intraday fluctuations. The smoothed data is then transmitted to the weight calculation unit and the demand range analysis unit to generate customized component probability weights and potential demand ranges. The purpose of this method is to smooth the data, reveal long-term trends, and avoid misjudgments caused by instantaneous data fluctuations.

[0081] Step S13 identifies that in actual product configurations or customer needs, multiple customized components do not exist independently, but rather appear in some combination or dependency relationship. For example, some customized components may be complementary, mutually exclusive, or must appear simultaneously. By analyzing these logical relationships, the intent signals of strongly related customized components can be packaged into a "demand scenario," such as a "luxury interior package" or a "high-performance powertrain upgrade." The aim is to shift from the perspective of a single component to the perspective of the overall solution, and to more accurately understand the customer's potential needs.

[0082] Step S14, after forming the demand scenario, no longer evaluates the probability weight and demand range of each customized component individually. Instead, it assigns an overall comprehensive probability weight and total demand range to the entire demand scenario. This comprehensive probability weight can be calculated based on the weights of each component within the scenario, while the total demand range reflects the total demand potential of all relevant components under the scenario. Its purpose is to provide a more macro-level demand signal with greater decision-making value.

[0083] Step S15 assesses the reliability and urgency of each demand scenario. The overall probability weight reflects the likelihood of the scenario occurring; the volatility reflects the stability of the demand forecast for that scenario; and the expected demand refinement timeline indicates when the scenario will translate into confirmed orders. Based on these three dimensions, demand scenarios can be categorized into different maturity levels, such as "high potential to be observed," "medium certainty," and "urgent to be confirmed." The aim is to provide upstream suppliers with more guiding information, enabling them to adopt differentiated and flexible preparation strategies based on demand scenarios at different maturity levels.

[0084] Through the above technical solutions, this application can significantly improve the accuracy and reliability of demand intention information. Continuous monitoring and time window aggregation effectively filter out short-term market noise, making demand forecasting more stable; analyzing the logical correlation of customized components and forming demand scenarios allows for a deeper and more comprehensive understanding of complex customized demands; and the introduction of maturity level assessment makes demand intention information more instructive and actionable. Upstream suppliers can plan production resources and material procurement more rationally based on demand scenarios at different maturity levels, thereby effectively reducing inventory risk and improving the responsiveness and overall collaborative efficiency of the supply chain.

[0085] Furthermore, step S13 includes:

[0086] S131: Construct a knowledge graph of customized components. The nodes and edges between nodes in the knowledge graph represent customized components and the relationships between customized components, respectively. The relationships include at least compatibility, dependency or mutual exclusion between customized components.

[0087] S132: Based on the aggregated probability weights and potential demand ranges of customized components, identify component clusters with related relationships in the aggregated probability weights and potential demand ranges of customized components using a knowledge graph;

[0088] S133: Form a demand scenario from the component cluster.

[0089] In step S131, the nodes of the knowledge graph can be understood as various customized components involved in the supply chain, such as specific chip models, customized casings, and dedicated connectors. The edges between nodes represent the relationships between these customized components, which are key to understanding the interactions between them. For example, relationships can include compatibility (some customized components must or can work together), dependency (the production or use of one customized component depends on the existence of another), or mutual exclusion (some customized components cannot coexist in the same product configuration). By constructing such a knowledge graph, a structured data model can be formed, clearly demonstrating the inherent connections between customized components.

[0090] In step S132, the system no longer simply searches for one-to-one relationships, but is able to identify a set of interrelated customized components. For example, if the knowledge graph shows that customized component A depends on customized component B, and customized component B is compatible with customized component C, then when customized components A, B, and C appear simultaneously in demand forecasting, they may be identified as a component cluster. This identification process utilizes predefined relationships such as compatibility, dependency, or mutual exclusion in the knowledge graph to ensure the accuracy and comprehensiveness of the identification.

[0091] In step S133, a component cluster represents a group of logically closely related customized components that typically appear as a whole in a product configuration or customer requirement. Directly forming these component clusters into a demand scenario ensures that the generated demand scenario is based on real technical relationships and business logic, thereby improving the accuracy and reliability of demand forecasting.

[0092] Furthermore, step S15 includes:

[0093] S151: Pre-configure a business rule set. The business rule set must define at least a priority sequence and condition thresholds. The priority is defined as follows: comprehensive probability weight assessment takes precedence over fluctuation amplitude assessment, and fluctuation amplitude assessment takes precedence over the expected demand refinement time point assessment. The condition thresholds are defined as follows: when the comprehensive probability weight is higher than 0.7, the judgment result is "high potential"; when the fluctuation amplitude is lower than 0.1, the judgment result is "stable"; when the expected demand refinement time point is more than 30 days earlier than the current date, the judgment result is "urgent".

[0094] S152: The comprehensive probability weight, fluctuation range and expected demand are refined into specific time points, and logical judgment is made according to the priority and condition thresholds defined in the business rule set to obtain the judgment result;

[0095] S153: Based on the judgment results, assign maturity levels to demand scenarios to generate demand intention information.

[0096] In step S151, the priority sequence clarifies the order in which various indicators are considered during the evaluation process. For example, the comprehensive probability weight assessment is set to take precedence over the volatility assessment, which in turn takes precedence over the assessment of the expected demand refinement time point. This priority setting ensures that, in multi-dimensional evaluation, the core indicators that have the greatest impact on the demand scenario are given priority first. The condition thresholds set specific judgment criteria for each evaluation indicator. For example, when the comprehensive probability weight is higher than 0.7, it can be judged as "high potential"; when the volatility is lower than 0.1, it can be judged as "stable"; and when the expected demand refinement time point is more than 30 days earlier than the current date, it can be judged as "urgent". These thresholds are preset based on historical data, business experience, or industry standards and are used to transform continuous indicator values ​​into discrete judgment results.

[0097] In step S152, the logical judgment process can be as follows: The business rule executor receives the comprehensive probability weight, fluctuation range, and expected demand refinement time point data from the upstream data processing module. The business rule executor evaluates these data sequentially according to the priority sequence in the rule memory. For example, it first evaluates whether the comprehensive probability weight meets the "high potential" threshold; if so, a preliminary judgment result is generated. Subsequently, based on the preliminary judgment result, it evaluates whether the fluctuation range meets the "stable" threshold and updates the judgment result. Finally, it evaluates whether the expected demand refinement time point meets the "urgent" threshold and updates the judgment result again. Ultimately, the rule executor outputs a data structure containing the final judgment result for use by the downstream decision support system.

[0098] In step S153, if the judgment result shows "high potential," "stable," and "urgent," it may be assigned to the "high maturity" level; if the judgment result is "low potential," "volatile," and "not urgent," it may be assigned to the "low maturity" level. Through this structured allocation method, the final generated demand intention information will contain an objective and accurate maturity level, thereby providing a reliable basis for subsequent supply chain collaborative decisions.

[0099] Furthermore, step S3 includes:

[0100] S31: After receiving demand intention information from the upstream supplier's production planning system, identify long-cycle customized materials provided by key second- or third-tier suppliers based on the demand intention information.

[0101] S32: Transform demand intention information into the demand quantity and delivery time of long-cycle customized materials;

[0102] S33: Send inquiry instructions regarding demand and delivery time to key Tier 2 or Tier 3 suppliers;

[0103] S34: Receive production capacity and delivery cycle information from key Tier 2 or Tier 3 suppliers in accordance with query instructions;

[0104] S35: Based on production capacity and delivery cycle, assess potential bottlenecks for long-lead-time customized materials, and generate a supply assurance report as the assessment result based on the potential bottlenecks.

[0105] In step S31, long-cycle customized materials refer to materials or components with long production or procurement cycles that typically require customization based on specific product needs. These materials are often supplied by second- or third-tier suppliers deeper within the supply chain, and their supply status has a critical impact on the overall production plan. The identification process can be based on pre-defined bill of materials (BOM) analysis, supplier database queries, and material attribute tags.

[0106] In step S32, the probability weights and potential demand ranges of customized components contained in the demand intention information are converted into specific demand quantities and expected delivery times for particular long-cycle customized materials. This conversion process may involve quantitative analysis and time planning of the demand intention information.

[0107] In step S33, the query instruction typically includes detailed specifications of the required materials, the required quantity, and the expected delivery time.

[0108] In step S34, the feedback information typically includes the supplier’s current production capacity, i.e., the maximum quantity that can be produced or supplied within a given time, and its estimated delivery cycle, i.e. the time required from order confirmation to material delivery.

[0109] In step S35, a potential bottleneck refers to a situation where a supplier's production capacity is insufficient to meet demand, or its delivery cycle cannot meet the expected delivery time. Once a potential bottleneck is identified, the system generates a supply assurance report that details the type and severity of the bottleneck and its potential impact on production planning, and outputs it as an assessment result.

[0110] The proposed solution, through the aforementioned steps, enables in-depth and forward-looking supply risk assessment of critical, long-lead-time customized materials in the supply chain. Specifically, S31 identifies the long-lead-time customized materials with the greatest impact on production, avoiding the need to assess all materials equally, thus improving assessment efficiency and focus. S32 transforms abstract demand intentions into specific material requirements and delivery times, laying a quantitative foundation for subsequent communication with suppliers. S33 and S34 proactively exchange information with key second- or third-tier suppliers to obtain the most direct and accurate production capacity and delivery cycle data, compensating for the shortcomings of assessments relying solely on internal data. Finally, S35, based on this real-time feedback data, accurately identifies potential supply bottlenecks and generates a guiding supply assurance report. It is precisely this bottom-up, critical material-focused assessment mechanism that enables upstream suppliers to grasp the deep-seated potential risks in the supply chain earlier and more accurately, thereby providing solid data support for subsequent flexible preparations.

[0111] Furthermore, step S35 includes:

[0112] S351: Pre-configure the supply shortage judgment rule set and the delivery delay judgment rule set;

[0113] S352: Compare production capacity with the demand for long-lead-time customized materials to obtain production capacity comparison results;

[0114] S353: Compare the delivery cycle with the required delivery time for long-cycle customized materials to obtain the delivery cycle comparison results;

[0115] S354: Based on the comparison results of production capacity and delivery cycle, and combined with the rule set for judging supply shortages and the rule set for judging delivery delays, determine whether there is a supply shortage or delivery delay.

[0116] S355: If there is a supply shortage or delivery delay, analyze the impact of the supply shortage or delivery delay on the overall product delivery cycle and cost, identify long-lead-time customized materials with a high degree of impact as key potential bottlenecks, and generate a supply assurance report as the assessment result.

[0117] Specifically, before the system goes live, business experts or system administrators define a series of logical conditions and thresholds to determine whether a supply shortage or delivery delay exists. For example, the supply shortage judgment rule set might include a rule that states "a supply shortage is determined when the supplier's promised production capacity is X% lower than the demand"; the delivery delay judgment rule set might include a rule that states "a delivery delay is determined when the supplier's promised delivery cycle is Y days later than the required delivery time". These rule sets aim to provide objective and quantifiable judgment criteria, avoiding subjective assumptions.

[0118] The system automatically obtains feedback on production capacity and demand for long-lead-time customized materials from key second- or third-tier suppliers and performs quantitative comparisons. For example, it can calculate the difference or ratio between production capacity and demand to intuitively reflect whether capacity is sufficient. Similarly, it compares delivery cycles with the required delivery time for long-lead-time customized materials to obtain delivery cycle comparison results. This involves the system obtaining and comparing the delivery cycles reported by suppliers with the expected required delivery time, such as calculating the time difference between the two to determine if delays exist.

[0119] The system takes the comparison results as input and performs logical reasoning and judgment based on a preset set of rules. For example, if the production capacity comparison result shows insufficient capacity and meets a certain condition in the supply shortage judgment rule set, the system will determine that there is a supply shortage. If the delivery cycle comparison result shows a delay and meets a certain condition in the delivery delay judgment rule set, the system will determine that there is a delivery delay.

[0120] Furthermore, for identified supply shortages or delivery delays, the system simulates their impact on key indicators such as final product delivery time, production costs, and customer satisfaction. The analysis of the degree of impact can be based on preset priorities, cost models, or historical data. Long-lead-time customized materials that have the greatest impact on the overall delivery cycle or cost will be marked as key potential bottlenecks and included as core content in the supply assurance report. This report will detail the type of potential bottleneck, its degree of impact, the materials involved, and recommended responses, thus providing clear guidance for subsequent flexibility preparation.

[0121] In one specific embodiment, suppose a manufacturing company is producing an industrial device that includes a variety of customized components. Among them, the dedicated chip for the core control unit and the customized housing for the high-precision sensors are materials that require long-cycle customization.

[0122] The system received a notification from Supplier A regarding a two-week delay in delivery due to adjustments to the dedicated chip production line, and a notification from Supplier B regarding a 10% increase in the price of raw materials for customized casings.

[0123] Based on these notifications, the system determined that there were delivery delays for the dedicated chips and increased costs for the customized casings.

[0124] Further analysis revealed that the delay in the delivery of the dedicated chip would extend the overall equipment delivery cycle by two weeks and potentially trigger late delivery penalties. The increased cost of the customized casing would directly lead to a rise in the total equipment cost. Quantitative analysis showed that the delay in the dedicated chip resulted in a 14-day extension of the delivery cycle, with a potential penalty of 0.5% of the total equipment price; the increased cost of the customized casing led to a 0.2% increase in the total equipment cost.

[0125] Based on the above analysis, the system identified that the delivery delay of dedicated chips has a significant impact on the overall product delivery cycle, and the increased cost of customized casings has a significant impact on the overall product cost. Therefore, both dedicated chips and customized casings are identified as key potential bottlenecks.

[0126] For the specific chip, the system evaluated supplier A's production capacity, inventory levels, and the feasibility of alternative suppliers. The evaluation results showed that supplier A's production capacity fluctuated, and there were no other qualified alternative suppliers.

[0127] For customized casings, the system evaluates supplier B's raw material procurement channels, price stability, and the feasibility of alternative materials or suppliers. The evaluation results show that supplier B has a single raw material procurement channel, but there is another supplier C with production capabilities.

[0128] Based on the assessment results, the system generates a supply assurance report. The report includes the following: the supply assurance level for the dedicated chip is "medium risk," and it is recommended to sign a long-term supply agreement with supplier A and explore the possibility of reserving safety stock; the supply assurance level for the customized casing is "low risk," and it is recommended to establish a backup supply relationship with supplier C to cope with price fluctuations.

[0129] Furthermore, in step S354,

[0130] The comparison results of production capacity include at least the first difference between production capacity and the demand for long-cycle customized materials, and the capacity satisfaction status, which is either sufficient or insufficient. The capacity satisfaction status is determined based on the first difference.

[0131] The delivery cycle comparison result includes at least a second difference between the delivery cycle and the required delivery time for long-cycle customized materials, and the cycle compliance status, which is either compliant or delayed, wherein the cycle compliance status is determined based on the second difference.

[0132] The supply shortage judgment rule set includes at least the rule: if the capacity satisfaction status is insufficient, it is judged as a supply shortage; the delivery delay judgment rule set includes at least the rule: if the cycle compliance status is delayed, and the expected completion date is later than the customer's required date by more than a preset threshold, it is judged as a delivery delay.

[0133] Specifically, the composition of the production capacity comparison results is further refined. It not only includes the first difference between production capacity and the demand for long-cycle customized materials, but also introduces the capacity satisfaction status. This capacity satisfaction status is defined as "sufficient" or "insufficient," and is determined directly based on the first difference. For example, when the first difference is positive (i.e., production capacity is greater than demand), the capacity satisfaction status can be determined as "sufficient"; when the first difference is negative (i.e., production capacity is less than demand), the capacity satisfaction status can be determined as "insufficient."

[0134] The composition of the delivery cycle comparison results is also clearly defined, including at least a second difference between the delivery cycle and the required delivery time for long-cycle customized materials, as well as the cycle compliance status. This cycle compliance status is defined as "compliant" or "delayed," and is determined based on the second difference. For example, when the second difference is negative or zero (i.e., the delivery cycle is earlier than or equal to the required delivery time), the cycle compliance status can be determined as "compliant"; when the second difference is positive (i.e., the delivery cycle is later than the required delivery time), the cycle compliance status can be determined as "delayed."

[0135] In practical applications, the supply shortage judgment rule set is explicitly defined, and it must contain at least one core rule: if the capacity satisfaction status is judged as "insufficient," the system will directly determine that a supply shortage exists. Furthermore, the delivery delay judgment rule set also contains at least one core rule: if the cycle commensurate status is judged as "delayed," and the expected completion date is later than the customer's requested date by more than a preset threshold, the system will determine that a delivery delay exists. This preset threshold can be configured according to actual business needs, such as 3 days, 7 days, or longer, to distinguish between minor and severe delays.

[0136] Furthermore, in step S4, the assessment results include at least the supply risk level information for long-cycle customized materials and corresponding recommended countermeasures. Step S4 includes:

[0137] S41: Pre-configure flexible preparation strategy rule sets;

[0138] S42: Combining the flexible preparation strategy rule set, supply risk level information and suggested countermeasures are mapped into a production window soft reservation plan, an upstream material pre-communication plan, and a special mold preparation plan;

[0139] S43: Implement flexible preparation based on the production window soft reservation plan, upstream material pre-communication plan, and special mold preparation plan.

[0140] Specifically, the assessment results are not a single, general judgment, but rather detailed information on the supply risk level of long-lead-time customized materials, along with corresponding suggested countermeasures. The supply risk level information can be a quantitative or qualitative assessment of the risk of supply disruption, shortage, or delay faced by specific long-lead-time customized materials, categorized as "high risk," "medium risk," or "low risk," etc. The suggested countermeasures are preliminary solutions automatically or manually recommended by the system based on different risk levels and specific circumstances, such as "increasing safety stock," "finding alternative suppliers," or "expediting orders."

[0141] To translate these detailed assessment results into actionable flexible preparedness, this application pre-configures a set of flexible preparedness strategy rules. This set of rules is a predefined set of logical rules that guides the generation of specific flexible preparedness plans based on different supply risk levels and recommended responses. For example, the rule set could define, "If the risk level is high and the recommended response is to increase safety stock, then generate a pre-communication plan for upstream materials containing specific quantities and time points."

[0142] Based on this, and combined with the aforementioned flexible preparation strategy rule set, the supply risk level information and the suggested countermeasures are mapped to a production window soft reservation plan, an upstream material pre-communication plan, and a dedicated mold preparation plan. This mapping process, based on the rule set's automated or semi-automated conversion, ensures the targeting and effectiveness of flexible preparation. The production window soft reservation plan can specify the reserved production capacity for specific products or components within a future time period; the upstream material pre-communication plan can clarify which upstream suppliers need to be communicated with in advance regarding which materials, including quantities, delivery dates, and alternative solutions; and the dedicated mold preparation plan can indicate whether the procurement, design, or production process of dedicated molds needs to be initiated in advance.

[0143] Finally, based on the generated production window soft reservation plan, upstream material pre-communication plan, and dedicated mold preparation plan, the flexible preparation is executed. This means that flexible preparation is no longer a vague instruction, but is driven by a specific and actionable plan, thereby improving the efficiency and accuracy of execution.

[0144] Furthermore, step S42 includes:

[0145] S421: Configure parameter templates for production window soft reservation, upstream material pre-communication, and special mold preparation respectively;

[0146] S422: When mapping supply risk level information and recommended response measures, adjust each parameter template according to the flexible preparation strategy rule set; the flexible preparation strategy rule set shall at least include rules for adjusting parameter values ​​in the parameter templates according to supply risk level information and recommended response measures.

[0147] S423: Based on the adjusted parameter templates, instantiate and generate the production window soft reservation plan, upstream material pre-communication plan, and special mold preparation plan.

[0148] Specifically, in step S421, the parameter template can be understood as a predefined, configurable structure that contains the various parameters required to generate a specific plan, along with their default values ​​or value ranges. For example, the parameter template for soft reservation of the production window may include parameters such as reservation duration, reservation ratio, and effective date; the parameter template for upstream material pre-communication may include parameters such as communication frequency, focus of communication content, and target supplier range; and the parameter template for special mold preparation may include parameters such as mold type, preparation quantity, and start time. Its purpose is to provide a standardized input structure and adjustable benchmark for generating flexible preparation plans.

[0149] In step S422, the flexible preparation strategy rule set can be understood as a series of preset logical judgments and operational instructions used to guide how to modify the parameter values ​​in the parameter template based on specific supply risk level information and suggested countermeasures. For example, if the supply risk level is "high risk" and the suggested countermeasure is "emergency procurement," the rule set may instruct the increase of the reservation period for soft reservations in the production window, the increase of the communication frequency for upstream material pre-communication, and the advancement of the start time for special mold preparation. The purpose is to achieve dynamic adjustment and personalized generation of the flexible preparation plan to accurately respond to different risk scenarios.

[0150] In step S423, instantiation refers to using the adjusted parameter template as a blueprint, filling in specific parameter values, and thus generating an executable and detailed flexible preparation plan. For example, the adjusted production window soft reservation parameter template might have a reservation duration of "30 days," a reservation ratio of "20%," and an effective date of "T+7," where T represents the "base date" or "trigger date" used as the starting point for time calculation. This generates a specific production window soft reservation plan. The purpose is to transform abstract strategies and adjustments into concrete and actionable plans.

[0151] Please refer to Figure 2 , Figure 3 A smart inventory control and management system based on a supply chain collaboration mechanism, used to implement any of the above methods, the system comprising:

[0152] Generation module 201: Receives preliminary demand forecasts from downstream partners and generates demand intention information that includes the probability weights of customized components and the potential demand range based on the preliminary demand forecasts;

[0153] Synchronization module 202: Synchronizes demand intention information with the upstream supplier's production planning system in real time;

[0154] Evaluation Module 203: After receiving demand intention information from the upstream supplier's production planning system, evaluate the impact of the demand intention information on future production resources and obtain the evaluation results;

[0155] Collaborative Adjustment Module 204: Based on the assessment results, make flexible preparations in advance, including soft reservation of production windows, pre-communication with upstream materials, and preparation of special molds.

[0156] Specifically, the generation module 201 can be a software service deployed on a server, configured to receive preliminary demand forecasts from downstream partners through various interfaces. For example, this module can provide a user interface for downstream partners to manually input preliminary demand data; alternatively, it can expose an API interface to receive structured or semi-structured data from downstream partners' ERP systems. Upon receiving the preliminary demand forecasts, the processor within the generation module 201 performs preliminary parsing of these non-refined demands based on preset business rules or basic algorithms. For instance, through simple text matching or keyword recognition, it maps the vague descriptions in the preliminary demands to internally defined customized component categories. Subsequently, the module assigns a preliminary probability weight to the identified customized components based on historical sales data or industry averages and estimates a potential demand range. This generates demand intention information containing the probability weights of customized components and the potential demand range.

[0157] The synchronization module 202 is responsible for synchronizing the demand intention information generated by the generation module to the upstream supplier's production planning system in real time. The method for synchronizing the demand intention information to the upstream supplier's production planning system in real time has been described in the above embodiments. It should be emphasized that the synchronization module of this application is configured to perform the above functions. This module can be implemented as a message queue client, encapsulating the demand intention information into a standard format message and publishing it to a preset message queue for the upstream supplier's system to subscribe to and consume. Alternatively, the synchronization module 202 can also be configured to periodically upload the demand intention information file to a shared directory specified by the upstream supplier via a Secure File Transfer Protocol (SFTP). These methods ensure that the demand intention information can be transmitted to the upstream supplier in a timely and accurate manner, providing early signals for its subsequent production planning.

[0158] In practical applications, the assessment module 203 is deployed within the upstream supplier's production planning system. Its main function is to assess the impact of received demand intention information on future production resources. The above embodiments have already described a method for assessing the impact of the demand intention information on future production resources after the upstream supplier's production planning system receives the demand intention information, and obtaining the assessment results. It should be emphasized that the assessment module 203 of this application is configured to perform the above functions. This module can be configured to perform a preliminary comparison between the received demand intention information and the upstream supplier's own bill of materials and current production plan. For example, through simple inventory queries and capacity load analysis, it can identify potentially affected key materials or production lines. The assessment result can be a preliminary resource utilization forecast, for example, indicating which general-purpose material inventories may decrease due to potential customized demand, or which production periods may face higher loads. Its purpose is to provide basic risk identification for subsequent flexibility preparation.

[0159] Furthermore, the collaborative adjustment module 204 guides upstream suppliers to make flexible preparations in advance based on the evaluation results obtained by the evaluation module. The above embodiments have already described methods for making flexible preparations in advance based on the evaluation results, including soft reservation of production windows, pre-communication with upstream materials, and preparation of dedicated molds. It is important to emphasize that the collaborative adjustment module 204 of this application is configured to perform the above functions. This module can be a decision support tool integrated into a production planning system, providing users with preset flexible preparation suggestions based on the potential resource impact identified in the evaluation results. For example, if the evaluation results show that a production line may face a potential increase in load, the collaborative adjustment module will suggest manually marking a "soft reservation" period in the production plan for contingency purposes. For materials that may be involved, the module will prompt purchasing personnel to conduct "pre-communication with upstream materials," for example, by making initial contact with suppliers via telephone or email to understand their approximate supply capacity. If the evaluation results suggest that dedicated molds may be needed, the module will suggest initiating a preliminary "dedicated mold preparation" process, for example, by conducting market research or preliminary price inquiries. These flexible preparation measures aim to provide a basic response framework to address the uncertainty of future demand.

[0160] The intelligent inventory control and management system based on supply chain collaboration mechanism proposed in this application effectively solves the challenges faced by traditional collaborative inventory management systems in handling the early, ambiguous demands of highly customized products through its modular design. Traditional systems often incorrectly map ambiguous demands onto standard products, leading to structural material deviations and production delivery delays. The system in this application transforms preliminary demands into structured demand intention information through a generation module 201, enabling upstream suppliers to understand potential downstream customized demands earlier and more accurately. A synchronization module 202 ensures timely information transmission, while an evaluation module 203 can identify potential resource bottlenecks and risks in advance. Most importantly, a collaborative adjustment module 204 can guide upstream suppliers to make flexible preparations in advance based on the evaluation results, including soft reservation of production windows, pre-communication with upstream materials, and preparation of dedicated molds. Compared with existing technologies, the system in this application can more effectively cope with demand uncertainty, significantly improve the overall flexibility and responsiveness of the supply chain, thereby avoiding problems such as material mismatch, production delays, and increased costs, providing an innovative solution for the supply chain management of highly customized products.

[0161] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0162] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A smart inventory control and management method based on a supply chain collaboration mechanism, characterized in that, The method includes the following steps: S1: Receive preliminary demand forecasts from downstream partners, and generate demand intention information including customized component weights and potential demand ranges based on the preliminary demand forecasts; Step S1 includes: S11: Receive preliminary demand forecasts from downstream partners and continuously monitor changes in the weighting of customized component demand and the potential demand range in the preliminary demand forecasts; S12: Aggregate the monitored changes over a time window to obtain the aggregated weights of customized components and the scope of potential demand; S13: Based on the aggregated weights of customized components and the scope of potential demand, analyze the logical relationships between customized components and form demand scenarios from the intention signals of the interrelated customized components. S14: Assign a comprehensive weight and a total demand range to the aforementioned demand scenario; S15: Based on the comprehensive weight, fluctuation range, and the expected demand refinement time point, assign maturity levels to the demand scenarios to generate the demand intention information; the fluctuation range is the fluctuation range of the total demand range; the expected demand refinement time point is the time point at which the demand scenario is transformed into a definite order. S2: Synchronize the aforementioned demand intention information with the upstream supplier's production planning system in real time; S3: After receiving the demand intention information in the production planning system of the upstream supplier, assess the impact of the demand intention information on future production resources and obtain the assessment result; the future production resources are long-cycle customized materials provided by second- or third-tier suppliers. Step S3 includes: S31: After receiving the demand intention information from the upstream supplier's production planning system, the system identifies long-cycle customized materials provided by second- or third-tier suppliers based on the demand intention information. S32: Transform the demand intention information into the demand quantity and delivery time of the long-cycle customized materials; S33: Send the query instructions for the required quantity and the delivery time to the second- or third-tier supplier; S34: Receive production capacity and delivery cycle information from Tier 2 or Tier 3 suppliers based on query instructions; S35: Based on the production capacity and delivery cycle, assess the potential bottlenecks of the long-lead-time customized materials, and generate a supply assurance report as the assessment result based on the potential bottlenecks; the potential bottlenecks are the risks of supply shortages or delivery delays of the long-lead-time customized materials. S4: Based on the assessment results, make flexible preparations in advance, including soft reservation of production windows, pre-communication with upstream materials, and preparation of special molds.

2. The intelligent inventory control and management method based on a supply chain collaboration mechanism according to claim 1, characterized in that, Step S13 includes: S131: Construct a knowledge graph of customized components, wherein nodes in the knowledge graph represent customized components, and edges between nodes represent the relationships between customized components, wherein the relationships include at least compatibility, dependency, or mutual exclusion between customized components; S132: Based on the aggregated customized component weights and potential demand range, and using the knowledge graph, identify component clusters with related relationships among the aggregated customized component weights and potential demand ranges; S133: Form the component cluster into a demand scenario.

3. The intelligent inventory control and management method based on a supply chain collaboration mechanism according to claim 1, characterized in that, Step S15 includes: S151: Pre-configure a business rule set. The business rule set defines at least a priority sequence and condition thresholds. The priority is defined as follows: comprehensive weight assessment takes precedence over fluctuation amplitude assessment, and fluctuation amplitude assessment takes precedence over the expected demand refinement time point assessment. The condition thresholds are defined as follows: when the comprehensive weight is higher than 0.7, the judgment result is "high potential"; when the fluctuation amplitude is lower than 0.1, the judgment result is "stable"; when the expected demand refinement time point is 30 days earlier than the current date, the judgment result is "urgent". S152: The comprehensive weight, fluctuation range and expected demand are refined into time points, and logical judgment is made according to the priority and condition threshold defined in the business rule set to obtain the judgment result; S153: Based on the judgment result, assign a maturity level to the demand scenario, thereby generating the demand intention information.

4. The intelligent inventory control and management method based on a supply chain collaboration mechanism according to claim 1, characterized in that, Step S35 includes: S351: Pre-configure the supply shortage judgment rule set and the delivery delay judgment rule set; S352: Compare the production capacity with the demand for the long-cycle customized materials to obtain a production capacity comparison result; S353: Compare the delivery cycle with the required delivery time of the long-cycle customized material to obtain a delivery cycle comparison result; S354: Based on the production capacity comparison results and the delivery cycle comparison results, and in conjunction with the supply shortage judgment rule set and the delivery delay judgment rule set, determine whether there is a supply shortage or delivery delay. S355: If there is a supply shortage or delivery delay, analyze the impact of the supply shortage or delivery delay on the overall product delivery cycle and cost, identify potential bottlenecks in long-lead-time customized materials with a high degree of impact, and generate a supply assurance report as the assessment result.

5. The intelligent inventory control and management method based on a supply chain collaboration mechanism according to claim 4, characterized in that, In step S354, the production capacity comparison result includes at least a first difference between the production capacity and the demand for the long-cycle customized materials, and a capacity satisfaction status, wherein the capacity satisfaction status is sufficient or insufficient, and the capacity satisfaction status is determined based on the first difference. The delivery cycle comparison result includes at least a second difference between the delivery cycle and the required delivery time of the long-cycle customized material, and a cycle compliance status, wherein the cycle compliance status is compliant or delayed, and the cycle compliance status is determined based on the second difference. The supply shortage judgment rule set includes at least the rule that if the capacity is insufficient, it is judged as a supply shortage; the delivery delay judgment rule set includes at least the rule that if the cycle is delayed and the expected completion date is later than the customer's required date by more than a preset threshold, it is judged as a delivery delay.

6. The intelligent inventory control and management method based on a supply chain collaboration mechanism according to claim 1, characterized in that, In step S4, the assessment results include at least the supply risk level information for long-cycle customized materials and corresponding suggested countermeasures. Step S4 includes: S41: Pre-configure flexible preparation strategy rule sets; S42: Combining the flexible preparation strategy rule set, the supply risk level information and the suggested response measures are mapped into a production window soft reservation plan, an upstream material pre-communication plan, and a special mold preparation plan; S43: Execute the flexible preparation according to the production window soft reservation plan, the upstream material pre-communication plan, and the special mold preparation plan.

7. The intelligent inventory control and management method based on a supply chain collaboration mechanism according to claim 6, characterized in that, Step S42 includes: S421: Configure parameter templates for production window soft reservation, upstream material pre-communication, and special mold preparation respectively; S422: When mapping the supply risk level information and the suggested response measures, adjust each parameter template according to the flexible preparation strategy rule set; the flexible preparation strategy rule set includes at least the rules for adjusting the parameter values ​​in the parameter templates according to the supply risk level information and the suggested response measures; S423: Based on the adjusted parameter templates, instantiate and generate the production window soft reservation plan, the upstream material pre-communication plan, and the special mold preparation plan.

8. An intelligent inventory control and management system based on a supply chain collaboration mechanism, characterized in that, The system for implementing the method of any one of claims 1-7 comprises: Generation module: Receives preliminary demand forecasts from downstream partners and generates demand intention information including customized component weights and potential demand ranges based on the preliminary demand forecasts; The generation module is used to: receive preliminary demand forecasts from downstream partners and continuously monitor changes in the demand weights and potential demand ranges of customized components in the preliminary demand forecasts; aggregate the monitored changes within a time window to obtain aggregated customized component weights and potential demand ranges; analyze the logical relationships between customized components based on the aggregated customized component weights and potential demand ranges, and form demand scenarios from the interrelated customized component intention signals; assign a comprehensive weight and a total demand range to the demand scenarios; and assign maturity levels to the demand scenarios based on the comprehensive weights, fluctuation ranges, and expected demand refinement time points, thereby generating the demand intention information; the fluctuation range is the fluctuation range of the total demand range; and the expected demand refinement time point is the time point at which the demand scenario is transformed into a confirmed order. Synchronization module: Synchronizes the demand intention information with the upstream supplier's production planning system in real time; Evaluation module: After receiving the demand intention information from the upstream supplier's production planning system, the module evaluates the impact of the demand intention information on future production resources and obtains the evaluation result; the future production resources are long-cycle customized materials provided by second- or third-tier suppliers. The assessment module is also used to, after receiving the demand intention information from the upstream supplier's production planning system, identify long-lead-time customized materials provided by second- or third-tier suppliers based on the demand intention information; convert the demand intention information into the demand quantity and delivery time of the long-lead-time customized materials; send query instructions for the demand quantity and delivery time to the second- or third-tier suppliers; receive the production capacity and delivery cycle feedback from the second- or third-tier suppliers based on the query instructions; assess the potential bottlenecks of the long-lead-time customized materials based on the production capacity and delivery cycle, and generate a supply assurance report as the assessment result based on the potential bottlenecks; the potential bottlenecks are the supply shortages or delivery delay risks of the long-lead-time customized materials. Collaborative adjustment module: Based on the assessment results, make flexible preparations in advance, including soft reservation of production windows, pre-communication with upstream materials, and preparation of special molds.

Images