Intelligent enterprise work order management system

Abstract

The invention discloses an intelligent enterprise work order management system, which comprises a work order information acquisition module, relates to the technical field of enterprise data processing, and is characterized in that historical work order processing data is introduced, a feature association model is constructed, and a work order association score is generated; the priority sequence of the standard work orders in the standard work order set is obtained in combination with the work order remaining time and the resource occupation amount, work order priority evaluation is made to better fit the actual production rule through historical experience, subjective experience deviation is avoided, the reasonability of scheduling decision making is improved, and the work order delay rate is reduced in combination with priority ranking of the work order remaining time and the resource occupation amount; the weight group is randomly generated, the fitness is evaluated through the work order scheduling simulation model, and a new group is generated based on the to-be-selected weight group to screen the optimal weight, so that the weight group of the work order relevance score, the work order remaining time and the resource occupation amount better fits the actual production scene.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of enterprise data processing, and in particular to an intelligent enterprise work order management system. BACKGROUND

[0002] The enterprise work order is a structured instruction carrier used to standardize recording, transmission and tracking of specific tasks in the enterprise operation process. The enterprise production work order is an instructional document or electronic voucher used to specify the specific requirements of production tasks and guide the execution of production activities in the workshop, triggered by the production planning department, the scheduling department or customer orders, and is the core carrier connecting production planning and actual production execution.

[0003] Publication No. CN118014314A discloses a semiconductor work order management system, which includes a multi-dimensional acquisition module, a resource configuration module and a management service module. The semiconductor work order management system collects work order data sets, resource data sets and production data sets through the multi-dimensional acquisition module, calculates and generates work order data sets through the resource configuration module, accurately calculates the number of to-be-produced and the corresponding required equipment, calculates and generates capacity data sets through the capacity configuration unit to calculate the real-time capacity efficiency, calculates and generates planned working hours through the working hour analysis unit to statistically consume the working hours required by existing work orders, and calculates and generates scheduling data sets and progress bars through the management service module to accurately calculate the to-be-scheduled procurement materials and the remaining human capacity to generate corresponding instructions. The flexible scheduling of work orders has high accuracy, the integrated data optimizes the production response speed, and the use experience is better.

[0004] However, the above-mentioned application still has the following problems: the work order priority evaluation of the above-mentioned application depends on the direct calculation of real-time data, does not introduce historical work order processing data for analysis, is easily affected by subjective experience on the scheduling logic, and leads to insufficient adaptability of the priority order to the actual production scene. In addition, the fixed parameter generation method involved in the above-mentioned application, such as resource configuration and working hour calculation, is a static setting based on a preset fixed value. The fixed parameter cannot adapt to the dynamically changing production scene, and when the scene deviates from the preset condition, the adaptability of the weight to the actual production scene will decrease significantly. SUMMARY

[0005] To solve the technical problems in the background art, the present application provides an intelligent enterprise work order management system.

[0006] The intelligent enterprise work order management system provided by the present application comprises:

[0007] The work order information acquisition module acquires enterprise work orders, pre-processes the enterprise work orders to generate standard work orders, and forms a standard work order set from multiple standard work orders.

[0008] Dynamic feature extraction module: Extracts features from standard work orders in the standard work order set, generates work order features, and multiple work order features form a work order feature set; work order features include remaining time and resource usage of the work order.

[0009] Work order scheduling module: Based on the work order feature set, prioritize the standard work orders in the standard work order set and generate work order dispatch instructions.

[0010] Preferably, in the work order scheduling module, the standard work orders in the standard work order set are prioritized according to the work order feature set, and a work order dispatch instruction is generated, as follows:

[0011] Acquire historical work order processing data to form a historical work order processing dataset;

[0012] Historical work order processing data includes the total historical processing time;

[0013] The correlation analysis between the work order feature set and the historical work order processing dataset is performed using the Pearson correlation coefficient algorithm or the Spearman rank correlation coefficient algorithm to generate a feature correlation model.

[0014] Based on the feature association model, the association of standard work orders in the standard work order set is evaluated, and the work order association score is generated. The work order association score is combined with the remaining time and resource usage of the work order to evaluate the priority. The weights of the work order association score, the remaining time of the work order, and the resource usage are set to obtain the priority sequence of standard work orders in the standard work order set.

[0015] The work order relevance score ranges from [0,1].

[0016] It should be noted that the feature association model uses the Pearson correlation coefficient algorithm or the Spearman rank correlation coefficient algorithm to perform correlation analysis on the work order feature set and the historical work order processing dataset. The original value range of the Pearson correlation coefficient algorithm or the Spearman rank correlation coefficient algorithm is [-1, 1]. Here, when the work order correlation score is ≤ 0, the correlation score is directly set to 0. Therefore, the value range of the work order correlation score is [0, 1].

[0017] Obtain the real-time load rate of production equipment; the real-time load rate of production equipment refers to the current resource utilization ratio of the equipment, and includes the load required by standard work orders that have been allocated but not yet started to be processed.

[0018] Obtaining the real-time load rate of production equipment refers to obtaining the real-time load rate of the production equipment required for the current standard work order;

[0019] Based on the priority sequence and the real-time load rate of the production equipment, standard work orders are allocated to production equipment to generate matching results.

[0020] Based on the matching results, a work order dispatch instruction is generated.

[0021] Preferably, in the work order scheduling module, based on the feature association model, the association of standard work orders in the standard work order set is evaluated, and a work order association score is generated for each standard work order, as follows:

[0022] For a specific standard work order in the standard work order set, the historical work order processing data in the historical work order processing dataset is traversed through by the feature association model to obtain the association score set of the specific standard work order. The maximum association score in the association score set of the specific standard work order is taken as the work order association score of the specific standard work order. Let the historical work order processing data corresponding to the maximum association score in the association score set of the specific standard work order be the associated historical work order data.

[0023] Preferably, in the work order scheduling module, the work order relevance score is combined with the remaining time and resource usage of the work order for priority evaluation. Weights are assigned to the work order relevance score, remaining time, and resource usage to obtain the priority sequence of standard work orders in the standard work order set, as follows:

[0024] Multiply the work order relevance score by 100% to get the work order relevance percentage as a percentage.

[0025] The ratio of the remaining time of a work order to the preset maximum remaining time is the percentage of remaining time.

[0026] The ratio of resource usage to the preset maximum resource amount is the resource percentage.

[0027] The work order relevance score, remaining work order time, and resource usage are assigned the first, second, and third weights, respectively.

[0028] For each standard work order, the priority score is as follows:

[0029] The priority score for a standard work order is calculated as follows: work order relevance percentage × first weight + remaining time percentage × second weight + resource percentage × third weight.

[0030] The priority scores of standard work orders in the standard work order set are sorted in descending order to obtain a priority sequence from high to low.

[0031] Preferably, in the work order scheduling module, standard work orders are allocated to production equipment based on priority sequence and real-time load rate of production equipment, generating matching results as follows:

[0032] Obtain all production equipment of the enterprise and generate a pool of candidate equipment;

[0033] Based on the priority sequence, perform the following production equipment allocation operation for each standard work order in the standard work order set:

[0034] Obtain a standard work order as the target work order, and obtain the required production equipment for the target work order;

[0035] Select the required production equipment corresponding to the target work order from the candidate equipment pool as the initial candidate production equipment pool;

[0036] Select the production equipment with the lowest real-time load rate from the initial pool of candidate production equipment as the final production equipment, and generate matching results;

[0037] As an explanation, selecting the production equipment with the lowest real-time load rate in the initial pool of candidate production equipment as the final production equipment means that if there is only one production equipment required, then the production equipment with the lowest real-time load rate is selected. If there are multiple production equipment required, then the production equipment with the lowest real-time load rate is selected, and the multiple production equipment have the lowest real-time load rate among the corresponding required production equipment.

[0038] For example, if 5 different production devices are required, that is, 5 types of final production devices are needed, then each type of final production device has the lowest real-time load rate in the initial pool of candidate production devices.

[0039] Preferably, in the work order scheduling module, the weights for work order relevance score, remaining work order time, and resource usage are set as a first weight, a second weight, and a third weight, respectively. The values ​​of the first weight, the second weight, and the third weight are generated in the following manner:

[0040] Let the first weight, second weight, and third weight be respectively , , ,and , , The range of values ​​for all values ​​is set to [0,2].

[0041] When there is no data to process. , , The value is the default value;

[0042] For clarification, the default value can be understood as the preset value;

[0043] Based on the work order dispatch instructions, collect processing data during the standard work order processing process;

[0044] Statistical analysis of the processed data yields the total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation.

[0045] Obtain real-time status data of production equipment, based on , , The default values, total delay time, total equipment overload time, total processing efficiency, total time saved by correlation, historical work order processing data, and real-time status data of production equipment are used to construct a work order scheduling simulation model through digital twin technology.

[0046] The work order scheduling simulation model is used to... , , The numerical output includes the estimated total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation.

[0047] Multiple weight combinations are randomly generated, each weight combination representing a group. , , The values ​​of each weight combination , , All values ​​are randomly selected within the range [0,2].

[0048] By inputting multiple weight combinations into the work order scheduling simulation model, we can obtain the estimated total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation for each weight combination.

[0049] Based on the estimated total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation, a weighted average method is used to generate the fitness of each weight combination.

[0050] Select the X weight combinations with the highest fitness as candidate weight combinations, where 3 ≤ X and X is a positive integer;

[0051] The values ​​of each weight combination in the selected weight combination are changed to generate multiple new weight combinations. These new weight combinations are then input into the work order scheduling simulation model to obtain the fitness of each new weight combination.

[0052] Choose the weight combination with the highest fitness from the candidate weight combinations and the new weight combinations. , , The final weight.

[0053] Preferably, in the work order scheduling module, statistical analysis is performed on the processing data to obtain the total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation.

[0054] The total delay time is the sum of the differences between the actual processing time and the expected processing time for all standard work orders.

[0055] The total overload time of the equipment is the sum of the durations during which the actual load of the equipment exceeds the threshold.

[0056] Overall processing efficiency is the ratio of total processing time to total expected processing time;

[0057] The total time saved by association is generated in the following way:

[0058] For a given standard work order, obtain the actual total processing time of that standard work order, assuming the actual total processing time is... ;

[0059] Retrieve the associated historical work order data for a given standard work order, and extract the total historical processing time from this data. Let the total historical processing time be... ;

[0060] when > At that time, take - The difference is taken as the time saved, and the sum of all the time saved is taken as the total time saved in relation to the relationship.

[0061] Preferably, in the work order scheduling module, the value of each weight combination in the selected weight combination is changed to generate multiple new weight combinations, as follows:

[0062] Let any two weight combinations in the candidate weight combinations be [ , , ]and[ , , ];

[0063] Then any two weight combinations correspond to a new weight combination as [α× +(1-α) , α× +(1-α) , α× +(1-α) ], where α is a random number between (0,1). If α is randomly changed X times, then any two weight combinations will result in X new weight combinations.

[0064] The intelligent enterprise work order management system proposed in this invention has the following beneficial technical effects:

[0065] 1. By introducing historical work order processing data, a feature association model is constructed using Pearson or Spearman rank correlation coefficient algorithms to generate work order association scores. Combined with the remaining time and resource occupancy of the work orders, a priority sequence of standard work orders in the standard work order set is obtained. Based on the priority sequence and the real-time load rate of production equipment, production equipment is allocated to the standard work orders. This approach uses historical experience to make work order priority assessment more in line with actual production patterns, avoids subjective experience bias, improves the rationality of scheduling decisions, and reduces work order delay rates by prioritizing work orders based on their remaining time and resource occupancy.

[0066] 2. By constructing a work order scheduling simulation model through digital twin technology, the model outputs estimated values ​​for total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation. By randomly generating weight combinations and evaluating their fitness, and generating new combinations based on candidate weight combinations to select the optimal weights, the weight combinations of work order correlation score, work order remaining time, and resource occupancy are made more consistent with the actual production scenario. This helps to reduce total delay time and total equipment overload time, and improves total processing efficiency and total time saved by correlation. Attached Figure Description

[0067] Figure 1 This is a schematic diagram of the principle of an intelligent enterprise work order management system according to the present invention. Detailed Implementation

[0068] Embodiments of the present invention are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar symbols denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0069] like Figure 1 The intelligent enterprise work order management system shown includes:

[0070] Work order information collection module: collects enterprise work orders, preprocesses enterprise work orders to generate standard work orders, and multiple standard work orders form a standard work order set;

[0071] Dynamic feature extraction module: Extracts features from standard work orders in the standard work order set, generates work order features, and multiple work order features form a work order feature set; work order features include remaining time and resource usage of the work order.

[0072] Work order scheduling module: Based on the work order feature set, prioritize the standard work orders in the standard work order set and generate work order dispatch instructions;

[0073] In an optional embodiment, the work order scheduling module prioritizes standard work orders in the standard work order set based on the work order feature set and generates a work order dispatch instruction, as follows:

[0074] Acquire historical work order processing data to form a historical work order processing dataset;

[0075] Historical work order processing data includes the total historical processing time;

[0076] The correlation analysis between the work order feature set and the historical work order processing dataset is performed using the Pearson correlation coefficient algorithm or the Spearman rank correlation coefficient algorithm to generate a feature correlation model.

[0077] Based on the feature association model, the association of standard work orders in the standard work order set is evaluated, and the work order association score is generated. The work order association score is combined with the remaining time and resource usage of the work order to evaluate the priority. The weights of the work order association score, the remaining time of the work order, and the resource usage are set to obtain the priority sequence of standard work orders in the standard work order set.

[0078] The work order relevance score ranges from [0,1].

[0079] It should be noted that the feature association model uses the Pearson correlation coefficient algorithm or the Spearman rank correlation coefficient algorithm to perform correlation analysis on the work order feature set and the historical work order processing dataset. The original value range of the Pearson correlation coefficient algorithm or the Spearman rank correlation coefficient algorithm is [-1, 1]. Here, when the work order correlation score is ≤ 0, the correlation score is directly set to 0. Therefore, the value range of the work order correlation score is [0, 1].

[0080] In an optional embodiment, based on a feature association model, the association of standard work orders in the standard work order set is evaluated, and a work order association score is generated for each standard work order, as follows:

[0081] For a specific standard work order in the standard work order set, the historical work order processing data in the historical work order processing dataset is traversed through by the feature association model to obtain the association score set of the specific standard work order. The maximum association score in the association score set of the specific standard work order is taken as the work order association score of the specific standard work order. Let the historical work order processing data corresponding to the maximum association score in the association score set of the specific standard work order be the associated historical work order data.

[0082] In an optional embodiment, the work order relevance score is combined with the remaining time and resource usage of the work order for priority evaluation. Weights are assigned to the work order relevance score, remaining time, and resource usage to obtain the priority sequence of standard work orders in the standard work order set, as follows:

[0083] Multiply the work order relevance score by 100% to get the work order relevance percentage as a percentage.

[0084] The ratio of the remaining time of a work order to the preset maximum remaining time is the percentage of remaining time.

[0085] The ratio of resource usage to the preset maximum resource amount is the resource percentage.

[0086] The work order relevance score, remaining work order time, and resource usage are assigned the first, second, and third weights, respectively.

[0087] For each standard work order, the priority score is as follows:

[0088] The priority score for a standard work order is calculated as follows: work order relevance percentage × first weight + remaining time percentage × second weight + resource percentage × third weight.

[0089] The priority scores of standard work orders in the standard work order set are sorted in descending order to obtain a priority sequence from high to low.

[0090] Obtain the real-time load rate of production equipment; the real-time load rate of production equipment refers to the current resource utilization ratio of the equipment, and includes the load required by standard work orders that have been allocated but not yet started to be processed.

[0091] Obtaining the real-time load rate of production equipment refers to obtaining the real-time load rate of the production equipment required for the current standard work order;

[0092] Based on the priority sequence and the real-time load rate of the production equipment, standard work orders are allocated to production equipment to generate matching results.

[0093] Based on the matching results, a work order dispatch instruction is generated.

[0094] By introducing historical work order processing data and constructing a feature association model using Pearson or Spearman rank correlation coefficient algorithms, the work order priority assessment incorporates historical experience and avoids subjective experience bias. Priority ranking is performed by combining work order correlation scores, remaining time, and resource occupancy, which improves the adaptability of scheduling decisions to actual production patterns.

[0095] In an optional embodiment, standard work orders are allocated to production equipment based on a priority sequence and the real-time load rate of the production equipment, generating matching results as follows:

[0096] Obtain all production equipment of the enterprise and generate a pool of candidate equipment;

[0097] Based on the priority sequence, perform the following production equipment allocation operation for each standard work order in the standard work order set:

[0098] Obtain a standard work order as the target work order, and obtain the required production equipment for the target work order;

[0099] Select the required production equipment corresponding to the target work order from the candidate equipment pool as the initial candidate production equipment pool;

[0100] Select the production equipment with the lowest real-time load rate from the initial pool of candidate production equipment as the final production equipment, and generate matching results;

[0101] At the same time, the allocation of resources takes into account the real-time load rate of production equipment, which optimizes the utilization of equipment resources, effectively reduces the work order delay rate, and improves the rationality of scheduling.

[0102] Equipment is allocated according to priority sequence to ensure that high-priority work orders receive resources first; by screening the required production equipment and selecting the equipment with the lowest real-time load rate, the occurrence of equipment overload is reduced.

[0103] As an explanation, selecting the production equipment with the lowest real-time load rate in the initial pool of candidate production equipment as the final production equipment means that if there is only one production equipment required, then the production equipment with the lowest real-time load rate is selected. If there are multiple production equipment required, then the production equipment with the lowest real-time load rate is selected, and the multiple production equipment have the lowest real-time load rate among the corresponding required production equipment.

[0104] For example, if 5 different production devices are required, that is, 5 types of final production devices are needed, then each type of final production device has the lowest real-time load rate in the initial pool of candidate production devices.

[0105] In an optional embodiment, the work order relevance score, remaining work order time, and resource usage are assigned weights as a first weight, a second weight, and a third weight, respectively. The values ​​of the first weight, the second weight, and the third weight are generated in the following manner:

[0106] Let the first weight, second weight, and third weight be respectively , , ,and , , The range of values ​​for all values ​​is set to [0,2].

[0107] When there is no data to process. , , The value is the default value;

[0108] For clarification, the default value can be understood as the preset value;

[0109] Based on the work order dispatch instructions, collect processing data during the standard work order processing process;

[0110] Statistical analysis of the processed data yields the total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation.

[0111] Obtain real-time status data of production equipment, based on , , The default values, total delay time, total equipment overload time, total processing efficiency, total time saved by correlation, historical work order processing data, and real-time status data of production equipment are used to construct a work order scheduling simulation model through digital twin technology.

[0112] The work order scheduling simulation model is used to... , , The numerical output includes the estimated total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation.

[0113] In an optional embodiment, statistical analysis of the processed data is performed to obtain the total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation.

[0114] The total delay time is the sum of the differences between the actual processing time and the expected processing time for all standard work orders.

[0115] The total overload time of the equipment is the sum of the durations during which the actual load of the equipment exceeds the threshold.

[0116] Overall processing efficiency is the ratio of total processing time to total expected processing time;

[0117] The total time saved by association is generated in the following way:

[0118] For a given standard work order, obtain the actual total processing time of that standard work order, assuming the actual total processing time is... ;

[0119] Retrieve the associated historical work order data for a given standard work order, and extract the total historical processing time from this data. Let the total historical processing time be... ;

[0120] when > At that time, take - The difference is taken as the time saved, and the sum of all the saved times is taken as the total time saved by correlation.

[0121] Multiple weight combinations are randomly generated, each weight combination representing a group. , , The values ​​of each weight combination , , All values ​​are randomly selected within the range [0,2].

[0122] By inputting multiple weight combinations into the work order scheduling simulation model, we can obtain the estimated total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation for each weight combination.

[0123] Based on the estimated total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation, a weighted average method is used to generate the fitness of each weight combination.

[0124] Select the X weight combinations with the highest fitness as candidate weight combinations, where 3 ≤ X and X is a positive integer;

[0125] The values ​​of each weight combination in the selected weight combination are changed to generate multiple new weight combinations. These new weight combinations are then input into the work order scheduling simulation model to obtain the fitness of each new weight combination.

[0126] Choose the weight combination with the highest fitness from the candidate weight combinations and the new weight combinations. , , The final weight.

[0127] In an optional embodiment, the values ​​of each weight combination in the selected weight combinations are changed to generate multiple new weight combinations, as follows:

[0128] Let any two weight combinations in the candidate weight combinations be [ , , ]and[ , , ];

[0129] Then any two weight combinations correspond to a new weight combination as [α× +(1-α) , α× +(1-α) , α× +(1-α) ], where α is a random number between (0,1). If α is randomly changed X times, then any two weight combinations will result in X new weight combinations.

[0130] By using random α values ​​to fuse candidate weight combinations to generate new combinations, the advantages of different weight combinations among the candidate weight combinations are fully combined, thus expanding the weight search range. X random transformations ensure the diversity of new combinations, increase the probability of selecting better weight combinations, make the weight optimization process more flexible and comprehensive, and further enhance the adaptability of weights to dynamic production scenarios.

[0131] By introducing historical work order processing data, a feature association model is constructed using Pearson or Spearman rank correlation coefficient algorithms to generate work order association scores. Combining the remaining time and resource occupancy of work orders, a priority sequence of standard work orders in the standard work order set is obtained. Based on the priority sequence and the real-time load rate of production equipment, production equipment is allocated to standard work orders. This approach leverages historical experience to make work order priority assessment more aligned with actual production patterns, avoiding subjective bias and improving the rationality of scheduling decisions. Prioritizing work orders based on remaining time and resource occupancy reduces work order delay rates. A work order scheduling simulation model is constructed using digital twin technology, outputting estimated values ​​for total delay time, total equipment overload time, total processing efficiency, and total time saved through association. By randomly generating weight combinations and evaluating their fitness, and generating new combinations based on candidate weight combinations to select the optimal weights, the weight combination of work order association scores, remaining time, and resource occupancy better reflects actual production scenarios, which helps reduce total delay time and total equipment overload time, and improves overall processing efficiency and total time saved through association.

[0132] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0133] In the embodiments provided by this invention, it should be understood that the disclosed system or method can be implemented in other ways. For example, the embodiments of the invention described above are merely illustrative; for instance, the division of modules is only a logical functional division, and there may be other division methods in actual implementation.

[0134] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or in the form of hardware plus software functional modules.

[0136] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the basic characteristics of the present invention.

[0137] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. An intelligent enterprise work order management system, characterized in that, include: Work order information collection module: collects enterprise work orders, preprocesses enterprise work orders to generate standard work orders, and multiple standard work orders form a standard work order set; Dynamic feature extraction module: Extracts features from standard work orders in the standard work order set, generates work order features, and multiple work order features form a work order feature set; Work order characteristics include remaining time and resource usage. Work order scheduling module: Based on the work order feature set, prioritize the standard work orders in the standard work order set and generate work order dispatch instructions.

2. The intelligent enterprise work order management system according to claim 1, characterized in that, In the work order scheduling module, standard work orders in the standard work order set are prioritized based on the work order feature set, and work order dispatch instructions are generated, as follows: Acquire historical work order processing data to form a historical work order processing dataset; Historical work order processing data includes the total historical processing time; The correlation analysis between the work order feature set and the historical work order processing dataset is performed using the Pearson correlation coefficient algorithm or the Spearman rank correlation coefficient algorithm to generate a feature correlation model. Based on the feature association model, the association of standard work orders in the standard work order set is evaluated, and the work order association score is generated. The work order association score is combined with the remaining time and resource usage of the work order to evaluate the priority. The weights of the work order association score, the remaining time of the work order, and the resource usage are set to obtain the priority sequence of standard work orders in the standard work order set. The work order relevance score ranges from [0,1]. Obtain the real-time load rate of production equipment; Based on the priority sequence and the real-time load rate of the production equipment, standard work orders are allocated to production equipment to generate matching results. Based on the matching results, a work order dispatch instruction is generated.

3. The intelligent enterprise work order management system according to claim 2, characterized in that, In the work order scheduling module, based on the feature association model, the association of standard work orders in the standard work order set is evaluated, and the work order association score of the standard work orders is generated as follows: For a specific standard work order in the standard work order set, the historical work order processing data in the historical work order processing dataset is traversed through by the feature association model to obtain the association score set of the specific standard work order. The maximum association score in the association score set of the specific standard work order is taken as the work order association score of the specific standard work order. Let the historical work order processing data corresponding to the maximum association score in the association score set of the specific standard work order be the associated historical work order data.

4. The intelligent enterprise work order management system according to claim 2 or 3, characterized in that, In the work order scheduling module, the work order relevance score is combined with the remaining time and resource usage of the work order to evaluate priority. Weights are assigned to the work order relevance score, remaining time, and resource usage to obtain the priority sequence of standard work orders in the standard work order set, as follows: Multiply the work order relevance score by 100% to get the work order relevance percentage as a percentage. The ratio of the remaining time of a work order to the preset maximum remaining time is the percentage of remaining time. The ratio of resource usage to the preset maximum resource amount is the resource percentage. The work order relevance score, remaining work order time, and resource usage are assigned the first, second, and third weights, respectively. For each standard work order, the priority score is as follows: The priority score for a standard work order is calculated as follows: work order relevance percentage × first weight + remaining time percentage × second weight + resource percentage × third weight. The priority scores of standard work orders in the standard work order set are sorted in descending order to obtain a priority sequence from high to low.

5. The intelligent enterprise work order management system according to claim 2, characterized in that, In the work order scheduling module, standard work orders are allocated to production equipment based on priority sequence and real-time load rate of production equipment, generating matching results as follows: Obtain all production equipment of the enterprise and generate a pool of candidate equipment; Based on the priority sequence, perform the following production equipment allocation operation for each standard work order in the standard work order set: Obtain a standard work order as the target work order, and obtain the required production equipment for the target work order; Select the required production equipment corresponding to the target work order from the candidate equipment pool as the initial candidate production equipment pool; Select the production equipment with the lowest real-time load rate from the initial pool of candidate production equipment as the final production equipment, and generate the matching results.

6. The intelligent enterprise work order management system according to claim 4, characterized in that, In the work order scheduling module, the work order relevance score, remaining time, and resource usage are assigned weights as the first weight, second weight, and third weight, respectively. The values ​​of the first weight, second weight, and third weight are generated in the following manner: Let the first weight, second weight, and third weight be respectively , , ,and , , The range of values ​​for all values ​​is set to [0,2]. When there is no data to process. , , The value is the default value; Based on the work order dispatch instructions, collect processing data during the standard work order processing process; Statistical analysis of the processed data yields the total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation. Obtain real-time status data of production equipment, based on , , The default values, total delay time, total equipment overload time, total processing efficiency, total time saved by correlation, historical work order processing data, and real-time status data of production equipment are used to construct a work order scheduling simulation model through digital twin technology. The work order scheduling simulation model is used to... , , The numerical output includes the estimated total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation. Multiple weight combinations are randomly generated, each weight combination representing a group. , , The value of each weight combination , , All values ​​are randomly selected within the range [0,2]. By inputting multiple weight combinations into the work order scheduling simulation model, we can obtain the estimated total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation for each weight combination. Based on the estimated total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation, a weighted average method is used to generate the fitness of each weight combination. Select the X weight combinations with the highest fitness as candidate weight combinations, where 3 ≤ X and X is a positive integer; The values ​​of each weight combination in the selected weight combination are changed to generate multiple new weight combinations. These new weight combinations are then input into the work order scheduling simulation model to obtain the fitness of each new weight combination. Choose the weight combination with the highest fitness from the candidate weight combinations and the new weight combinations. , , The final weight.

7. The intelligent enterprise work order management system according to claim 6, characterized in that, In the work order scheduling module, statistical analysis of the processing data is performed to obtain the total delay time, total equipment overload time, total processing efficiency, and total time saved by correlation. The total delay time is the sum of the differences between the actual processing time and the expected processing time for all standard work orders. The total overload time of the equipment is the sum of the durations during which the actual load of the equipment exceeds the threshold. Overall processing efficiency is the ratio of total processing time to total expected processing time; The total time saved by association is generated in the following way: For a given standard work order, obtain the actual total processing time of that standard work order, assuming the actual total processing time is... ; Retrieve the associated historical work order data for a given standard work order, and extract the total historical processing time from this data. Let the total historical processing time be... ; when > At that time, take - The difference is taken as the time saved, and the sum of all the time saved is taken as the total time saved in relation to the relationship.

8. The intelligent enterprise work order management system according to claim 6, characterized in that, In the work order scheduling module, the value of each weight combination in the selected weight combination is changed to generate multiple new weight combinations, as follows: Any two weight combinations from the candidate weight combinations generate X new weight combinations, resulting in multiple new weight combinations: Let any two weight combinations in the candidate weight combinations be [ , , ]and[ , , ]; Then any two weight combinations correspond to a new weight combination as [α× +(1-α) , α× +(1-α) , α× +(1-α) ], where α is a random number between (0,1). If α is randomly changed X times, then any two weight combinations will result in X new weight combinations.

Images