Simulation model construction method and simulation model construction device

Abstract

The present disclosure is about a method for constructing a simulation model and a device for constructing a simulation model, the method comprising: obtaining a process operation log and process business information; generating a process model G_3 based on the process operation log and the process business information; screening the process operation log using the process model G_3 to obtain process data; obtaining additional relationships based on the process data; generating an original simulation model based on the process model G_3 and the additional relationships; adjusting the simulation parameters of the original simulation model using the process data to obtain a target simulation model. In this way, the present disclosure can obtain a simulation model based on the process operation log and the process business information, that is, the process operation log and the process business information can be effectively combined to automatically generate a simulation model. The attention paid to the changes in the process and the changes in the data during the actual operation of the project is strengthened, and the accuracy of the constructed simulation model is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and more specifically, to a method for constructing a simulation model and a device for constructing a simulation model. Background Art

[0002] With the development of science and technology, simulation technology has become an indispensable means for the development of various complex systems, and various simulation software has emerged, such as Dassault APS system, Anylogic, FlexSim, etc. These software have been polished into mature products and have been widely used. However, reliable simulation software is only part of completing accurate simulation. What is more important is to ensure that the model running in the simulation software is also very accurate.

[0003] In the related technology, professional simulation engineers observe and clean the data, select appropriate simulation models in the simulation software, and adjust simulation parameters to make the operation of the simulation model more consistent with the actual situation. However, when constructing the simulation model, simulation engineers often set the simulation model and simulation parameters based on their previous experience in establishing simulation models for similar equipment, and pay insufficient attention to changes in the process and data during the actual operation of the project, resulting in poor accuracy of the constructed simulation model. Summary of the invention

[0004] The present disclosure provides a method for constructing a simulation model and a device for constructing a simulation model, so as to at least solve the problem that the precision of the constructed simulation model in the above-mentioned related technologies is poor and inaccurate.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for constructing a simulation model is provided, comprising: obtaining a process operation log and process business information; generating a process model G_3 based on the process operation log and the process business information; filtering the process operation log using the process model G_3 to obtain process data; obtaining additional relationships based on the process data; generating an original simulation model based on the process model G_3 and the additional relationships; and adjusting simulation parameters of the original simulation model using the process data to obtain a target simulation model.

[0006] Optionally, the process operation log includes operation logs of multiple cases, each of which includes multiple actions; the process model G_3 is generated based on the process operation log and the process business information, including: based on the multiple actions included in each case in the multiple cases, generating a connection relationship diagram G_1 between the multiple actions; based on the process business information, generating a business process diagram G_0; based on the overlapping part between the business process diagram G_0 and the connection relationship diagram G_1 between the multiple actions, generating a business process extension diagram G_0'; based on the connection relationship diagram G_1 between the multiple actions and the business process extension diagram G_0', generating the process model G_3.

[0007] Optionally, generating the process model G_3 according to the connection relationship graph G_1 between the multiple actions and the business process extension graph G_0' includes: calculating the difference between the connection relationship graph G_1 between the multiple actions and the business process extension graph G_0' to obtain the business process supplement graph G_2; generating a business missing process supplement graph G_2' based on the business process supplement graph G_2; and superimposing the business process extension graph G_0' and the business missing process supplement graph G_2' to obtain the process model G_3.

[0008] Optionally, the business process complement graph G_2 includes multiple nodes, and multiple edges are formed between the multiple nodes; the business missing process complement graph G_2' is generated based on the business process complement graph G_2, including: for each of the multiple nodes, determining a first number of the cases passing through the node and a second number of the cases not passing through the node; for each of the multiple edges, determining a third number of the cases passing through the edge and a fourth number of the cases not passing through the edge; based on the first number and the second number, determining whether the node is an additional supplementary node; based on the third number and the fourth number, determining whether the edge is an additional supplementary edge; using the additional supplementary nodes among the multiple nodes and the additional supplementary edges among the multiple edges to generate the business missing process complement graph G_2'.

[0009] Optionally, judging whether the node is an additional supplementary node based on the first quantity and the second quantity includes: calculating a first sum of the first quantity and the second quantity; calculating a first ratio between the first quantity and the first sum; and determining that the node is the additional supplementary node when the first ratio is greater than a preset first threshold.

[0010] Optionally, judging whether the edge is an additional supplementary edge based on the third quantity and the fourth quantity includes: if one of the two nodes corresponding to the edge belongs to the additional supplementary node, and the other node is included in the business process expansion graph G_0', calculating a second sum result between the third quantity and the fourth quantity; calculating a second ratio between the third quantity and the second sum result; and determining that the edge is the additional supplementary edge when the second ratio is greater than a preset second threshold.

[0011] Optionally, the using the process model G_3 to filter the process operation log to obtain process data includes: filtering out cases that are completely run in the process model G_3 from the multiple cases as the process data.

[0012] Optionally, the obtaining of additional relations based on the process data includes: classifying a plurality of complete running cases to obtain a plurality of complete running case sets; for each complete running case in the plurality of complete running cases, obtaining a case running interval corresponding to the complete running case set to which the complete running case belongs, wherein the left endpoint of the case running interval is the minimum time corresponding to the complete running case in the complete running case set, and the right endpoint of the case running interval is the maximum time corresponding to the complete running case in the complete running case set; expanding the plurality of complete running case sets to obtain at least one expanded case set, wherein, for each complete running case set, adding the complete running cases whose corresponding running times in other complete running case sets are included in the case running interval corresponding to the complete running case set to the complete running case set to obtain an expanded case set corresponding to the complete running case set; and finding the running order between the expanded complete running cases in each expanded case set and the original complete running cases contained in the expanded case set as the additional relation.

[0013] Optionally, using the process data to adjust the simulation parameters of the original simulation model to obtain a target simulation model includes: building a simulator corresponding to the original simulation model; iteratively adjusting the simulation parameters of the original simulation model using the complete running case and the simulator until the iteration terminates: obtaining the simulation result corresponding to this iteration by the following operations: selecting multiple simulation parameters whose corresponding simulation results have the highest degree of match with the actual results from the simulation parameter group obtained in the previous iteration; performing cross-mutation on the multiple simulation parameters to obtain cross-mutation simulation parameters; based on the complete running case, using the simulator to perform simulation verification on the cross-mutation simulation parameters to obtain cross-mutation simulation results corresponding to the cross-mutation simulation parameters; when the iteration terminates, selecting the simulation parameters whose corresponding simulation results in previous iterations are most consistent with the actual results as the simulation parameters of the target simulation model.

[0014] Optionally, the method further includes: determining that the iteration is terminated when a preset condition is met; wherein the preset condition includes one of the following conditions: the number of iterations reaches a preset number of iterations; and at the end of the iteration, there are cross-variation simulation parameters whose corresponding cross-variation simulation results differ from the actual results by less than a preset difference threshold.

[0015] Optionally, the difference between the crossover mutation simulation result and the real result is expressed by the following formula:

[0016]

[0017] Among them, job_i is the case of the i-th complete operation, sim p (t[i]|real_s) is the time it takes for the ith complete run case to complete on the simulator, real t (t[i]) is the actual running time of the i-th complete running case.

[0018] According to a second aspect of an embodiment of the present disclosure, a device for constructing a simulation model is provided, comprising: an acquisition module configured to acquire a process operation log and process business information; a generation module configured to generate a process model G_3 based on the process operation log and the process business information; a screening module configured to screen the process operation log using the process model G_3 to obtain process data; the acquisition module configured to acquire additional relationships based on the process data; the generation module configured to generate an original simulation model based on the process model G_3 and the additional relationships; an adjustment module configured to adjust the simulation parameters of the original simulation model using the process data to obtain a target simulation model.

[0019] Optionally, the process operation log includes operation logs of multiple cases, each of which includes multiple actions; the generation module is configured to: generate a connection relationship diagram G_1 between the multiple actions based on the multiple actions included in each case in the multiple cases; generate a business process diagram G_0 based on the process business information; generate a business process extension diagram G_0' based on the overlapping part between the business process diagram G_0 and the connection relationship diagram G_1 between the multiple actions; generate the process model G_3 based on the connection relationship diagram G_1 between the multiple actions and the business process extension diagram G_0'.

[0020] Optionally, the generation module is configured to: calculate the difference between the connection relationship graph G_1 between the multiple actions and the business process expansion graph G_0' to obtain the business process supplement graph G_2; based on the business process supplement graph G_2, generate a business missing process supplement graph G_2'; superimpose the business process expansion graph G_0' and the business missing process supplement graph G_2' to obtain the process model G_3.

[0021] Optionally, the business process complement graph G_2 includes multiple nodes, and multiple edges are formed between the multiple nodes; the generation module is configured to: for each of the multiple nodes, determine the first number of the cases passing through the node and the second number of the cases not passing through the node; for each of the multiple edges, determine the third number of the cases passing through the edge and the fourth number of the cases not passing through the edge; based on the first number and the second number, determine whether the node is an additional supplementary node; based on the third number and the fourth number, determine whether the edge is an additional supplementary edge; and generate the business missing process complement graph G_2' by using the additional supplementary nodes among the multiple nodes and the additional supplementary edges among the multiple edges.

[0022] Optionally, the generation module is configured to: calculate a first sum of the first quantity and the second quantity; calculate a first ratio between the first quantity and the first sum; and determine that the node is the additional supplementary node when the first ratio is greater than a preset first threshold.

[0023] Optionally, the generation module is configured to: if one of the two nodes corresponding to the edge belongs to the additional supplementary node, and the other node is included in the business process expansion graph G_0', then calculate the second sum result between the third quantity and the fourth quantity; calculate the second ratio between the third quantity and the second sum result; and when the second ratio is greater than a preset second threshold, determine that the edge is the additional supplementary edge.

[0024] Optionally, the screening module is configured to screen out cases that are completely run in the process model G_3 from the multiple cases as the process data.

[0025] Optionally, the acquisition module is configured to: classify multiple complete running cases to obtain multiple complete running case sets; for each complete running case in the multiple complete running cases, obtain a case running interval corresponding to the complete running case set to which the complete running case belongs, wherein the left endpoint of the case running interval is the minimum time corresponding to the complete running case in the complete running case set, and the right endpoint of the case running interval is the maximum time corresponding to the complete running case in the complete running case set; expand the multiple complete running case sets to obtain at least one expanded case set, wherein, for each complete running case set, add the complete running cases whose corresponding running times in other complete running case sets are included in the case running interval corresponding to the complete running case set to the complete running case set to obtain the expanded case set corresponding to the complete running case set; and find the running order between the expanded complete running cases in each expanded case set and the original complete running cases contained in the expanded case set as the additional relationship.

[0026] Optionally, the adjustment module is configured to: build a simulator corresponding to the original simulation model; adjust the simulation parameters of the original simulation model in an iterative manner using the complete running case and the simulator until the iteration terminates: obtain the simulation result corresponding to this iteration by the following operations: select multiple simulation parameters whose corresponding simulation results have the highest degree of match with the actual results from the simulation parameter group obtained in the previous iteration; perform cross-mutation on the multiple simulation parameters to obtain cross-mutation simulation parameters; based on the complete running case, use the simulator to perform simulation verification on the cross-mutation simulation parameters to obtain the cross-mutation simulation results corresponding to the cross-mutation simulation parameters; when the iteration terminates, select the simulation parameters whose corresponding simulation results in previous iterations are most consistent with the actual results as the simulation parameters of the target simulation model.

[0027] Optionally, the construction device also includes: a determination module, configured to determine that the iteration is terminated when a preset condition is met; wherein the preset condition includes one of the following conditions: the number of iterations reaches a preset number of iterations; and at the end of the iteration, there are cross-mutation simulation parameters whose corresponding cross-mutation simulation results have a difference with the actual results that is less than a preset difference threshold.

[0028] Optionally, the difference between the crossover mutation simulation result and the real result is expressed by the following formula:

[0029]

[0030] Among them, job_i is the case of the i-th complete operation, sim p (t[i]|real_s) is the time it takes for the ith complete run case to complete on the simulator, real t (t[i]) is the actual running time of the i-th complete running case.

[0031] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement a method for constructing a simulation model according to the present disclosure.

[0032] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for constructing a simulation model according to the present disclosure.

[0033] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0034] The present disclosure can obtain a simulation model based on the process operation log and process business information, that is, the process operation log and process business information can be effectively combined to automatically generate a simulation model. This strengthens the attention paid to the changes in the process and data during the actual operation of the project, and improves the accuracy of the constructed simulation model.

[0035] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0037] Figure 1 is a flow chart illustrating a method for constructing a simulation model according to an exemplary embodiment of the present disclosure;

[0038] Figure 2 is a schematic diagram showing a connection relationship diagram G_1 between multiple actions according to an exemplary embodiment of the present disclosure;

[0039] Figure 3 is a schematic diagram showing a business process diagram G_0 according to an exemplary embodiment of the present disclosure;

[0040] Figure 4 is a schematic diagram showing a business process expansion graph G_0' according to an exemplary embodiment of the present disclosure;

[0041] Figure 5 is a schematic diagram showing a comparison between a connection relationship diagram G_1 between multiple actions, a business process expansion diagram G_0' and a business process supplement diagram G_2 according to an exemplary embodiment of the present disclosure;

[0042] Figure 6 is a schematic diagram illustrating a method of determining additional supplementary nodes and additional supplementary edges according to an exemplary embodiment of the present disclosure;

[0043] Figure 7 is a schematic diagram illustrating an additional relationship according to an exemplary embodiment of the present disclosure;

[0044] Figure 8 is a block diagram illustrating a construction apparatus of a simulation model according to an exemplary embodiment of the present disclosure;

[0045] Fig. 9 is a block diagram illustrating an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0047] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation methods described in the following examples do not represent all implementation methods consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the attached claims.

[0048] It should be noted that the phrase "at least one of the items" in the present disclosure includes three types of parallel situations: "any one of the items", "a combination of any number of the items", and "all of the items". For example, "including at least one of A and B" includes the following three parallel situations: (1) including A; (2) including B; (3) including A and B. Another example is "executing at least one of step 1 and step 2" which means the following three parallel situations: (1) executing step 1; (2) executing step 2; (3) executing step 1 and step 2.

[0049] Figure 1 is a flowchart illustrating a method for constructing a simulation model according to an exemplary embodiment of the present disclosure.

[0050] Reference Figure 1 In step 101, the process operation log and process business information can be obtained. The process operation log can include the operation logs of multiple cases, each case can include multiple actions, and each action of each case can correspond to an operation log. For example, a case can correspond to a case id, that is, case_id, each case id can correspond to multiple action ids, and each action id has an execution time. The process business information is the execution order of multiple processes contained in the case specified by the customer, and the granularity of the process business information is coarse.

[0051] In step 102, a process model G_3 may be generated based on the process operation log and process business information.

[0052] According to an exemplary embodiment of the present disclosure, as mentioned above, the process operation log may include operation logs of multiple cases, and each case may include multiple actions.

[0053] Based on the multiple actions included in each case in the multiple cases, a connection relationship graph G_1 between the multiple actions can be generated. In the following, the solution of the present disclosure is described by taking semiconductor production as an example. Figure 2 , is a schematic diagram showing a connection relationship diagram G_1 between multiple actions according to an exemplary embodiment of the present disclosure. Figure 2 In the figure, multiple nodes are shown, namely: "Prepare for lithography", "Start lithography", "End lithography", "Measurement 1", empty node (dummy), "Start etching", "End etching", "Measurement 2", "Waiting pool waiting" and "Cleaning". The arrows between these nodes represent the edges formed between the nodes. It should be noted that a case can also be called an event (case) or a job task, and each case can start with "Prepare for lithography" and end with "Cleaning".

[0054] Based on the process business information, a business process diagram G_0 can be generated. Figure 3 , is a schematic diagram showing a business process diagram G_0 according to an exemplary embodiment of the present disclosure. Figure 3 In FIG. 1 , multiple nodes are shown, namely, “lithography”, “measurement”, “etching”, and “cleaning”. The arrows between these nodes represent the edges formed between the nodes. Figure 2 and Figure 3 By comparison, we can see that the business process graph G_0 is much sparser than the connection relationship graph G_1 between multiple actions.

[0055] According to the overlapping parts between the business process graph G_0 and the connection relationship graph G_1 between multiple actions, the business process expansion graph G_0' can be generated, that is, the business process graph G_0 and the connection relationship graph G_1 between multiple actions can be mapped to find out which parts of the connection relationship graph G_1 between multiple actions correspond to the "photolithography" in the business process graph G_0; find out which parts of the connection relationship graph G_1 between multiple actions correspond to the "measurement" in the business process graph G_0; find out which parts of the connection relationship graph G_1 between multiple actions correspond to the "etching" in the business process graph G_0; find out which parts of the connection relationship graph G_1 between multiple actions correspond to the "cleaning" in the business process graph G_0.

[0056] For example, "Prepare for photolithography", "Start photolithography", and "End photolithography" in the connection relationship diagram G_1 between multiple actions correspond to "Photolithography" in the business process diagram G_0; "Measurement 1" in the connection relationship diagram G_1 between multiple actions corresponds to "Measurement" in the business process diagram G_0; "Start etching" and "End etching" in the connection relationship diagram G_1 between multiple actions correspond to "Etching" in the business process diagram G_0; "Cleaning" in the connection relationship diagram G_1 between multiple actions corresponds to "Cleaning" in the business process diagram G_0. Figure 2 It can be seen that the connection relationship diagram G_1 between multiple actions includes "Measurement 2", and "Measurement 2" is between "End Etching" and "Cleaning", but Figure 3 It can be seen that there is no "measurement" between "etching" and "cleaning" contained in the business process diagram G_0 corresponding to the process business information provided by the customer. Therefore, "measurement 2" in the connection relationship diagram G_1 between multiple actions cannot find the corresponding relationship with the business process diagram G_0, that is, it cannot find the mapping relationship. Therefore, "measurement 2" in the connection relationship diagram G_1 between multiple actions will be ignored and will not appear in the business process expansion diagram G_0'. Figure 4 , is a schematic diagram showing a business process expansion graph G_0' according to an exemplary embodiment of the present disclosure. Figure 4 It can be seen that the business process expansion graph G_0' will only select the points and edges that appear in the connection relationship graph G_1 between multiple actions, but some points and edges will not be selected. For example, the node "Measurement 2" in the connection relationship graph G_1 between multiple actions is not selected into the business process expansion graph G_0'.

[0057] The process model G_3 can be generated according to the connection relationship graph G_1 between multiple actions and the business process expansion graph G_0'.

[0058] According to an exemplary embodiment of the present disclosure, the difference between the connection relationship graph G_1 between multiple actions and the business process expansion graph G_0' can be calculated to obtain the business process supplement graph G_2. As mentioned above, the points and edges appearing in the connection relationship graph G_1 between multiple actions will not be completely selected into the business process expansion graph G_0'. At this time, the points and edges that are not selected into the business process expansion graph G_0' form the business process supplement graph G_2. Figure 5 , is a schematic diagram showing a comparison between a connection relationship diagram G_1 between multiple actions, a business process expansion diagram G_0' and a business process supplement diagram G_2 according to an exemplary embodiment of the present disclosure. Figure 5 In the business process supplementary diagram G_2, the nodes "prepare for lithography", "end lithography", "wait for pool", "empty node", "end etching", and "measurement 2" are shown, and Figure 5 The edge between the two nodes "Prepare for photolithography" and "End photolithography" in the business process supplementary graph G_2 has been removed. Figure 5 The retained edges in the business process complement graph G_2 are all the edges in the connection relationship graph G_1 between multiple actions that are not selected into the business process expansion graph G_0'.

[0059] Based on the business process supplement graph G_2, the business missing process supplement graph G_2' can be generated. Then, the business process expansion graph G_0' and the business missing process supplement graph G_2' can be superimposed to obtain the process model G_3.

[0060] According to an exemplary embodiment of the present disclosure, Figure 5 It can be seen that the business process supplementary graph G_2 includes multiple nodes, and multiple edges are formed between the multiple nodes. For each of the multiple nodes, the first number of cases passing through the node and the second number of cases not passing through the node can be determined. For each of the multiple edges, the third number of cases passing through the edge and the fourth number of cases not passing through the edge can be determined. Based on the first number and the second number, it can be determined whether the node is an additional supplementary node; based on the third number and the fourth number, it can be determined whether the edge is an additional supplementary edge. Next, the additional supplementary nodes in the multiple nodes and the additional supplementary edges in the multiple edges can be used to generate the business missing process supplementary graph G_2'. It can be seen that the business missing process supplementary graph G_2' is a subgraph of the business process supplementary graph G_2.

[0061] According to an exemplary embodiment of the present disclosure, referring to Figure 6 , is a schematic diagram showing a method of determining additional supplementary nodes and additional supplementary edges according to an exemplary embodiment of the present disclosure. Figure 6 In the process 1, Figure 2The connection relationship between multiple actions in G_1 is the process of "start etching" and "end etching"; "Process 2" can correspond to Figure 2 The connection relationship diagram between multiple actions in G_1 shows the process of "cleaning"; Figure 6 The node R0 in can correspond to Figure 2 The node "Measurement 2" in the connection relationship graph G_1 between multiple actions in FIG. Assume that the first number of cases passing through the node R0 is 50, and the second number of cases not passing through the node R0 is 1000.

[0062] A first sum result 1050 between the first number 50 and the second number 1000 may be calculated, and then a first ratio 50 / 1050 between the first number 50 and the first sum result 1050 may be calculated. Next, when the first ratio 50 / 1050 is greater than a preset first threshold, the node R0 may be determined to be an additional supplementary node, that is, the node "Measurement 2" may be determined to be an additional supplementary node.

[0063] According to an exemplary embodiment of the present disclosure, if one of the two nodes corresponding to the edge is an additional supplementary node and the other node is included in the business process expansion graph G_0', a second sum of the third number of cases passing through the edge and the fourth number of cases not passing through the edge can be calculated. Figure 5 It can be seen that the edge l 目标 A node “prepare for lithography” is included in the business process expansion graph G_0'. As mentioned above, the edge l 目标 The other node "Measurement 2" belongs to an additional supplementary node, then the edge l 目标 The third number of cases and the number of cases that do not pass through the edge l 目标 Assuming that the third quantity is 60 and the fourth quantity is 800, the second summation result between the third quantity 60 and the fourth quantity 800 is 860. Then, the second ratio 60 / 860 between the third quantity 60 and the second summation result 860 can be calculated. Next, when the second ratio 60 / 860 is greater than the preset second threshold, it can be determined that the edge l 目标 For additional supplementary sides.

[0064] In step 103, the process model G_3 may be used to filter the process operation log to obtain process data.

[0065] According to an exemplary embodiment of the present disclosure, cases that are fully run in the process model G_3 can be screened out from multiple cases as the above process data. That is, only cases that have completed all processes included in the process model G_3 will be used as process data, and cases that have not completed all processes included in the process model G_3 will be considered as abnormal cases and will be eliminated instead of being used as process data.

[0066] At step 104 , additional relationships may be obtained based on the process data.

[0067] According to an exemplary embodiment of the present disclosure, multiple complete running cases can be classified to obtain multiple complete running case sets. For example, multiple complete running cases can be classified according to case id, and each complete running case set can be counted as E_{case_id}.

[0068] Then, for each complete running case among the multiple complete running cases, the case running interval [t_l, t_r] corresponding to the complete running case set to which the complete running case belongs can be obtained, wherein the left endpoint t_l of the case running interval is the minimum time corresponding to the complete running case in the complete running case set, and the right endpoint t_r of the case running interval is the maximum time corresponding to the complete running case in the complete running case set.

[0069] Next, multiple complete running case sets can be expanded to obtain at least one expanded case set. For each complete running case set E_{case_id}, complete running cases whose corresponding running times in other complete running case sets are included in the case running interval [t_l, t_r] corresponding to the complete running case set E_{case_id} can be added to the complete running case set E_{case_id} to obtain the expanded case set E'_{case_id} corresponding to the complete running case set E_{case_id}.

[0070] Then, the running order between the expanded complete running cases in each expanded case set E'_{case_id} and the original complete running cases included in the expanded case set E'_{case_id} can be found as the above-mentioned additional relationship.

[0071] Reference Figure 7 , is a schematic diagram showing an additional relationship according to an exemplary embodiment of the present disclosure. The dashed arrow is the “additional relationship”. Figure 7In the figure, a timeline, case 1 and case 2 are shown. Case 1 includes three processes: wait 1 - start 1 - end 1, and case 2 includes three processes: wait 2 - start 2 - end 2. Moreover, case 2 will start waiting when case 1 has started but not ended, and case 2 will start only after case 1 ends. That is, the start of the next case should be after the end of the previous case, which is the "extra relationship". The above-mentioned "extra relationship" should be filled in the obtained process model G_3, and then the original simulation model can be obtained. It can be seen that the original simulation model can be understood as consisting of the process model G_3 and some "extra relationships".

[0072] In step 105 , as described above, an original simulation model may be generated based on the process model G_3 and the additional relationships.

[0073] In step 106, the simulation parameters of the original simulation model can be adjusted using the process data to obtain a target simulation model. That is, the simulation parameters of the original simulation model can be adjusted using the aforementioned "complete running case" to obtain a target simulation model.

[0074] According to an exemplary embodiment of the present disclosure, the original simulation model can be adjusted by non-gradient optimization and tuning, thereby correcting the optimal simulation parameters. Among them, a simulator sim corresponding to the original simulation model can be built, and then the simulation parameters of the original simulation model can be adjusted by iteratively using the complete running case and the simulator sim until the iteration is terminated.

[0075] The simulation result corresponding to this iteration can be obtained by the following operation: multiple simulation parameters with the highest matching degree between the corresponding simulation result and the real result can be selected from the simulation parameter group obtained in the previous iteration, that is, some simulation parameters with the corresponding simulation result and the real result can be selected from the simulation parameter group obtained in the previous iteration. Then, cross-mutation can be performed on multiple simulation parameters to obtain cross-mutation simulation parameters. The multiple simulation parameters with the highest matching degree can be multiple simulation parameters with the highest matching degree of a preset number, or multiple simulation parameters with a matching degree in a preset proportion, or multiple simulation parameters with a matching degree higher than a preset threshold, which are not exhaustively listed in the embodiment of the present invention.

[0076] It should be noted that the simulation parameter can be an n-dimensional vector, for example, it can be expressed as (a1, a2, a3..., a n). The meaning of "cross-mutation" is to use the above-mentioned partial simulation parameters to expand the simulation parameter set. For example, suppose there are three partial simulation parameters, namely simulation parameter 1 (a1, a2, a3, a4); simulation parameter 2 (a5, a6, a7, a8); simulation parameter 3 (a9, a10, a111, a12, a13, a14); simulation parameter 4 (a11, a12, a13, a14); simulation parameter 5 (a12, a13, a14); simulation parameter 6 (a14, a15, a16, a17, a18); simulation parameter 7 (a15, a16, a17, a18); simulation parameter 8 (a19, a10, a111, a12, a13, a14); simulation parameter 9 (a10, a11 10 , a 11 , a 12 ). Then the "cross-mutation" method can be used to generate new cross-mutation simulation parameters: the first half of simulation parameter 1, i.e., a1 and a2, can be intercepted as the first half of the new cross-mutation simulation parameters; and the second half of simulation parameter 2, i.e., a7 and a8, can be intercepted as the second half of the new cross-mutation simulation parameters, and the new cross-mutation simulation parameters (a1, a2, a7, a8) can be obtained. Through the "cross-mutation" method, multiple cross-mutation simulation parameters can be obtained to expand the simulation parameter set.

[0077] Then, based on the complete running case, the simulator sim can be used to simulate and verify the crossover mutation simulation parameters to obtain the crossover mutation simulation results corresponding to the crossover mutation simulation parameters at the end of this iteration.

[0078] When the iteration ends, the simulation parameters whose corresponding simulation results in previous iterations are most consistent with the actual results can be selected as the simulation parameters of the target simulation model.

[0079] According to an exemplary embodiment of the present disclosure, when a preset condition is met, the iteration may be determined to be terminated. The preset condition includes one of the following conditions: the number of iterations reaches a preset number of iterations; or, at the end of the iteration, there is a cross-mutation simulation parameter whose corresponding cross-mutation simulation result and the actual result differ by less than a preset difference threshold.

[0080] According to an exemplary embodiment of the present disclosure, the difference between the crossover mutation simulation result and the real result can be expressed by the following formula:

[0081]

[0082] Among them, job_i is the case of the i-th complete operation, sim p (t[i]|real_s) is the time it takes for the ith complete run of the case to complete on the simulator sim, real t (t[i]) is the actual running time of the i-th complete run case.

[0083] For example, the above process data, i.e., the complete running case, can be used to build the historical simulation data set of the simulator sim, which can include the historical time set of all job tasks entering the device real_s:{job_i,t_i}, and the historical time set of all job tasks completed on the device real_t:{job_i,t_i}. Among them, "job_i" represents the i-th job task, and each "job task" is a complete running case. "The historical time when the job task enters the device" can be understood as Figure 2 The log time corresponding to "prepare for lithography" in the above example; "the historical time when the job task was completed on the device" can be understood as Figure 2 The log time corresponding to the “cleaning” in . Assume that the historical simulation data set contains a total of 10 complete run cases.

[0084] For each simulation parameter, the historical simulation data set can be brought into the simulator sim to obtain the completion time set of each job task in the simulator sim for each historical simulation data, that is, the running completion time of each complete running case in the simulator sim can be obtained, and at this time, a total of 10 running completion times can be obtained. In addition, for each complete running case in the 10 complete running cases, there is also a corresponding real running time, and at this time, there are a total of 10 real running times.

[0085] For each of the 10 complete running cases, the difference between the running completion time of the complete running case in the simulator sim and the real running time corresponding to the complete running case can be calculated, and at this time, 10 differences can be obtained. Then, the sum of the absolute values ​​of the 10 differences can be calculated, and then the sum of the absolute values ​​of the 10 differences can be used to judge the degree of difference between the simulation result and the real result of each simulation parameter. Among them, for each simulation parameter, the smaller the sum of the absolute values ​​of the above differences corresponding to multiple complete running cases is, the smaller the difference between the simulation result and the real result of the simulation parameter is, and the better the simulation effect of the simulation parameter is, that is, the more inclined to retain the simulation parameter.

[0086] Figure 8 is a block diagram illustrating a construction apparatus of a simulation model according to an exemplary embodiment of the present disclosure.

[0087] Reference Figure 8 The device 800 may include an acquisition module 801, a generation module 802, a screening module 803 and an adjustment module 804.

[0088] The acquisition module 801 is configured to acquire process operation logs and process business information;

[0089] A generating module 802 is configured to generate a process model G_3 based on the process operation log and the process business information;

[0090] The screening module 803 is configured to screen the process operation log using the process model G_3 to obtain process data;

[0091] The acquisition module 801 is configured to acquire additional relations based on the process data;

[0092] The generating module 802 is configured to generate an original simulation model based on the process model G_3 and the additional relationship;

[0093] The adjustment module 804 is configured to adjust the simulation parameters of the original simulation model using the process data to obtain a target simulation model.

[0094] According to an exemplary embodiment of the present disclosure, the process operation log includes operation logs of multiple cases, each of which includes multiple actions;

[0095] The generating module 802 is configured to:

[0096] Based on the multiple actions included in each of the multiple cases, generate a connection relationship graph G_1 between the multiple actions;

[0097] Based on the process business information, generate a business process diagram G_0;

[0098] Generate a business process expansion graph G_0' according to the overlapped part between the business process graph G_0 and the connection relationship graph G_1 between the multiple actions;

[0099] The process model G_3 is generated according to the connection relationship graph G_1 between the multiple actions and the business process expansion graph G_0'.

[0100] According to an exemplary embodiment of the present disclosure, the generating module 802 is configured to:

[0101] Calculate the difference between the connection relationship graph G_1 between the multiple actions and the business process expansion graph G_0' to obtain the business process supplement graph G_2;

[0102] Based on the business process supplementary graph G_2, generate a business missing process supplementary graph G_2';

[0103] The business process expansion graph G_0' and the business missing process supplement graph G_2' are superimposed to obtain the process model G_3.

[0104] According to an exemplary embodiment of the present disclosure, the business process complement graph G_2 includes a plurality of nodes, and a plurality of edges are formed between the plurality of nodes;

[0105] The generating module 802 is configured to:

[0106] For each node of the plurality of nodes, determining a first number of the cases that passed through the node and a second number of the cases that did not pass through the node;

[0107] For each of the plurality of edges, determining a third number of the cases that pass through the edge and a fourth number of the cases that do not pass through the edge;

[0108] Based on the first number and the second number, determining whether the node is an additional supplementary node;

[0109] Based on the third number and the fourth number, determining whether the edge is an additional supplementary edge;

[0110] The service missing process supplement graph G_2' is generated by using the additional supplementary nodes among the multiple nodes and the additional supplementary edges among the multiple edges.

[0111] According to an exemplary embodiment of the present disclosure, the generating module 802 is configured to:

[0112] calculating a first sum result between the first number and the second number;

[0113] calculating a first ratio between the first number and the first sum result;

[0114] When the first ratio is greater than a preset first threshold, the node is determined to be the additional supplementary node.

[0115] According to an exemplary embodiment of the present disclosure, the generating module 802 is configured to:

[0116] If one of the two nodes corresponding to the edge belongs to the additional supplementary node, and the other node is included in the business process expansion graph G_0', then a second sum result between the third number and the fourth number is calculated;

[0117] calculating a second ratio between the third quantity and the second addition result;

[0118] When the second ratio is greater than a preset second threshold, the edge is determined to be the additional supplementary edge.

[0119] According to an exemplary embodiment of the present disclosure, the screening module 803 is configured to:

[0120] The cases that are completely run in the process model G_3 are selected from the multiple cases as the process data.

[0121] According to an exemplary embodiment of the present disclosure, the acquisition module 801 is configured to:

[0122] Classify multiple complete running cases to obtain multiple complete running case sets;

[0123] For each of the multiple completely run cases, obtain a case run interval corresponding to the complete run case set to which the completely run case belongs, wherein the left endpoint of the case run interval is the minimum time corresponding to the completely run case in the complete run case set, and the right endpoint of the case run interval is the maximum time corresponding to the completely run case in the complete run case set;

[0124] Expanding the multiple complete running case sets to obtain at least one expanded case set, wherein, for each complete running case set, adding complete running cases whose corresponding running times in other complete running case sets are included in the case running interval corresponding to the complete running case set to the complete running case set to obtain an expanded case set corresponding to the complete running case set;

[0125] The running order between the expanded complete running cases in each expanded case set and the original complete running cases included in the expanded case set is found as the additional relationship.

[0126] According to an exemplary embodiment of the present disclosure, the adjustment module 804 is configured to:

[0127] Building a simulator corresponding to the original simulation model;

[0128] The simulation parameters of the original simulation model are adjusted by using the complete running case and the simulator in an iterative manner until the iteration is terminated:

[0129] The simulation results corresponding to this iteration are obtained through the following operations:

[0130] Selecting multiple simulation parameters whose corresponding simulation results have the highest matching degree with the real results from the simulation parameter group obtained in the previous iteration;

[0131] Performing crossover mutation on the multiple simulation parameters to obtain crossover mutation simulation parameters;

[0132] Based on the complete running case, using the simulator to perform simulation verification on the crossover-mutation simulation parameters to obtain crossover-mutation simulation results corresponding to the crossover-mutation simulation parameters;

[0133] When the iteration is terminated, the simulation parameters whose corresponding simulation results in previous iterations are most consistent with the actual results are selected as the simulation parameters of the target simulation model.

[0134] According to an exemplary embodiment of the present disclosure, the constructing device 800 may further include:

[0135] A determination module is configured to determine that the iteration is terminated when a preset condition is met;

[0136] The preset condition includes one of the following conditions:

[0137] The number of iterations reaches the preset number of iterations; and

[0138] At the end of this iteration, there are cross-mutation simulation parameters whose corresponding cross-mutation simulation results and actual results have a difference less than a preset difference threshold value.

[0139] According to an exemplary embodiment of the present disclosure, the difference between the crossover mutation simulation result and the real result is expressed by the following formula:

[0140]

[0141] Among them, job_i is the case of the i-th complete operation, sim p (t[i]|real_s) is the time it takes for the ith complete run case to complete on the simulator, real t (t[i]) is the actual running time of the i-th complete running case.

[0142] Fig. 9 is a block diagram illustrating an electronic device 900 according to an exemplary embodiment of the present disclosure.

[0143] Reference Fig. 9 The electronic device 900 includes at least one memory 901 and at least one processor 902. The at least one memory 901 stores instructions. When the instructions are executed by the at least one processor 902, the method for constructing a simulation model according to an exemplary embodiment of the present disclosure is executed.

[0144] As an example, the electronic device 900 may be a PC, a tablet device, a personal digital assistant, a smart phone, or other device capable of executing the above instructions. Here, the electronic device 900 is not necessarily a single electronic device, but may also be any device or circuit capable of executing the above instructions (or instruction sets) individually or in combination. The electronic device 900 may also be part of an integrated control system or a system manager, or may be configured as a portable electronic device interconnected with a local or remote (e.g., via wireless transmission) interface.

[0145] In the electronic device 900, the processor 902 may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller or a microprocessor. As an example and not limitation, the processor may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0146] The processor 902 may execute instructions or codes stored in the memory 901, wherein the memory 901 may also store data. Instructions and data may also be sent and received over a network via a network interface device, wherein the network interface device may employ any known transmission protocol.

[0147] The memory 901 may be integrated with the processor 902, for example, by placing RAM or flash memory within an integrated circuit microprocessor or the like. In addition, the memory 901 may include a separate device, such as an external disk drive, a storage array, or any other storage device that can be used by a database system. The memory 901 and the processor 902 may be operatively coupled, or may communicate with each other, such as through an I / O port, a network connection, etc., so that the processor 902 can read files stored in the memory.

[0148] In addition, the electronic device 900 may further include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.) All components of the electronic device 900 may be connected to each other via a bus and / or a network.

[0149] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium may also be provided, and when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to execute the above-mentioned method for constructing a simulation model. Examples of computer-readable storage media here include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disk storage, hard disk drive (HDD), solid state drive (SSD), card storage (such as, multimedia card, secure digital (SD) card or extreme digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk and any other device, any other device is configured to store computer programs and any associated data, data files and data structures in a non-transitory manner and provide the computer programs and any associated data, data files and data structures to a processor or computer so that the processor or computer can execute the computer program. The computer program in the above-mentioned computer-readable storage medium can be run in an environment deployed in a computer device such as a client, a host, an agent device, a server, etc. In addition, in one example, the computer program and any associated data, data files and data structures are distributed on a networked computer system, so that the computer program and any associated data, data files and data structures are stored, accessed and executed in a distributed manner by one or more processors or computers.

[0150] According to the simulation model construction method and simulation model construction device disclosed in the present invention, a simulation model can be obtained based on the process operation log and process business information, that is, the process operation log and process business information can be effectively combined to automatically generate a simulation model. This strengthens the attention paid to the changes in the process and data during the actual operation of the project, and improves the accuracy of the constructed simulation model.

[0151] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0152] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for constructing a simulation model, characterized in that: include: Obtain process operation logs and process business information; Generate a process model G_3 based on the process operation log and the process business information; Using the process model G_3 to filter the process operation log, obtaining process data; Based on the process data, obtaining additional relationships; Based on the process model G_3 and the additional relationship, generating an original simulation model; Using the process data to adjust the simulation parameters of the original simulation model to obtain a target simulation model; The process operation log includes operation logs of multiple cases, and each case includes multiple actions; The process model G_3 is generated based on the process operation log and the process business information, including: Based on the multiple actions included in each of the multiple cases, generate a connection relationship graph G_1 between the multiple actions; Based on the process business information, generate a business process diagram G_0; Generate a business process expansion graph G_0' according to the overlapped part between the business process graph G_0 and the connection relationship graph G_1 between the multiple actions; Generate the process model G_3 according to the connection relationship graph G_1 between the multiple actions and the business process expansion graph G_0'; Among them, the additional relationship is the running order between the complete running cases expanded in the expanded case set and the original complete running cases contained in the expanded case set, the expanded case set is the expanded case set obtained by expanding the complete running case set, the complete running case set is the complete running case set obtained by classifying multiple complete running cases, and the multiple complete running cases are the cases among the multiple cases that are completely run in the process model G_3.

2. The construction method according to claim 1, characterized in that: The process model G_3 is generated according to the connection relationship graph G_1 between the multiple actions and the business process expansion graph G_0', including: Calculate the difference between the connection relationship graph G_1 between the multiple actions and the business process expansion graph G_0' to obtain the business process supplement graph G_2; Based on the business process supplementary graph G_2, generate a business missing process supplementary graph G_2'; The business process expansion graph G_0' and the business missing process supplement graph G_2' are superimposed to obtain the process model G_3.

3. The construction method according to claim 2, characterized in that: The business process complement graph G_2 includes a plurality of nodes, and a plurality of edges are formed between the plurality of nodes; The generating of the business missing process supplementary graph G_2' based on the business process supplementary graph G_2 includes: For each node of the plurality of nodes, determining a first number of the cases that passed through the node and a second number of the cases that did not pass through the node; For each of the plurality of edges, determining a third number of the cases that pass through the edge and a fourth number of the cases that do not pass through the edge; Based on the first number and the second number, determining whether the node is an additional supplementary node; Based on the third number and the fourth number, determining whether the edge is an additional supplementary edge; The service missing process supplement graph G_2' is generated by using the additional supplementary nodes among the multiple nodes and the additional supplementary edges among the multiple edges.

4. The construction method according to claim 3, characterized in that: The determining, based on the first number and the second number, whether the node is an additional supplementary node includes: calculating a first sum result between the first number and the second number; calculating a first ratio between the first number and the first sum result; When the first ratio is greater than a preset first threshold, the node is determined to be the additional supplementary node.

5. The construction method according to claim 3, characterized in that: The determining, based on the third number and the fourth number, whether the edge is an additional supplementary edge includes: If one of the two nodes corresponding to the edge belongs to the additional supplementary node, and the other node is included in the business process expansion graph G_0', then a second sum result between the third number and the fourth number is calculated; calculating a second ratio between the third quantity and the second addition result; When the second ratio is greater than a preset second threshold, the edge is determined to be the additional supplementary edge.

6. The construction method according to claim 1, characterized in that: The process model G_3 is used to filter the process operation log to obtain process data, including: The cases that are completely run in the process model G_3 are selected from the multiple cases as the process data.

7. The construction method according to claim 6, characterized in that: The acquiring of additional relationships based on the process data includes: Classify multiple complete running cases to obtain multiple complete running case sets; For each of the multiple completely run cases, obtain a case run interval corresponding to the complete run case set to which the completely run case belongs, wherein the left endpoint of the case run interval is the minimum time corresponding to the completely run case in the complete run case set, and the right endpoint of the case run interval is the maximum time corresponding to the completely run case in the complete run case set; Expanding the multiple complete running case sets to obtain at least one expanded case set, wherein, for each complete running case set, adding complete running cases whose corresponding running times in other complete running case sets are included in the case running interval corresponding to the complete running case set to the complete running case set to obtain an expanded case set corresponding to the complete running case set; The running order between the expanded complete running cases in each expanded case set and the original complete running cases included in the expanded case set is found as the additional relationship.

8. The construction method according to claim 6, characterized in that: The using the process data to adjust the simulation parameters of the original simulation model to obtain the target simulation model includes: Building a simulator corresponding to the original simulation model; The simulation parameters of the original simulation model are adjusted by using the complete running case and the simulator in an iterative manner until the iteration is terminated: The simulation results corresponding to this iteration are obtained through the following operations: Selecting multiple simulation parameters whose corresponding simulation results have the highest matching degree with the real results from the simulation parameter group obtained in the previous iteration; Performing crossover mutation on the multiple simulation parameters to obtain crossover mutation simulation parameters; Based on the complete running case, using the simulator to perform simulation verification on the crossover-mutation simulation parameters to obtain crossover-mutation simulation results corresponding to the crossover-mutation simulation parameters; When the iteration is terminated, the simulation parameters whose corresponding simulation results in previous iterations are most consistent with the actual results are selected as the simulation parameters of the target simulation model.

9. The construction method according to claim 8, characterized in that: The method further comprises: When the preset conditions are met, the iteration is terminated; The preset condition includes one of the following conditions: The number of iterations reaches the preset number of iterations; and At the end of this iteration, there are cross-mutation simulation parameters whose corresponding cross-mutation simulation results and actual results have a difference less than a preset difference threshold value.

10. The construction method according to claim 9, characterized in that: The difference between the crossover mutation simulation result and the real result is expressed by the following formula: in, is the case of the ith complete run, is the completion time of the i-th complete run case on the simulator, is the actual running time of the i-th complete running case.

11. A device for constructing a simulation model, characterized in that: include: An acquisition module, configured to acquire process operation logs and process business information; A generation module, configured to generate a process model G_3 based on the process operation log and the process business information; A screening module is configured to screen the process operation log using the process model G_3 to obtain process data; The acquisition module is configured to acquire additional relations based on the process data; The generating module is configured to generate an original simulation model based on the process model G_3 and the additional relationship; An adjustment module is configured to adjust the simulation parameters of the original simulation model using the process data to obtain a target simulation model; The process operation log includes operation logs of multiple cases, and each case includes multiple actions; The generation module is configured to: Based on the multiple actions included in each of the multiple cases, generate a connection relationship graph G_1 between the multiple actions; Based on the process business information, generate a business process diagram G_0; Generate a business process expansion graph G_0' according to the overlapped part between the business process graph G_0 and the connection relationship graph G_1 between the multiple actions; Generate the process model G_3 according to the connection relationship graph G_1 between the multiple actions and the business process expansion graph G_0'; Among them, the additional relationship is the running order between the complete running cases expanded in the expanded case set and the original complete running cases contained in the expanded case set, the expanded case set is the expanded case set obtained by expanding the complete running case set, the complete running case set is the complete running case set obtained by classifying multiple complete running cases, and the multiple complete running cases are the cases among the multiple cases that are completely run in the process model G_3.

12. The construction device according to claim 11, characterized in that The generation module is configured to: Calculate the difference between the connection relationship graph G_1 between the multiple actions and the business process expansion graph G_0' to obtain the business process supplement graph G_2; Based on the business process supplementary graph G_2, generate a business missing process supplementary graph G_2'; The business process expansion graph G_0' and the business missing process supplement graph G_2' are superimposed to obtain the process model G_3.

13. The construction device according to claim 12, characterized in that The business process complement graph G_2 includes a plurality of nodes, and a plurality of edges are formed between the plurality of nodes; The generation module is configured to: For each node of the plurality of nodes, determining a first number of the cases that passed through the node and a second number of the cases that did not pass through the node; For each of the plurality of edges, determining a third number of the cases that pass through the edge and a fourth number of the cases that do not pass through the edge; Based on the first number and the second number, determining whether the node is an additional supplementary node; Based on the third number and the fourth number, determining whether the edge is an additional supplementary edge; The service missing process supplement graph G_2' is generated by using the additional supplementary nodes among the multiple nodes and the additional supplementary edges among the multiple edges.

14. The construction device according to claim 13, characterized in that The generation module is configured to: calculating a first sum result between the first number and the second number; calculating a first ratio between the first number and the first sum result; When the first ratio is greater than a preset first threshold, the node is determined to be the additional supplementary node.

15. The construction device according to claim 13, characterized in that The generation module is configured to: If one of the two nodes corresponding to the edge belongs to the additional supplementary node, and the other node is included in the business process expansion graph G_0', then a second sum result between the third number and the fourth number is calculated; calculating a second ratio between the third quantity and the second addition result; When the second ratio is greater than a preset second threshold, the edge is determined to be the additional supplementary edge.

16. The construction device according to claim 11, characterized in that The screening module is configured to: The cases that are completely run in the process model G_3 are selected from the multiple cases as the process data.

17. The construction device according to claim 16, characterized in that The acquisition module is configured as follows: Classify multiple complete running cases to obtain multiple complete running case sets; For each of the multiple completely run cases, obtain a case run interval corresponding to the complete run case set to which the completely run case belongs, wherein the left endpoint of the case run interval is the minimum time corresponding to the completely run case in the complete run case set, and the right endpoint of the case run interval is the maximum time corresponding to the completely run case in the complete run case set; Expanding the multiple complete running case sets to obtain at least one expanded case set, wherein, for each complete running case set, adding complete running cases whose corresponding running times in other complete running case sets are included in the case running interval corresponding to the complete running case set to the complete running case set to obtain an expanded case set corresponding to the complete running case set; The running order between the expanded complete running cases in each expanded case set and the original complete running cases included in the expanded case set is found as the additional relationship.

18. The construction device according to claim 16, characterized in that The adjustment module is configured to: Building a simulator corresponding to the original simulation model; The simulation parameters of the original simulation model are adjusted by using the complete running case and the simulator in an iterative manner until the iteration is terminated: The simulation results corresponding to this iteration are obtained through the following operations: Selecting multiple simulation parameters whose corresponding simulation results have the highest matching degree with the real results from the simulation parameter group obtained in the previous iteration; Performing crossover mutation on the multiple simulation parameters to obtain crossover mutation simulation parameters; Based on the complete running case, using the simulator to perform simulation verification on the crossover-mutation simulation parameters to obtain crossover-mutation simulation results corresponding to the crossover-mutation simulation parameters; When the iteration is terminated, the simulation parameters whose corresponding simulation results in previous iterations are most consistent with the actual results are selected as the simulation parameters of the target simulation model.

19. The construction device according to claim 18, characterized in that The construction device also includes: A determination module is configured to determine that the iteration is terminated when a preset condition is met; The preset condition includes one of the following conditions: The number of iterations reaches the preset number of iterations; and At the end of this iteration, there are cross-mutation simulation parameters whose corresponding cross-mutation simulation results and actual results have a difference less than a preset difference threshold value.

20. The construction device according to claim 19, characterized in that The difference between the crossover mutation simulation result and the real result is expressed by the following formula: in, is the case of the ith complete run, is the completion time of the i-th complete run case on the simulator, is the actual running time of the i-th complete running case.

21. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for constructing a simulation model as described in any one of claims 1 to 10.

22. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for constructing a simulation model as claimed in any one of claims 1 to 10.

Images