A device manufacturing progress simulation method and system based on data mining technology

Abstract

The application discloses a kind of equipment manufacturing progress simulation method and system based on data mining technology, it is related to equipment manufacturing progress monitoring field, the method includes: from the multiple business modules involved in equipment manufacturing, business data is collected regularly, and the business data is cleaned and standardized, to form standard data assets;Based on the standard data assets, the virtual progress and state of the procurement stage, production stage, delivery stage and settlement stage in the equipment manufacturing process are calculated respectively;According to the virtual progress of the procurement stage, production stage, delivery stage and settlement stage, the dynamic weight coefficient of each stage is combined to calculate the overall virtual progress of equipment manufacturing;Monitor the state change of each stage, when the preset reminder trigger condition is met, generate and send progress reminder information.Through data mining and intelligent algorithm, real-time, accurate, quantitative simulation of equipment manufacturing progress is realized.

Description

Technical Field

[0001] This invention relates to the field of equipment manufacturing progress monitoring, and in particular to a method and system for simulating equipment manufacturing progress based on data mining technology. Background Technology

[0002] Large-scale equipment manufacturing is typically characterized by long cycles, numerous components, complex production processes, and a multitude of process documents. Both manufacturers and purchasers desire real-time and accurate monitoring of the overall equipment manufacturing progress for production coordination, resource allocation, and delivery schedule management. However, traditional equipment manufacturing schedule management suffers from several significant problems due to fragmented information, large data volumes, and numerous business processes, often relying on manual experience for schedule estimation and status tracking. 1. Poor timeliness: Traditional methods rely on manual collection, organization and reporting of progress information on a regular basis. The information update cycle is long and it is difficult to reflect the dynamic changes in the manufacturing process in a timely manner, resulting in a lag in progress feedback. 2. Low accuracy: Due to the lack of systematic and quantitative analysis methods, manual estimation is often highly subjective and cannot accurately reflect the actual completion status of each stage. In particular, when multiple stages are carried out in parallel and overlapping, progress assessment is prone to deviation. 3. Inability to perform quantitative analysis: Traditional management models make it difficult to quantify and comprehensively evaluate the progress at each stage, and even more difficult to establish a correlation model between progress and key factors such as materials, costs, and time, which limits the level of refinement and scientific management of progress. 4. Inadequate status tracking and reminder mechanisms: During the manufacturing process, there is a lack of automated and intelligent identification and reminder mechanisms for status changes at each stage (such as procurement arrival, production completion, shipment receipt, settlement completion, etc.). Important node information often relies on manual transmission, which is prone to omissions or delays.

[0003] With the improvement of enterprise informatization, various business systems (such as ERP, MES, SCM, etc.) have accumulated a large amount of manufacturing process data. However, this data is usually stored in a scattered manner and in different formats, failing to be effectively integrated and used for progress analysis and decision support. Therefore, how to extract valuable information from massive and heterogeneous business data and build a simulation and management system that can reflect the equipment manufacturing progress in real time, accurately and quantitatively has become an urgent technical problem to be solved in the field of manufacturing management.

[0004] To this end, this invention proposes a method for simulating equipment manufacturing progress based on data mining technology. The aim is to achieve digital, automated, and visualized control of equipment manufacturing progress through data collection, cleaning, integration, and intelligent analysis, thereby improving the management efficiency and transparency of the manufacturing process. Summary of the Invention

[0005] This invention provides a method for simulating equipment manufacturing progress based on data mining technology, comprising: Step 1: Collect business data from multiple business modules involved in equipment manufacturing at regular intervals, and clean and standardize the business data to form standard data assets; Step 2: Based on the standard data assets, calculate the virtual progress and status of the procurement, production, delivery and settlement stages in the equipment manufacturing process, respectively. Step 3: Based on the virtual progress of the procurement stage, production stage, delivery stage and settlement stage, and combined with the dynamic weight coefficient of each stage, calculate the overall virtual progress of equipment manufacturing. Step 4: Monitor the status changes at each stage, and generate and send progress reminder information when the preset reminder trigger conditions are met.

[0006] The equipment manufacturing progress simulation method based on data mining technology, as described above, involves periodically collecting business data from multiple business modules involved in equipment manufacturing, and cleaning and standardizing the business data to form standard data assets. Specifically, this process includes the following sub-steps: Define and access business document data that serves as the basis for progress calculation from multiple business modules involved in equipment manufacturing; The data from the incoming business documents is cleaned and standardized. The processed standardized data is categorized and stored in the database according to its business stage and data theme.

[0007] The equipment manufacturing progress simulation method based on data mining technology, as described above, calculates the virtual progress and status of the procurement, production, delivery, and settlement stages of the equipment manufacturing process based on the standard data assets. This is specifically divided into the following sub-steps: Introduce price factors and calculate the virtual progress and status of the procurement stage by combining the demand and purchase volume of main materials; Calculate the virtual progress and status of the production stage based on the material requisition process; Based on the shipment tracking data, a hybrid entropy reduction algorithm is used to calculate the virtual progress of the shipment stage and determine its current status. The virtual progress and status of the settlement stage are calculated based on invoicing and payment data.

[0008] The equipment manufacturing progress simulation method based on data mining technology, as described above, calculates the virtual progress of the delivery stage using a hybrid entropy reduction algorithm based on shipment tracking data. This process is specifically divided into the following sub-steps: Based on the continuous process from shipment to confirmation of receipt, five mutually exclusive milestone states are defined; The shipment tracking data is processed to generate three evidence feature vectors. Each evidence feature vector contains five components, which correspond to five predefined milestone states. The three evidence feature vectors are fused into the probability of achieving each milestone state; The probability of achieving each milestone state is fed into the hybrid entropy reduction calculation model to output the virtual progress of the delivery stage.

[0009] The equipment manufacturing progress simulation method based on data mining technology, as described above, includes the following calculation process for the dynamic weight coefficients at each stage: Calculate the data entropy factor, schedule relevance factor, and schedule deviation risk factor for each stage; By combining the above three factors, the initial weight coefficients for each stage are obtained; Based on the game process of competing for contribution to the overall progress in four stages, the initial weight coefficients are optimized and iterated to output the optimal dynamic weight coefficients at the current moment.

[0010] The equipment manufacturing progress simulation method based on data mining technology, as described above, monitors the status changes at each stage and generates and sends progress reminder information when preset reminder trigger conditions are met. This method specifically comprises the following sub-steps: Set reminder trigger conditions and reminder message templates for the macro business status at each stage; Real-time monitoring of changes in business status; if the reminder trigger conditions are met, a progress reminder message is generated based on the defined reminder message template. The generated progress reminder messages are forwarded to the user through a separate messaging service.

[0011] The present invention also provides a device manufacturing progress simulation system based on data mining technology, comprising: a business data processing module, a virtual progress calculation module, a virtual progress fusion module, and a progress reminder module; The business data processing module is used to periodically collect business data from multiple business modules involved in equipment manufacturing, and to clean and standardize the business data to form standard data assets. The virtual progress calculation module is used to calculate the virtual progress and status of the procurement, production, delivery and settlement stages of the equipment manufacturing process based on the standard data assets. The virtual progress fusion module is used to calculate the overall virtual progress of equipment manufacturing based on the virtual progress of the procurement stage, production stage, delivery stage and settlement stage, combined with the dynamic weight coefficient of each stage. The progress reminder module is used to monitor the status changes at each stage. When the preset reminder trigger conditions are met, it generates and sends progress reminder information.

[0012] The beneficial effects achieved by this invention are as follows: Through data mining and intelligent algorithms, real-time, accurate, and quantitative simulation of equipment manufacturing progress is realized; based on multi-source heterogeneous business data, the virtual progress of each stage is automatically calculated, and the overall progress is obtained by dynamic weight fusion, which significantly improves the accuracy and timeliness of progress assessment; at the same time, the system can automatically monitor key status changes and trigger intelligent reminders, effectively solving the problems of information lag, large subjective bias, and inconvenient tracking in traditional manual management, and realizing the digitalization, automation, and visualization of manufacturing progress management. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0014] Figure 1 This is a flowchart of a method for simulating equipment manufacturing progress based on data mining technology, provided in Embodiment 1 of this application; Figure 2 This is a schematic diagram of a device manufacturing progress simulation system based on data mining technology provided in Embodiment 2 of this application. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] Example 1 like Figure 1 As shown, Embodiment 1 of this application provides a method for simulating equipment manufacturing progress based on data mining technology, including: Step S10: Collect business data periodically from multiple business modules involved in equipment manufacturing, and clean and standardize the business data to form standard data assets; Business data is collected periodically from predefined data sources, processed into standardized data, and then stored to form a big data asset layer, which is then used for progress calculations at various stages. This process is divided into the following sub-steps: Step S11: Define and access business document data from multiple business modules involved in equipment manufacturing, which will serve as the basis for progress calculation; The defined and accessed business document data includes at least: main material requisition details, purchase plan, and material purchase details during the procurement stage; work orders, material requisition details, and component completion records during the production stage; sales orders, delivery records, transportation tracking records, and customer signed receipts during the delivery stage; and sales orders, invoicing records, and payment records during the settlement stage.

[0017] By using preset timed scheduling tasks, business document data that has been added or changed since the last extraction time can be automatically extracted from each business module at fixed time points.

[0018] Step S12: Perform data cleaning and standardization processing on the accessed business document data; The data cleaning process includes correcting abnormal formats, filling in missing values ​​in key fields, and removing duplicate records; and filtering out valid data and removing irrelevant or invalid data based on predefined business rules related to progress calculation. Standardization processing refers to the transformation and mapping of data from different data sources according to a unified data model, encoding rules, and measurement units, thereby eliminating semantic ambiguity and format differences.

[0019] Step S13: Store the processed standardized data in the database according to its business stage and data theme; The processed standardized data is categorized and integrated according to its business stage and data theme, and persistently stored in the database to form a structured standard data asset that can be called on demand by the progress calculation modules of each stage; the data theme is the model of the device.

[0020] Step S20: Based on the standard data assets, calculate the virtual progress and status of the procurement stage, production stage, delivery stage and settlement stage in the equipment manufacturing process respectively; The entire equipment manufacturing process is divided into four stages: procurement, production, delivery, and settlement. Based on standard data assets in the database, the virtual progress and status of each stage are calculated, specifically divided into the following sub-steps: Step S21: Introduce a price factor and calculate the virtual progress and status of the procurement stage by combining the demand and purchase quantity of the main materials; From the standard data assets, the requisition quantities of various main materials are extracted from the main material requisition details according to the equipment model as the actual demand for manufacturing the equipment. The purchase quantities of various main materials are extracted from the material purchase details as the actual purchase quantity. Then, these quantities are substituted into a formula that includes a price factor: In this process, the virtual progress of the procurement phase is calculated. Where k is the type index of the main material, and k takes values ​​from 1 to n, where n is the total quantity of the main material type in the purchase requisition details. Let be the price factor (i.e., the unit price of the material) for the k-th type of main material. This represents the actual purchase quantity of the k-th type of main material. This represents the actual demand for the k-th type of main material; Combining various business documents during the procurement phase with the calculated virtual progress The procurement phase can be divided into one of the following macro-business states: Status 0 - No Purchase: This indicates that there is no corresponding purchase plan, meaning the purchase plan is empty. Status 1 - No Purchases: This indicates that a purchasing plan has been made, but no materials have been purchased. In other words, the purchasing plan is not empty, but the material purchase details are empty. Status 2 - Procurement in progress indicates that materials have been received, meaning the purchase details are not empty and the virtual progress CGJD is less than 100%. Status 3 - Completed indicates that all materials have been received, which is the virtual progress. Or the associated equipment has been completed.

[0021] Step S22: Calculate the virtual progress and status of the production stage based on the material requisition process; Based on the equipment model, extract the registered quantities of various materials from the work orders of the standard data assets as the planned material requisition quantity, and extract the requisition quantities of various materials from the material requisition details as the actual material requisition quantity. Substitute these quantities into the formula: In the process, the initial virtual progress of the production phase is calculated. ,in For material indexing, Value , This represents the total quantity of material types registered in the work order. For the production of the first The average cost required for this type of material (calculated based on the average of historical production costs). For the first The actual amount of materials issued for this type of material For the first Planned material requisition quantity for this type of material; Subsequently, based on the component completion records for this equipment model in the standard data asset, a preliminary virtual progress was established. The correction process involves obtaining the planned total number of all components to be completed. and the actual number of completed projects ; Calculate the completion factor of parts ; Execute the correction formula The corrected virtual progress ,in The preset material requisition progress weighting coefficient, This formula indicates that production progress is jointly determined by the degree of material readiness and the actual degree of processing completion. Combining various business documents during the production phase with the calculated virtual progress The production stage can be divided into one of the following macro-business states: Status 0 - Not in production indicates that no production work order has been issued, i.e., the work order is empty; Status 1 - Pending Production indicates that a work order has been issued, but no materials have been requisitioned yet. That is, the work order is not empty, but the material requisition details are empty. Status 2 - In Production: This indicates that material requisition has occurred, but not all parts are completed. The material requisition details are not empty. ; Status 3 - Completed: This indicates that all components have been completed. .

[0022] Step S23: Based on the shipment tracking data, calculate the virtual progress of the shipment stage using the hybrid entropy reduction algorithm, and determine its current status; Based on the equipment model, sales orders, shipping records, transportation tracking records, and customer receipts for that equipment are extracted from the standard data assets. Combined with external environmental data (collectively referred to as shipment tracking data), a hybrid entropy reduction algorithm is used to calculate the virtual progress. The specific implementation process is as follows: ① Based on the continuous process from shipment to confirmation of receipt, define five mutually exclusive milestone states; The five mutually exclusive milestone states include: The pending shipment status indicates that the sales order has been created, but there is no shipment record. The "in transit" status indicates that the goods have been shipped from the warehouse, but the transportation tracking record shows that they have not yet arrived at the destination city. The status of "arriving in the waiting state" indicates that the goods have arrived at the target city, but no unloading or handover has been recorded. The "in handover" status indicates that the goods have begun to be unloaded or handed over. The process is complete, indicating that the customer has signed for the goods and the goods have been confirmed.

[0023] ② Process the shipment tracking data to generate three evidence feature vectors. Each evidence feature vector contains five components, which correspond to five predefined milestone states. The three standardized feature vectors include: Time matching degree vector: for each state Its corresponding time matching degree component The calculation formula is: ,in t represents the task start time (sales order creation time), and t represents the current time. and These represent the milestone statuses derived from historical data statistics. Required mean time and standard deviation; Spatial matching degree vector: for each state Its corresponding spatial matching degree component The calculation process is as follows: using the formula: Determine the membership degree of the current location of the goods to each region. ,in The current GPS location of the goods. For state Typical geographical areas (preset values, such as...) The typical geographical region is the area where the target city is located. The radius of the region. For distance function, return and The closest distance to the boundary. The preset membership threshold is set (0.8 in this embodiment). If no 1 satisfies the condition, then... Then perform the judgment; if ,but ,otherwise ; Event conformity vector: for each state Its corresponding event conformity component The calculation formula is: , where e represents the events that have occurred (an event refers to a triggering event detected by the logistics module during the period from shipment to confirmation of receipt, such as outbound scanning and receipt scanning). , For the set of events that have already occurred, For state The following is a typical set of events. For indicator functions, if Returns 1 otherwise returns 0. The preset time decay coefficient, Let t be the time when event e occurs, and t be the current time.

[0024] ③ Fuse the three evidence feature vectors into the probability of achieving each milestone state; First, use the formula: Calculate the fusion score for each milestone state. ,in These are the fusion weights of the time matching vector, spatial matching vector, and event matching vector, predefined based on data quality and task stage; then, the scores are calculated using the softmax function. Convert to probability of achievement .

[0025] ④ Input the probability of achieving each milestone state into the hybrid entropy reduction calculation model to output the virtual progress of the delivery stage; The hybrid entropy reduction calculation model is expressed as follows:

[0026] in This is the virtual progress of the output shipping stage. The weight of the i-th milestone state is calculated as follows: The weights from the historical data are calculated based on the weights accumulated since the completion of each milestone state. The average time required (including delays) is denoted as Substitute into the formula: In the process, the weight of the i-th milestone state is obtained. Completed respectively The average time required for the state to be reached; Let be the probability of achieving the i-th milestone state. It is a preset constant (very small, used to ensure that the log term is calculated correctly). Let i be the initial value of the probability of achieving each milestone state (set to 0.5 in this embodiment), and let i be the index of the milestone state, which takes the value 1 to 5. For the identified event factors, ,in This is an abnormal event. , This is the set of all abnormal triggering events detected by the system so far (detection is based on preset rules, such as a truck staying in the same location for a longer than a preset threshold and the time period is not a rest period). For the event The severity coefficient (proportional to the deviation of the detection item and the preset threshold). For the event The duration; The total uncertainty event impact factor, ,in This represents the total number of waypoints in the transportation route. The maximum number of path points preset for the system (used for normalization). The total distance of the transportation route. This represents the longest transport distance for similar products. This is the maximum value of the special requirements indicator factor (preset values, such as 1.2 for cold chain transportation, 1.5 for dangerous goods qualification requirements, and 1.0 for general transportation). This refers to the number of times anomalies occurred in historical data among tasks that share the same combination of characteristics as the current transportation task. This refers to the total number of historical missions that share the same combination of characteristics as the current transportation mission. For data confidence, and Positive correlation (when historical data is insufficient) Used to reduce (item weights) and It is an adjustable parameter. The weather risk index is calculated by weighting the deviation of weather forecast data from the departure point, destination, and main transit points to a standard baseline. It is the traffic risk index (i.e., the real-time congestion index output by the navigation system based on the current road segment). The preset weighting coefficients (the weighting coefficients of each factor can be determined by analyzing historical task data and using linear regression or analytic hierarchy process).

[0027] After calculating the virtual progress, the delivery stage is divided into one of the following macro-business states based on the presence or absence of business document data: Status 0 - Not shipped, meaning the sales order does not exist; Status 1 - Shipped, meaning the sales order exists, but the receipt record does not exist; Status 2 - Received, meaning the receipt record exists, but the revenue confirmation record does not exist; Status 3 - Confirmed, meaning the revenue recognition record exists.

[0028] Step S24: Calculate the virtual progress and status of the settlement stage based on the invoicing and payment data; Based on the device model, extract the associated sales amount, invoice amount, and payment amount from the sales order, invoice record, and payment record data of the standard data assets. Calculate the virtual progress (JSJD) for the settlement stage and determine its current status. The calculation formula is as follows: ,in, The preset invoicing coefficient (set to 0.3 in this embodiment) is used. This refers to the cumulative invoice amount. The preset collection coefficient is 0.7 in this embodiment. C represents the cumulative amount received; C represents the total amount of sales orders. Based on the calculated virtual progress JSJD and the cumulative invoicing and collection amounts, the settlement stage is divided into one of the following macro-business states: Status 0 - Not started, i.e., virtual progress JSJD=0; Status 1 - In progress, i.e. ; Status 2 - Invoice issued, i.e. ; Status 3 - Payment Received: ; Status 4 - Ended: .

[0029] Step S30: Calculate the overall virtual progress of equipment manufacturing based on the virtual progress of the procurement stage, production stage, delivery stage and settlement stage, combined with the dynamic weight coefficient of each stage. Overall virtual progress The calculation formula is expressed as: Where s is the stage index, with a value from 1 to 4. Let be the virtual progress of the s-th stage at time t. The dynamic weight coefficients are the dynamic weight coefficients for the s-th stage at time t; The calculation process is as follows: ① Calculate the data entropy factor, schedule relevance factor, and schedule deviation risk factor for each stage; The data entropy factor is used to quantify the uncertainty of progress data at each stage. The higher the value, the greater the fluctuation in the state at that stage, and the lower the reliability of the progress value. Therefore, its weight is reduced accordingly. The calculation formula is as follows: ,in Let be the data entropy factor at time t in the s-th stage. This represents the probability, based on historical data, that the s-th stage is in the ith state (macro-business state) at time t, calculated as the proportion of the ith state occurrences within the sliding time window to the total number of occurrences; i takes values... , The number of macro-level business states included in the s-th stage.

[0030] The schedule correlation factor is used to measure the degree of mutual influence between schedule changes in any two stages. If the schedule of a certain stage is highly correlated with that of other stages, its change will have a greater impact on the overall schedule, and its weight should be increased. The calculation formula is expressed as follows: ,in Indicates the s-th stage and the s-th stage. Progress correlation factors between stages They are respectively the s-th and the s-th Virtual progress time sequence of each stage return and covariance, for standard deviation for The standard deviation.

[0031] The schedule deviation risk factor is used to identify bottleneck stages where the current schedule deviates significantly from the plan. The greater the deviation, the higher the risk contribution of this stage to the overall on-time completion, and therefore it should be given a higher weight to highlight its criticality. The calculation formula is as follows: ,in Let be the schedule deviation risk factor for the s-th stage at time t. Let be the virtual progress of the s-th stage at time t. This represents the expected progress of the s-th stage at the current moment (determined based on the project planning system or manually defined baselines). This is an adjustable scaling factor used to adjust the impact of schedule deviations on risk factors, calibrated based on the sensitivity of historical projects to deviations.

[0032] ② By integrating the above three factors, the initial weight coefficients for each stage are obtained; The initial weight of the s-th stage is expressed as The calculation formula is as follows: ,in This is the entropy suppression coefficient. The larger the coefficient, the more severely the weights of stages with high data uncertainty are suppressed. This is the correlation enhancement coefficient. The larger the coefficient, the greater the weight of the stage that is strongly correlated with other stages will be increased. This is the risk awareness coefficient; the larger the coefficient, the higher the weight of the stage where the schedule deviates more severely from the plan. It can be trained by analyzing historical data with the goal of "consistency between the weighting results and the project manager's experience-based decisions".

[0033] ③ Based on the game process of the four stages in competing for the contribution to the overall progress, the initial weight coefficient is optimized and iterated to output the optimal dynamic weight coefficient at the current moment. First, set the iteration counter n=0, and the current iteration weight... The game payoff function is defined as follows: ,in It is a set containing the weights of the current iteration at each stage. This represents the virtual progress of the s-th stage at time t; subsequently, the following iterative loop is executed: 1. Use the formula Calculate the marginal contribution of each stage's weight to the overall expected schedule. ; 2. Based on marginal contribution Update the weights for each stage, i.e. , For the updated weights, The preset game learning rate; 3. Calculate the total change in all weights between two adjacent iterations. ,like If the iteration terminates, the final dynamic weights are set. ,like Then, set the iteration counter n = n + 1, and return to step 1 of the current iteration training process to proceed to the next iteration. This is the preset convergence threshold.

[0034] Step S40: Monitor the status changes at each stage, and generate and send progress reminder information when the preset reminder trigger conditions are met; This step aims to automatically monitor changes in the status of equipment at each stage of manufacturing, and automatically generate and send progress reminders to relevant personnel when critical nodes or abnormal situations occur, thereby achieving proactive and intelligent progress management. It is specifically divided into the following sub-steps: Step S41: Set the reminder trigger conditions and reminder message templates for the macro business status of each stage; Procurement Stage: When the status is 0 - No Procurement, the reminder is triggered when the required date (extracted from the main material requisition details) arrives or is overdue; when the status is 1 - No Goods Received, the reminder is triggered when the procurement date (extracted from the procurement plan) arrives and no material delivery details are observed within the preset time window; when the status is 3 - Completed, the reminder is triggered when the last delivery date (the latest date extracted from the material delivery details) is recorded, or the status of the associated equipment changes to "Completed".

[0035] Production stage: When the status is 1 - waiting to be produced, the trigger condition is that the work order issuance date (extracted from the work order) arrives; when the status is 3 - completed, the trigger condition is that the actual completion date (the last completion date extracted from the component completion record) is recorded.

[0036] Shipment stage: When the status is 1 - Shipped, the trigger condition is that the shipment date (extracted from the shipment record) is recorded; when the status is 2 - Received, the trigger condition is that the receipt date (extracted from the customer's signed receipt) is recorded; when the status is 3 - Confirmed, the trigger condition is that the confirmation date (extracted from the revenue confirmation record) is recorded.

[0037] Solution phase: When the status is 2 - Invoice issued, the trigger condition is that the invoice date of the last invoice record (extracted from the invoice record) is recorded; when the status is 3 - Payment received, the trigger condition is that the payment date of the last payment record (extracted from the payment record) is recorded; when the status is 4 - Ended, the trigger condition is that the dates of the last payment and invoice records are both recorded.

[0038] Each trigger condition's preset reminder message template includes the device model, current stage, trigger status, key date, and current virtual progress.

[0039] Step S42: Monitor changes in business status in real time. If the reminder triggering conditions are met, generate a progress reminder message according to the defined reminder message template. The system monitors the macro-business status update events at each stage of step S20 and determines in real time whether the reminder trigger conditions associated with the corresponding status are met based on the data collected in step S10. If the conditions are met, the system automatically fills in the specific information according to the preset reminder message template and stores the generated progress reminder message in the designated message queue.

[0040] Step S43: Forward the generated progress reminder message to the user through a separate messaging service; The independent messaging service forwards progress reminder messages in the message queue to subscribed users according to a predefined configuration.

[0041] Example 2 like Figure 2 As shown, Embodiment 2 of this application provides a device manufacturing progress simulation system based on data mining technology, including: a business data processing module 21, a virtual progress calculation module 22, a virtual progress fusion module 23, and a progress reminder module 24; The business data processing module 21 is used to periodically collect business data from multiple business modules involved in equipment manufacturing, and to clean and standardize the business data to form standard data assets; specifically, it includes: a business data access submodule, a business data processing submodule, and a business data storage submodule. 1. Business data access submodule, used to define and access business document data as the basis for progress calculation from multiple business modules involved in equipment manufacturing; 2. Business data processing submodule, used to clean and standardize the incoming business document data; 3. Business data storage submodule, used to classify and store the processed standardized data into the database according to its business stage and data theme.

[0042] The virtual progress calculation module 22 is used to calculate the virtual progress and status of the procurement stage, production stage, delivery stage and settlement stage in the equipment manufacturing process based on the standard data assets. The virtual progress fusion module 23 is used to calculate the overall virtual progress of equipment manufacturing based on the virtual progress of the procurement stage, production stage, delivery stage and settlement stage, combined with the dynamic weight coefficient of each stage. The progress reminder module 24 is used to monitor the status changes at each stage. When the preset reminder trigger conditions are met, it generates and sends progress reminder information. Specifically, it includes: a trigger condition configuration submodule, a trigger condition monitoring submodule, and a reminder message forwarding submodule. 1. Trigger Condition Configuration Submodule, used to set the reminder trigger conditions and reminder message templates for the macro business status of each stage; 2. Trigger condition monitoring submodule, used to monitor changes in business status in real time. If the reminder trigger condition is met, a progress reminder message is generated according to the defined reminder message template; 3. The reminder message forwarding submodule is used to forward the generated progress reminder messages to the user through an independent message service.

[0043] Corresponding to the above embodiments, the present invention provides a computer storage medium, including: at least one memory and at least one processor; The memory is used to store one or more program instructions; A processor is used to run one or more program instructions to execute a device manufacturing progress simulation method based on data mining techniques.

[0044] Corresponding to the above embodiments, this embodiment of the invention provides a computer-readable storage medium containing one or more program instructions, which are executed by a processor to provide a device manufacturing progress simulation method based on data mining technology.

[0045] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions. When the computer program instructions are executed on a computer, the computer performs the above-described method for simulating equipment manufacturing progress based on data mining technology.

[0046] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0047] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0048] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0049] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0050] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0051] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0052] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0053] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for simulating equipment manufacturing progress based on data mining technology, characterized in that, include: Step 1: Collect business data from multiple business modules involved in equipment manufacturing at regular intervals, and clean and standardize the business data to form standard data assets; Step 2: Based on the standard data assets, calculate the virtual progress and status of the procurement, production, delivery and settlement stages in the equipment manufacturing process, respectively. Step 3: Based on the virtual progress of the procurement stage, production stage, delivery stage and settlement stage, and combined with the dynamic weight coefficient of each stage, calculate the overall virtual progress of equipment manufacturing. Step 4: Monitor the status changes at each stage, and generate and send progress reminder information when the preset reminder trigger conditions are met.

2. The equipment manufacturing progress simulation method based on data mining technology according to claim 1, characterized in that, Business data is collected periodically from multiple business modules involved in equipment manufacturing, and the business data is cleaned and standardized to form standard data assets. This process is specifically divided into the following sub-steps: Define and access business document data that serves as the basis for progress calculation from multiple business modules involved in equipment manufacturing; The data from the incoming business documents is cleaned and standardized. The processed standardized data is categorized and stored in the database according to its business stage and data theme.

3. The equipment manufacturing progress simulation method based on data mining technology according to claim 1, characterized in that, Based on the aforementioned standard data assets, the virtual progress and status of the procurement, production, delivery, and settlement stages in the equipment manufacturing process are calculated, specifically through the following sub-steps: Introduce price factors and calculate the virtual progress and status of the procurement stage by combining the demand and purchase volume of main materials; Calculate the virtual progress and status of the production stage based on the material requisition process; Based on the shipment tracking data, a hybrid entropy reduction algorithm is used to calculate the virtual progress of the shipment stage and determine its current status. The virtual progress and status of the settlement stage are calculated based on invoicing and payment data.

4. The equipment manufacturing progress simulation method based on data mining technology according to claim 3, characterized in that, Based on the shipment tracking data, a hybrid entropy reduction algorithm is used to calculate the virtual progress of the shipment stage, which is divided into the following sub-steps: Based on the continuous process from shipment to confirmation of receipt, five mutually exclusive milestone states are defined; The shipment tracking data is processed to generate three evidence feature vectors. Each evidence feature vector contains five components, which correspond to five predefined milestone states. The three evidence feature vectors are fused into the probability of achieving each milestone state; The probability of achieving each milestone state is fed into the hybrid entropy reduction calculation model to output the virtual progress of the delivery stage.

5. The equipment manufacturing progress simulation method based on data mining technology according to claim 1, characterized in that, The calculation process for the dynamic weighting coefficients at each stage is as follows: Calculate the data entropy factor, schedule relevance factor, and schedule deviation risk factor for each stage; By combining the above three factors, the initial weight coefficients for each stage are obtained; Based on the game process of competing for contribution to the overall progress in four stages, the initial weight coefficients are optimized and iterated to output the optimal dynamic weight coefficients at the current moment.

6. The equipment manufacturing progress simulation method based on data mining technology according to claim 1, characterized in that, Monitor the status changes at each stage, and when the preset reminder trigger conditions are met, generate and send progress reminder information. This is specifically divided into the following sub-steps: Set reminder trigger conditions and reminder message templates for the macro business status at each stage; Real-time monitoring of changes in business status; if the reminder trigger conditions are met, a progress reminder message is generated based on the defined reminder message template. The generated progress reminder messages are forwarded to the user through a separate messaging service.

7. A device manufacturing progress simulation system based on data mining technology, characterized in that, include: Business data processing module, virtual progress calculation module, virtual progress fusion module, progress reminder module; The business data processing module is used to periodically collect business data from multiple business modules involved in equipment manufacturing, and to clean and standardize the business data to form standard data assets. The virtual progress calculation module is used to calculate the virtual progress and status of the procurement, production, delivery and settlement stages of the equipment manufacturing process based on the standard data assets. The virtual progress fusion module is used to calculate the overall virtual progress of equipment manufacturing based on the virtual progress of the procurement stage, production stage, delivery stage and settlement stage, combined with the dynamic weight coefficient of each stage. The progress reminder module is used to monitor the status changes at each stage. When the preset reminder trigger conditions are met, it generates and sends progress reminder information.

8. The equipment manufacturing progress simulation system based on data mining technology according to claim 7, characterized in that, The business data processing module specifically includes: a business data access submodule, a business data processing submodule, and a business data storage submodule; The business data access submodule is used to define and access business document data, which serves as the basis for progress calculation, from multiple business modules involved in equipment manufacturing. The business data processing submodule is used to clean and standardize the incoming business document data. The business data storage submodule is used to classify and store the processed standardized data into the database according to its business stage and data theme.

9. The equipment manufacturing progress simulation system based on data mining technology according to claim 7, characterized in that, The progress reminder module specifically includes: a trigger condition configuration submodule, a trigger condition monitoring submodule, and a reminder message forwarding submodule; The trigger condition configuration submodule is used to set the reminder trigger conditions and reminder message templates for the macro business status of each stage; The trigger condition monitoring submodule is used to monitor changes in business status in real time. If the reminder trigger condition is met, a progress reminder message is generated according to the defined reminder message template. The reminder message forwarding submodule is used to forward the generated progress reminder messages to the user through an independent message service.

10. A computer storage medium, characterized in that, include: At least one memory and at least one processor; Memory, used to store one or more program instructions; A processor for running one or more program instructions to execute a device manufacturing progress simulation method based on data mining technology as described in any one of claims 1-6.

Images