Production line control method and system based on order data

Abstract

The invention provides a production line control method and system based on order data, and relates to the technical field of production control, and the method comprises the steps: connecting an order information platform, determining a current order of a target product through the order information platform, and obtaining the order attribute information of the current order; performing feature analysis on the order attribute information to obtain an order feature vector; identifying a target production line of the target product, and determining production line operation parameters of the target production line based on the order feature vector; and configuring the target production line according to the production line operation parameters and executing the production task of the current order. The technical problem of insufficient production resource configuration accuracy in production line control in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of production control, and more particularly to a production line control method and system based on order data. Background Technology

[0002] Traditional production line scheduling relies heavily on human experience, resulting in significant response lag. Especially in scenarios where order demand changes frequently, manual scheduling struggles to adapt to dynamic changes such as order priority adjustments and quantity fluctuations in real time. This leads to insufficient accuracy in production resource allocation, resulting in capacity bottlenecks due to excessive equipment load or waste due to idle resources, which in turn affects product quality stability.

[0003] As the manufacturing industry transforms towards flexibility and intelligence, there is an urgent need to establish an automated control mechanism based on order data. This mechanism will enable dynamic matching between production lines and order demands through data-driven approaches, addressing the pain point of insufficient precision in production resource allocation under the traditional model. Summary of the Invention

[0004] This invention addresses the technical problem of insufficient accuracy in production resource allocation in existing production line control technologies by providing a production line control method and system based on order data.

[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: In a first aspect, the present invention provides a production line control method based on order data, comprising: Connect to the order information platform, determine the current order for the target product through the order information platform, and obtain the order attribute information of the current order; The order attribute information is parsed to obtain the order feature vector; Identify the target production line for the target product, and determine the production line operation parameters of the target production line based on the order feature vector; Configure the target production line with the production line operating parameters and execute the production task of the current order.

[0006] Secondly, the present invention provides a production line control system based on order data, comprising: The information collection module is used to connect to the order information platform, determine the current order of the target product through the order information platform, and obtain the order attribute information of the current order; The information parsing module is used to perform feature parsing on the order attribute information to obtain the order feature vector; The operating parameter determination module is used to identify the target production line of the target product and determine the production line operating parameters of the target production line based on the order feature vector. The parameter execution module is used to configure the target production line with the production line operating parameters and execute the production task of the current order.

[0007] The beneficial effects of this invention are: Compared to existing technologies, this application first connects to an order information platform to determine the current order for the target product and obtain its order attribute information, providing a reliable data foundation for subsequent production line parameter determination. Secondly, it performs feature analysis on the order attribute information to obtain order feature vectors, transforming unstructured order attribute information into standardized order feature vectors, providing high-quality data input for accurate calculation of subsequent production line parameters. Thirdly, it identifies the target production line for the target product and determines the production line operating parameters based on the order feature vectors, achieving precise matching between production line operating parameters and order requirements, solving problems such as production line mismatch and blind parameter adjustments in traditional manual scheduling. Finally, it configures the target production line with the production line operating parameters to execute the production task of the current order, improving the accuracy of production resource allocation and quality stability.

[0008] Through the aforementioned technical solution, this application achieves dynamic identification of order priorities (e.g., marking orders for priority processing) and accurate extraction of feature vectors via real-time connection and intelligent analysis of the order information platform. This enables the production line to quickly respond to urgent orders or personalized needs, improving order response speed. Furthermore, by leveraging a feature parser trained on historical data and a time-quality mapping table, order attributes are transformed into optimal production line operating parameters, achieving intelligent decision-making for resource allocation and reducing errors caused by manual intervention. Thus, the accuracy of production resource allocation is improved. Attached Figure Description

[0009] Figure 1 A flowchart illustrating the production line control method based on order data provided by the present invention; Figure 2 This is a schematic diagram of the production line control system based on order data provided by the present invention.

[0010] In the attached diagram, the components represented by each number are as follows: Information acquisition module 11, information parsing module 12, running parameter determination module 13, and parameter execution module 14. Detailed Implementation

[0011] 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 embodiments of the present invention, and not all embodiments. 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.

[0012] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0013] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0014] Example 1, as Figure 1 As shown, this embodiment of the invention provides a production line control method based on order data, including: S10: Connect to the order information platform, determine the current order of the target product through the order information platform, and obtain the order attribute information of the current order; In the traditional manual production scheduling model, due to the large scale and complex dimensions of order data, there are common problems such as chaotic order information organization, poor response timeliness, and biased production scheduling decisions.

[0015] To address the aforementioned issues, this application connects to an order information platform, determines the current order for the target product through the order information platform, and obtains the order attribute information of the current order.

[0016] Specifically, step S10 in the method includes: Obtain the product model of the target product, and based on the product model, perform an order retrieval on the order information platform to obtain the order sequence of the target product; Extract the order with the earliest timestamp from the order sequence and use it as the current order, then retrieve the order number of the current order; Based on the order number, retrieve the order attribute information bound to the order number from the order information platform.

[0017] In this embodiment, the product model of the target product is first obtained. Based on the product model, an order retrieval is performed in an order information platform to obtain the order sequence of the target product. The order information platform is, for example, the order database of an enterprise ERP system, and the order sequence of the target product is a sequence of orders to be executed. For example, the product model of the target product serves as an identifier for different types of products. Using the product model as a search keyword, all pending order data for the target product is extracted from the order database of the enterprise ERP system through SQL queries or API interfaces, forming the order sequence of the target product. Thus, relevant orders are accurately retrieved by product model, effectively avoiding the problem of low accuracy in traditional manual screening.

[0018] Secondly, the order with the earliest timestamp in the order sequence of the target product is extracted as the current order, and its order number is retrieved. The order timestamp refers to the order creation time. For example, if the order sequence of the target product contains three orders with timestamps of 2024-07-25, 2024-07-26, and 2024-07-27, the order with timestamp 2024-07-25 is extracted as the current order, and its order number is retrieved, such as ORD20240725001. In this way, production priority is clearly defined by timestamp sorting, and the order number is obtained as a unique identifier, providing a precise index for subsequent information association.

[0019] Finally, based on the order number, the order attribute information bound to the order number is retrieved from the order information platform. This order attribute information includes specific requirements clearly defined in the order, such as product quantity, quality grade, delivery date, and customer-specific requirements. For example, by searching the order information platform using the order number (e.g., ORD20240725001), the order attribute information bound to the order number is retrieved. This includes, for instance, product quantity 500, yield rate 99.5%, quality grade 1, and delivery date 2024-08-05. This retrieves the order attribute information for the current order, providing complete data support for subsequent feature analysis.

[0020] Furthermore, after obtaining the order sequence of the target product, the method further includes: Detect whether there are marked orders in the order sequence; When a marked order exists in the order sequence, the marked order is taken as the current order; When there are multiple labeled orders in the order sequence, all labeled orders are extracted to form a labeled sequence, and the current order is determined from the labeled sequence according to priority.

[0021] In this embodiment, the system first detects whether there are marked orders in the order sequence. Marked orders refer to special orders explicitly identified by a preset marker field in the order information, such as expedited orders or VIP customer orders. For example, by identifying special marker fields in the order data, such as expedited or VIP customer, the system determines whether marked orders exist. For instance, if an order in the order sequence is marked with "expedited," it is identified as a marked order.

[0022] Secondly, when a marked order exists in the order sequence, the marked order is taken as the current order. Specifically, when there is only one marked order in the order sequence, the priority principle of "extracting the order with the earliest timestamp in the order sequence as the current order" in the previous step is directly broken, and the marked order is placed at the top as the current order. For example, if the order with the earliest timestamp in the order sequence is a regular order, but there is a marked order labeled "urgent", then the regular order with the earliest timestamp is skipped, and the marked order is taken as the current order, that is, the marked order is processed first. In this way, a fast response to marked orders can be ensured, and the start time of marked orders can be shortened.

[0023] Finally, when multiple marked orders exist in the order sequence, all marked orders are extracted to form a marked sequence. The current order is then determined from this marked sequence according to priority order. This priority order is a pre-defined priority rule, which can be set according to urgency level, customer priority, time limit priority, etc. For example, Level 3 urgency > Level 2 urgency > Level 1 urgency, VIP customers > regular customers, and marked orders with closer delivery dates take priority. For instance, if there are two marked orders in the order sequence, all marked orders are extracted to form a marked sequence. If this sequence contains "Level 3 urgency order A" and "Level 2 urgency order B," then according to the urgency level priority rule, order A takes precedence over order B, and order A is selected as the current order. In this way, the conflict problem of multiple marked orders is resolved through priority ordering, ensuring that resources are allocated to the most urgent and important needs, thereby improving customer satisfaction.

[0024] In summary, compared to existing technologies, this application connects to an order information platform, determines the current order for the target product through the platform, and obtains the order attribute information of the current order. This provides a reliable data foundation for subsequent production line parameter determination.

[0025] S20: Perform feature parsing on the order attribute information to obtain the order feature vector; Order attribute information often exists in unstructured data forms (such as text descriptions, table attachments, etc.). To meet the standardized input requirements for production line parameter calculations, this information needs to be converted into structured data. Furthermore, since the core attributes of orders for different product categories vary significantly—for example, electronic orders focus on parameters such as chip model and memory capacity, while mechanical orders focus on parameters such as material hardness and precision grade—general parsing tools may suffer from feature omissions or misjudgments due to insufficient adaptability.

[0026] To address the aforementioned issues, this application performs feature parsing on the order attribute information to obtain an order feature vector.

[0027] Specifically, step S20 in the method includes: Obtain the product model of the target product, and retrieve the order feature parser associated with the product model based on the product model; The order feature parser performs feature parsing on the order attribute information to obtain the order feature vector.

[0028] In this embodiment, the product model of the target product is first obtained from the current order, and the order feature parser associated with the product model is retrieved. For example, the product model of the target product is extracted from the current order, such as the laptop model DN15. The corresponding order feature parser is retrieved through a preset mapping relationship (such as a product model-order feature parser lookup table). For example, when the product model of the target product is detected as DN15, the corresponding electronic order feature parser is automatically loaded. In this way, by retrieving a dedicated parser through the product model, key features can be extracted in a targeted manner, avoiding feature omissions or misjudgments caused by general parsing tools.

[0029] Secondly, the order attribute information is analyzed using an order feature parser to obtain an order feature vector. For example, the order feature parser performs structured processing on the order attribute information, transforming textual descriptions and numerical requirements into multi-dimensional numerical vectors. For instance, the order feature parser analyzes the order attribute information "Produce 100 DN15 laptops, requiring a hard drive capacity of 1TB, a screen refresh rate of 120Hz, a delivery period of 10 days, and a yield rate ≥99%" to obtain an order feature vector [100, 1024, 120, 10, 99]. This order feature vector corresponds to the order quantity, hard drive capacity (GB), refresh rate (Hz), delivery days, and yield rate (%), respectively. In this way, the complex order attribute information is quantified into machine-recognizable digital signals, providing a data foundation for the subsequent algorithmic calculation of production line parameters.

[0030] Furthermore, the construction steps of the "order feature parser" include: Collect historical order records and construct a sample order attribute information set based on the historical order records; Feature annotation is performed on the attribute information of each sample order in the sample order attribute information set to obtain the sample order feature vector set; Based on the sample order attribute information set and the sample order feature vector set, the order feature parser is trained and obtained through supervised learning.

[0031] In this embodiment, historical order records are first collected, and a sample order attribute information set is constructed based on these records. Specifically, historical order records from several enterprises, covering different product models, order types, and customer needs, are collected. After cleaning and deduplication, these records are clustered according to product models to form several sample order attribute information sets associated with each product model. For example, 100,000 historical order data records from the past three years are collected, including multiple categories such as mobile phones, home appliances, and mechanical parts. Each record includes a complete order text description, product parameters, and other information. The order information is clustered according to product models to form several sample order attribute information sets associated with each product model. In this way, a large-scale sample set ensures that the order feature parser can learn diverse order feature patterns, avoiding the limitations of parsing due to single data sets, and providing data support for the model's generalization ability.

[0032] Secondly, feature annotation is performed on each sample order attribute information in the sample order attribute information set to obtain a sample order feature vector set. Specifically, through manual annotation or semi-automatic tools, feature extraction and numerical annotation are performed on each order attribute information in the sample order attribute information set to form a sample order feature vector set. During the annotation process, the feature dimensions need to be unified, such as converting delivery time into days to ensure the standardization of vector format. For example, a certain order attribute information "500 stainless steel parts, tensile strength ≥ 500MPa, delivery in 7 days" in the sample order attribute information set is manually annotated to obtain the order feature vector [500, 500, 7]. The same method is used to annotate the feature information of each sample order attribute information to obtain the sample order feature vector set.

[0033] Finally, based on the sample order attribute information set and sample order feature vector set, an order feature parser is trained using supervised learning. For example, the construction and training process of any order feature parser associated with a product model can follow this technical path: 1. Data Preparation: Divide the sample order attribute information set and sample order feature vector set into a training set and a validation set in an 8:2 ratio. The training set is used for model parameter learning, and the validation set is used to monitor the training effect in real time and adjust the model parameters, ensuring the consistency of data distribution to improve training reliability. 2. Model Construction: An order feature parser can be built based on an LSTM neural network architecture, mainly composed of an input layer, hidden layers, and an output layer. The input layer converts order attribute information into low-dimensional dense vectors through an embedding layer (for text-type attributes) and a normalization layer (for numerical-type attributes). The hidden layer contains bidirectional LSTM units and a dropout layer (to prevent overfitting) to capture the temporal and correlation features of order attributes. The output layer generates fixed-dimensional order feature vectors through a fully connected layer. 3. Model Training: Using sample order attribute information from the training set as input and sample order feature vectors as supervision labels, supervised learning is employed for model training. During training, the Adam optimizer iteratively updates parameters. Mean squared error (MSE) is selected as the loss function to measure the deviation between the predicted and true feature vectors. Overfitting is prevented by setting a dropout rate (e.g., 0.3) and an early stopping mechanism (e.g., terminating training when the accuracy on the validation set does not improve for five consecutive rounds). The training continues until the prediction accuracy on the validation set stabilizes at over 95%, at which point the model training is considered converged, resulting in an order feature parser. The trained order feature parser can then parse the order attribute information to obtain the order feature vector. Following the same method, several order feature parsers associated with product models are trained.

[0034] In summary, compared to existing technologies, this application performs feature parsing on the order attribute information to obtain an order feature vector. Thus, through an order feature parser associated with the product model, unstructured order attribute information is transformed into a standardized order feature vector, providing high-quality data input for the accurate calculation of subsequent production line parameters.

[0035] S30: Identify the target production line of the target product, and determine the production line operation parameters of the target production line based on the order feature vector; The order product quantity feature and order completion time feature in the order feature vector jointly constrain the processing speed requirements of the production line, while the order yield rate requirement feature clearly defines the production quality standards. Based on these features, the operating parameters of the target production line need to be calculated collaboratively to achieve a dynamic balance between capacity, efficiency and quality.

[0036] To address the aforementioned issues, this application identifies the target production line for the target product and determines the production line operating parameters of the target production line based on the order feature vector.

[0037] Specifically, step S30 in the method includes: Based on the product model of the target product, determine multiple matching production lines for the target product from multiple processing production lines; Idle production lines are identified from the matched production lines and used as the target production lines for the target products. Extract the order yield rate requirement feature, order product quantity feature, and order completion time limit feature from the order feature vector; The production line operating parameters of the target production line are determined based on the order yield rate requirement characteristics, the order product quantity characteristics, and the order completion time limit characteristics.

[0038] In this embodiment, firstly, based on the product model of the target product, multiple matching production lines with the capability to produce the target product are determined from multiple processing production lines. For example, using the product model of the target product (such as laptop model DN15) as the search criterion, multiple production lines with the capability to produce that product model are selected from the enterprise's production lines. For instance, by querying the production line capability table that records the product models that the production line can produce, three matching production lines capable of producing "DN15" are selected from 10 total production lines. Secondly, idle production lines are identified among the matched production lines and designated as the target production line for the target product. For example, industrial IoT sensors can be used to collect real-time operating status data of the production lines, selecting idle or soon-to-be-idle production lines from multiple matched production lines as the target production line. For instance, if production line 2 among three matched production lines is currently without tasks, it is designated as the target production line. This optimizes production resource utilization, avoids equipment overload or idleness, and improves overall capacity utilization.

[0039] Next, the order yield rate requirement, order product quantity, and order completion time limit features are extracted from the order feature vector. The order yield rate requirement determines the quality control standards of the production process, the order product quantity affects production batch size and efficiency planning, and the order completion time limit constrains the total production time. For example, the order yield rate requirement is extracted to be ≥99%, the order product quantity is 2000 units, and the order completion time limit is delivery within 10 days. These three parameters are core variables affecting the production line operating parameters, providing clear target constraints for subsequent calculations of production line operating parameters.

[0040] Finally, based on the order yield requirement characteristics, the order product quantity characteristics, and the order completion time limit characteristics, the production line operating parameters of the target production line are determined. Among them, the order product quantity characteristics and the order completion time limit characteristics jointly require processing speed. According to the empirical rule that processing speed affects processing quality, the faster the processing speed, the lower the yield rate is usually. Therefore, it is necessary to balance processing speed and processing quality according to the order yield requirement characteristics, order product quantity characteristics, and order completion time limit characteristics, and match the corresponding production line operating parameters accordingly to ensure that both time limit requirements and quality requirements are met.

[0041] Specifically, the step of "determining the production line operating parameters of the target production line based on the order yield rate requirement characteristics, the order product quantity characteristics, and the order completion time limit characteristics" includes: Obtain the time-quality mapping table of the target production line, which records the mapping relationship between the processing time of a single item and the corresponding yield rate; The processing constraint time for the target single item is determined based on the order completion time limit characteristics and the order product quantity characteristics. Based on the processing constraint time of the target single product, the corresponding yield rate is determined in the time-quality mapping table to obtain the expected yield rate; When the expected yield rate meets the order yield rate requirement, the corresponding production line operating parameters are obtained from the quality parameter mapping table based on the expected yield rate and used as the production line operating parameters of the target production line.

[0042] In this embodiment, a time-quality mapping table for the target production line is first obtained. This table records the mapping relationship between single-item processing time and the corresponding yield rate. Single-item processing time refers to the time required to process one target product, and the yield rate refers to the percentage of qualified products (those meeting order requirements after quality inspection) produced by the production line within a certain production cycle under the given single-item processing time parameter, out of the total production quantity within that cycle. For example, the time-quality mapping table is constructed based on the empirical rule that processing speed affects processing quality (i.e., yield rate). It can be constructed by collecting the single-item processing time and corresponding yield rate for a specific model of product on a certain production line from historical production records. For instance, the time-quality mapping table for a certain model of product might be: single-item processing time 431 seconds → yield rate 98.5%; single-item processing time 432 seconds → yield rate 99.2%; single-item processing time 433 seconds → yield rate 99.7%, etc. This transforms empirical rules into visualized data, providing an objective basis for parameter adjustment.

[0043] Secondly, the processing constraint time for the target single item is determined based on the order completion time limit characteristics and the order product quantity characteristics. The target single item processing constraint time = total order completion time limit in seconds / order product quantity. For example, if the order completion time limit is delivery within 10 days, the order product quantity is 2000 units, and the target production line operates 24 hours a day, then the total order completion time limit in seconds = 10 * 24 * 3600 = 864000 seconds. Therefore, the target single item processing constraint time = 864000 / 2000 = 432 seconds per unit. In this way, the macro-level order completion time limit characteristics are broken down into micro-level single item processing constraint times, providing a clear quantitative standard for balancing quality and efficiency in the future.

[0044] Next, the corresponding yield rate is determined in the time-quality mapping table based on the processing constraint time of the target single item, thus obtaining the expected yield rate. For example, in the time-quality mapping table, the corresponding yield rate is found based on the processing constraint time of the target single item. For instance, if the processing constraint time of the target single item is 432 seconds / unit, the corresponding yield rate matched in the time-quality mapping table is 99.2%, which is taken as the expected yield rate. If the processing constraint time of the target single item is between two data points in the mapping table, the expected yield rate can be calculated by linear interpolation. In this way, the expected yield rate under the current time constraint is obtained.

[0045] Finally, when the expected yield rate meets the order yield rate requirements, the corresponding production line operating parameters are retrieved from the quality parameter mapping table based on the expected yield rate. These parameters serve as the production line operating parameters for the target production line. The quality parameter mapping table is constructed based on the correspondence between yield rates and specific production line operating parameters. Historical production line operating parameters and corresponding yield rates can be collected from the historical production logs of the target production line to construct the quality parameter mapping table. For example, if the expected yield rate is 99.2% and the order yield rate requirement is ≥99%, the expected yield rate meets the order yield rate requirements. The corresponding production line operating parameters, such as a pick-and-place machine speed of 8000 rpm and a reflow soldering temperature of 250°C, are retrieved from the pre-constructed quality parameter mapping table based on the expected yield rate and used as the production line operating parameters for the target production line. Further, if the expected yield rate does not meet the order yield rate requirements, the system returns to the user client, allowing the user to reset the order completion time limit. In this way, by quantifying the entire chain from quality requirements to time constraints to yield rate to production line operating parameters, we can ensure that the final production parameters meet both the delivery deadline and the quality standards.

[0046] In summary, compared to existing technologies, this application identifies the target production line for the target product and determines the production line operating parameters based on the order feature vector. This achieves precise matching between production line operating parameters and order requirements, solving problems such as production line mismatch and blind parameter adjustments in traditional manual scheduling.

[0047] S40: Configure the target production line with the production line operating parameters and execute the production task of the current order.

[0048] The aforementioned steps output the production line operating parameters, which can be used to configure the target production line and execute the production task of the current order. For example, production line operating parameters (such as equipment speed, heating temperature, pressure value, detection frequency, etc.) can be automatically sent to each equipment terminal of the target production line through an industrial control system (such as PLC, SCADA, or an industrial IoT platform). For instance, for production line operating parameters such as a pick-and-place machine speed of 8000 rpm and a reflow soldering temperature of 250°C, these parameters can be written into the control system of the soldering equipment via a data interface, replacing the traditional method of manually setting parameters one by one. Furthermore, once the parameters are configured, the production line start command is automatically triggered, executing all production operations such as processing, testing, and packaging according to the preset process. During this process, sensors collect real-time equipment operating data (such as actual temperature and processing speed) and product quality data (such as appearance inspection results), dynamically comparing them with the parameter thresholds required by the order to ensure compliance of the production process. In this way, through automated configuration and real-time monitoring, the accuracy of production resource allocation and quality stability are improved.

[0049] In summary, the embodiments of this application have at least the following technical effects: Compared to existing technologies, this application first connects to an order information platform, determines the current order for the target product through the platform, and obtains the order attribute information of the current order. This provides a reliable data foundation for subsequent production line parameter determination.

[0050] Secondly, this application performs feature parsing on the order attribute information to obtain an order feature vector. Thus, through an order feature parser associated with the product model, unstructured order attribute information is transformed into a standardized order feature vector, providing high-quality data input for the accurate calculation of subsequent production line parameters.

[0051] Furthermore, this application identifies the target production line for the target product and determines the production line operating parameters based on the order feature vector. This achieves precise matching between production line operating parameters and order requirements, solving problems such as production line mismatch and blind parameter adjustments in traditional manual scheduling.

[0052] Finally, this application configures the target production line with the production line operating parameters to execute the production task of the current order. This improves the accuracy of production resource allocation and the stability of quality.

[0053] Through the aforementioned technical solution, this application achieves dynamic identification of order priorities (e.g., marking orders for priority processing) and accurate extraction of feature vectors via real-time connection and intelligent analysis of the order information platform. This enables the production line to quickly respond to urgent orders or personalized needs, improving order response speed. Furthermore, by leveraging a feature parser trained on historical data and a time-quality mapping table, order attributes are transformed into optimal production line operating parameters, achieving intelligent decision-making for resource allocation and reducing errors caused by manual intervention. Thus, the accuracy of production resource allocation is improved.

[0054] Example 2, as Figure 2 As shown, based on the same inventive concept as the production line control method based on order data provided in Embodiment 1, this embodiment of the invention also provides a production line control system based on order data, including: The information collection module 11 is used to connect to the order information platform, determine the current order of the target product through the order information platform, and obtain the order attribute information of the current order; Information parsing module 12 is used to perform feature parsing on the order attribute information to obtain the order feature vector; The operating parameter determination module 13 is used to identify the target production line of the target product and determine the production line operating parameters of the target production line based on the order feature vector. The parameter execution module 14 is used to configure the target production line with the production line operating parameters and execute the production task of the current order.

[0055] The information acquisition module 11 is specifically used for: Obtain the product model of the target product, and based on the product model, perform an order retrieval on the order information platform to obtain the order sequence of the target product; Extract the order with the earliest timestamp from the order sequence and use it as the current order, then retrieve the order number of the current order; Based on the order number, retrieve the order attribute information bound to the order number from the order information platform.

[0056] Specifically, after obtaining the order sequence of the target product, the process further includes: Detect whether there are marked orders in the order sequence; When a marked order exists in the order sequence, the marked order is taken as the current order; When there are multiple labeled orders in the order sequence, all labeled orders are extracted to form a labeled sequence, and the current order is determined from the labeled sequence according to priority.

[0057] The information parsing module 12 is specifically used for: Obtain the product model of the target product, and retrieve the order feature parser associated with the product model based on the product model; The order feature parser performs feature parsing on the order attribute information to obtain the order feature vector.

[0058] Furthermore, the construction steps of the "order feature parser" include: Collect historical order records and construct a sample order attribute information set based on the historical order records; Feature annotation is performed on the attribute information of each sample order in the sample order attribute information set to obtain the sample order feature vector set; Based on the sample order attribute information set and the sample order feature vector set, the order feature parser is trained and obtained through supervised learning.

[0059] The operating parameter determination module 13 is specifically used for: Based on the product model of the target product, determine multiple matching production lines for the target product from multiple processing production lines; Idle production lines are identified from the matched production lines and used as the target production lines for the target products. Extract the order yield rate requirement feature, order product quantity feature, and order completion time limit feature from the order feature vector; The production line operating parameters of the target production line are determined based on the order yield rate requirement characteristics, the order product quantity characteristics, and the order completion time limit characteristics.

[0060] Specifically, the step of "determining the production line operating parameters of the target production line based on the order yield rate requirement characteristics, the order product quantity characteristics, and the order completion time limit characteristics" includes: Obtain the time-quality mapping table of the target production line, which records the mapping relationship between the processing time of a single item and the corresponding yield rate; The processing constraint time for the target single item is determined based on the order completion time limit characteristics and the order product quantity characteristics. Based on the processing constraint time of the target single product, the corresponding yield rate is determined in the time-quality mapping table to obtain the expected yield rate; When the expected yield rate meets the order yield rate requirement, the corresponding production line operating parameters are obtained from the quality parameter mapping table based on the expected yield rate and used as the production line operating parameters of the target production line.

[0061] Specifically, the parameter execution module 14 is used for: Configure the target production line with the production line operating parameters and execute the production task of the current order.

[0062] In summary, the embodiments of this application have at least the following technical effects: Compared to existing technologies, this application first connects to an order information platform through an information acquisition module. This platform identifies the current order for the target product and obtains its attribute information, providing a reliable data foundation for subsequent production line parameter determination. Second, an information parsing module performs feature analysis on the order attribute information, obtaining order feature vectors. This transforms unstructured order attribute information into standardized order feature vectors, providing high-quality data input for accurate calculation of subsequent production line parameters. Third, an operation parameter determination module identifies the target production line for the target product and determines its operation parameters based on the order feature vectors. This achieves precise matching between production line operation parameters and order requirements, solving problems such as production line mismatch and blind parameter adjustments in traditional manual scheduling. Finally, a parameter execution module configures the target production line with the operation parameters to execute the production task of the current order, improving the accuracy and quality stability of production resource allocation. This enhances the accuracy of production resource allocation.

[0063] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0064] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0065] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0066] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0068] Although preferred embodiments of the invention have been described, those skilled in the art, once they have learned the basic inventive concept, can make other changes and modifications to these embodiments.

[0069] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A production line control method based on order data, characterized in that, The method includes: Connect to the order information platform, determine the current order for the target product through the order information platform, and obtain the order attribute information of the current order; The order attribute information is parsed to obtain the order feature vector; Identify the target production line for the target product, and determine the production line operation parameters of the target production line based on the order feature vector; Configure the target production line with the production line operating parameters and execute the production task of the current order.

2. The method according to claim 1, characterized in that, Connect to an order information platform, determine the current order for the target product through the order information platform, and obtain the order attribute information of the current order, including: Obtain the product model of the target product, and based on the product model, perform an order retrieval on the order information platform to obtain the order sequence of the target product; Extract the order with the earliest timestamp from the order sequence and use it as the current order, then retrieve the order number of the current order; Based on the order number, retrieve the order attribute information bound to the order number from the order information platform.

3. The method according to claim 2, characterized in that, After obtaining the order sequence of the target product, the method further includes: Detect whether there are marked orders in the order sequence; When a marked order exists in the order sequence, the marked order is taken as the current order; When there are multiple labeled orders in the order sequence, all labeled orders are extracted to form a labeled sequence, and the current order is determined from the labeled sequence according to priority.

4. The method according to claim 1, characterized in that, The order attribute information is subjected to feature parsing to obtain the order feature vector, including: Obtain the product model of the target product, and retrieve the order feature parser associated with the product model based on the product model; The order feature parser performs feature parsing on the order attribute information to obtain the order feature vector.

5. The method according to claim 4, characterized in that, The steps for constructing the order feature parser include: Collect historical order records and construct a sample order attribute information set based on the historical order records; Feature annotation is performed on the attribute information of each sample order in the sample order attribute information set to obtain the sample order feature vector set; Based on the sample order attribute information set and the sample order feature vector set, the order feature parser is trained and obtained through supervised learning.

6. The method according to claim 1, characterized in that, Identifying the target production line for the target product and determining the production line operating parameters of the target production line based on the order feature vector, including: Based on the product model of the target product, determine multiple matching production lines for the target product from multiple processing production lines; Idle production lines are identified from the matched production lines and used as the target production lines for the target products. Extract the order yield rate requirement feature, order product quantity feature, and order completion time limit feature from the order feature vector; The production line operating parameters of the target production line are determined based on the order yield rate requirement characteristics, the order product quantity characteristics, and the order completion time limit characteristics.

7. The method according to claim 6, characterized in that, Based on the order yield requirement characteristics, the order product quantity characteristics, and the order completion time limit characteristics, the production line operating parameters of the target production line are determined, including: Obtain the time-quality mapping table of the target production line, which records the mapping relationship between the processing time of a single item and the corresponding yield rate; The processing constraint time for the target single item is determined based on the order completion time limit characteristics and the order product quantity characteristics. Based on the processing constraint time of the target single product, the corresponding yield rate is determined in the time-quality mapping table to obtain the expected yield rate; When the expected yield rate meets the order yield rate requirement, the corresponding production line operating parameters are obtained from the quality parameter mapping table based on the expected yield rate and used as the production line operating parameters of the target production line.

8. A production line control system based on order data, characterized in that, For performing the method according to any one of claims 1-7, comprising: The information collection module is used to connect to the order information platform, determine the current order of the target product through the order information platform, and obtain the order attribute information of the current order; The information parsing module is used to perform feature parsing on the order attribute information to obtain the order feature vector; The operating parameter determination module is used to identify the target production line of the target product and determine the production line operating parameters of the target production line based on the order feature vector. The parameter execution module is used to configure the target production line with the production line operating parameters and execute the production task of the current order.

Images