Layout graph extraction method and device

Abstract

The invention provides a layout graph extraction method and device, and relates to the technical field of integrated circuits. When the method is executed, first layout data are obtained firstly, the first layout data comprise at least one layout graph, then at least one layout graph is selected from the first layout data to serve as an extracted layout graph sample, the layout graph sample is one layer or multiple layers, and the layout graph sample is selected from the first layout data to serve as the extracted layout graph sample. The method comprises the steps that a layout graph sample is obtained, then model parameters of a graph extraction model are determined according to the layout graph sample so as to construct the graph extraction model, finally, layout graphs in second layout data are extracted through the graph extraction model, and the second layout data comprise at least one layout graph. According to the technical scheme, the layout graph in the layout data is used as the extracted layout graph sample to construct the graph extraction model, and the graph extraction model is used for extracting the layout graph in the layout data, so that the accuracy of layout graph extraction can be improved.

Description

Technical Field

[0001] The present application relates to the field of integrated circuit technology, and in particular to a layout graphic extraction method and device. Background Art

[0002] There are some limitations in layout similarity comparison, such as the adverse effects of the filling pattern Dummy (i.e., layout pattern) in the integrated circuit, so it is necessary to extract and delete Dummy before layout similarity comparison to ensure the accuracy of the effective circuit connection relationship. In the prior art, based on the characteristics of Dummy, that is, most of the Dummy has a shorter length and smaller area than ordinary metal wires in appearance, Dummy is extracted, but there may be real metal wires with smaller area or length, or even shorter than Dummy, which will lead to inaccurate Dummy extraction.

[0003] In summary, how to improve the accuracy of layout graphic extraction is a problem that technical personnel in this field need to solve urgently. Summary of the invention

[0004] In view of this, the present application provides a layout graphic extraction method and device, aiming to improve the accuracy of layout graphic extraction.

[0005] In a first aspect, the present application provides a layout graphic extraction method, comprising: Acquire first layout data, wherein the first layout data includes at least one layout graphic; Selecting at least one layout graphic from the first layout data as an extracted layout graphic sample, wherein the layout graphic sample is one layer or multiple layers; Determining model parameters of a graphic extraction model according to the layout graphic sample to construct the graphic extraction model; Acquire second layout data; the second layout data includes at least one layout graphic; The layout graphics in the second layout data are extracted using the graphics extraction model.

[0006] Optionally, the model parameters include model name, model type and model features; The model type includes precise type or loose type; The model features include the layers of the layout graphics, the number of the layout graphics, and the size of the layout graphics; the size of the layout graphics is a fixed size or a range interval size.

[0007] Optionally, the extracting the layout graphics in the second layout data by using the graphics extraction model includes: When the model type of the graphic extraction model is the precise type, the graphic extraction model is used to extract the layout graphics in the second layout data, and the extracted layout graphics completely meet the definition of the graphic extraction model; When the model type of the graphic extraction model is the loose type, the graphic extraction model is used to extract the layout graphics in the second layout data, and the extracted layout graphics partially meet the definition of the graphic extraction model.

[0008] Optionally, the model parameters also include an adjustment ratio; When the adjustment ratio is greater than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is greater than the extraction range of the graphic extraction model not constructed according to the adjustment ratio; When the adjustment ratio is less than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is smaller than the extraction range of the graphic extraction model not constructed according to the adjustment ratio.

[0009] Optionally, the extracting the layout graphics in the second layout data by using the graphics extraction model includes: Setting the adjustment ratio for the graphic extraction model; When the adjustment ratio is greater than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is greater than the extraction range of the graphic extraction model without setting the adjustment ratio; When the adjustment ratio is less than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is smaller than the extraction range of the graphic extraction model without setting the adjustment ratio; The layout graphics in the second layout data are extracted according to the graphics extraction model after setting the adjusted ratio.

[0010] Optionally, before extracting the layout graphics in the second layout data using the graphics extraction model, the method further includes: Grouping the layout graphics in the second layout data to obtain at least one layout graphic group; The extracting the layout graphics in the second layout data by using the graphics extraction model includes: Matching the graphic extraction model with the layout graphic group to obtain a layout graphic group matching the graphic extraction model; A layout graphic group matching the graphic extraction model is extracted.

[0011] Optionally, grouping the layout graphics in the second layout data to obtain at least one layout graphic group includes: The interconnected layout graphics in the second layout data are grouped into one group to obtain at least one layout graphic group.

[0012] Optionally, after extracting the layout graphics in the second layout data using the graphics extraction model, the method further includes: The extracted layout graphics are deleted from the second layout data to obtain processed second layout data.

[0013] Optionally, after deleting the extracted layout graphic from the second layout data to obtain the processed second layout data, the method further includes: Selecting at least one layout graphic from the processed second layout data; The graphic extraction model is modified according to the layout graphics selected from the processed second layout data.

[0014] In a second aspect, the present application provides a layout pattern extraction device, comprising: A first acquisition module, used to acquire first layout data, wherein the first layout data includes at least one layout graphic; A first selection module is used to select at least one layout graphic from the first layout data as an extracted layout graphic sample, wherein the layout graphic sample is one layer or multiple layers; A determination module, used to determine model parameters of a graphic extraction model according to the layout graphic sample, so as to construct the graphic extraction model; A second acquisition module is used to acquire second layout data; the second layout data includes at least one layout graphic; An extraction module is used to extract the layout graphics in the second layout data using the graphics extraction model.

[0015] Optionally, the model parameters include model name, model type and model features; The model type includes precise type or loose type; The model features include the layers of the layout graphics, the number of the layout graphics, and the size of the layout graphics; the size of the layout graphics is a fixed size or a range interval size.

[0016] Optionally, the extraction module includes: A second extraction unit, configured to extract layout graphics from the second layout data using the graphics extraction model when the model type of the graphics extraction model is the precise type, and the extracted layout graphics fully meet the definition of the graphics extraction model; The third extraction unit is used to extract the layout graphics in the second layout data using the graphics extraction model when the model type of the graphics extraction model is the loose type, and the extracted layout graphics partially meet the definition of the graphics extraction model.

[0017] Optionally, the model parameters also include an adjustment ratio; When the adjustment ratio is greater than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is greater than the extraction range of the graphic extraction model not constructed according to the adjustment ratio; When the adjustment ratio is less than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is smaller than the extraction range of the graphic extraction model not constructed according to the adjustment ratio.

[0018] Optionally, the extraction module includes: A setting unit, configured to set the adjustment ratio for the graphic extraction model; When the adjustment ratio is greater than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is greater than the extraction range of the graphic extraction model without setting the adjustment ratio; When the adjustment ratio is less than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is smaller than the extraction range of the graphic extraction model without setting the adjustment ratio; The fourth extraction unit is used to extract the layout graphics in the second layout data according to the graphics extraction model after setting the adjusted ratio.

[0019] Optionally, the device further comprises: A grouping module, used for grouping the layout graphics in the second layout data to obtain at least one layout graphic group; The extraction module comprises: A matching unit, used for matching the graphic extraction model with the layout graphic group to obtain a layout graphic group matching the graphic extraction model; The first extraction unit is used to extract a layout graphic group matching the graphic extraction model.

[0020] Optionally, the grouping module includes: A grouping unit is used to group interconnected layout graphics in the second layout data into one group to obtain at least one layout graphic group.

[0021] Optionally, the device further comprises: The deletion module is used to delete the extracted layout graphics from the second layout data to obtain processed second layout data.

[0022] Optionally, the device further comprises: A second selection module, used for selecting at least one layout graphic from the processed second layout data; A modification module is used to modify the graphic extraction model according to the layout graphics selected from the processed second layout data.

[0023] The present application provides a layout graphic extraction method. When executing the method, first obtain the first layout data, wherein the first layout data includes at least one layout graphic, then select at least one layout graphic in the first layout data as an extracted layout graphic sample, wherein the layout graphic sample is one or more layers, and then determine the model parameters of the graphic extraction model according to the layout graphic sample to construct a graphic extraction model, and finally, use the graphic extraction model to extract the layout graphic in the second layout data, wherein the second layout data includes at least one layout graphic. The technical solution of the present application uses the layout graphic in the layout data as the extracted layout graphic sample to construct a graphic extraction model, and uses the graphic extraction model to extract the layout graphic in the layout data, which can improve the accuracy of layout graphic extraction. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A flowchart of a layout graphic extraction method provided in an embodiment of the present application; Figure 2 A schematic diagram of layout data provided in an embodiment of the present application; Figure 3 A schematic diagram of selecting a layout graphic from layout data provided in an embodiment of the present application; Figure 4 A schematic diagram of another method of selecting a graphic sample from layout data provided in an embodiment of the present application; Figure 5 Another schematic diagram of selecting a graphic sample from layout data provided in an embodiment of the present application; Figure 6 A schematic diagram of grouping graphics in layout data provided in an embodiment of the present application; Figure 7 A schematic diagram of extracting groups from layout data using a graphic extraction model provided in an embodiment of the present application; Figure 8A schematic diagram of deleting a group in layout data extracted from the layout data provided in an embodiment of the present application; Fig. 9 Another schematic diagram of grouping graphics in layout data provided in an embodiment of the present application; Fig.10 A schematic diagram of extracting layout graphics from layout data using an accurate graphics extraction model constructed based on a Dummy sample d provided in an embodiment of the present application; Fig.11 A schematic diagram of extracting layout graphics from layout data using a loose graphics extraction model constructed based on a Dummy sample d provided in an embodiment of the present application; Fig.12 A schematic diagram of extracting layout graphics from layout data using a graphics extraction model with an adjustment ratio of 0 provided in an embodiment of the present application; Fig.13 A schematic diagram of extracting layout graphics from layout data using a graphics extraction model with an adjustment ratio of 5 provided in an embodiment of the present application; Fig.14 A schematic diagram of extracting layout graphics from layout data using a graphics extraction model with an adjustment ratio of 10 provided in an embodiment of the present application; Fig.15 A schematic diagram of a legacy layout graphic in the layout data provided in an embodiment of the present application; Fig.16 A schematic diagram of the structure of a layout graphic extraction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. The present application provides a layout graphic extraction method and device for use in the field of integrated circuit technology. The above is only an example and does not limit the application field of the method and device provided in the present application.

[0027] There are some limitations in layout similarity comparison, such as the adverse effects of Dummy filling patterns in integrated circuits, so Dummy needs to be extracted and deleted before layout similarity comparison to ensure the accuracy of the comparison of effective circuit connection relationships. In the prior art, Dummy is extracted based on the characteristics of Dummy, that is, most Dummy has a shorter length and smaller area than ordinary metal wires in appearance. However, there may be real metal wires with smaller areas or lengths, or even shorter than Dummy, which will lead to inaccurate Dummy extraction.

[0028] After research, the inventor proposed the technical solution of the present application. First, the first layout data is obtained, wherein the first layout data includes at least one layout graphic. Then, at least one layout graphic is selected from the first layout data as an extracted layout graphic sample, wherein the layout graphic sample is one or more layers. Then, the model parameters of the graphic extraction model are determined according to the layout graphic sample to construct a graphic extraction model. Finally, the graphic extraction model is used to extract the layout graphics in the second layout data. By using the layout graphics in the layout data as the extracted layout graphic samples to construct the graphic extraction model, and using the graphic extraction model to extract the layout graphics in the layout data, the accuracy of the layout graphic extraction can be improved.

[0029] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. It should be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0030] See also Figure 1 , Figure 1 A flowchart of a layout graphic extraction method provided in an embodiment of the present application. In this embodiment, extracting a Dummy graphic from layout data is used as an example for explanation, specifically including: S101: Acquire first layout data.

[0031] Acquire first layout data, wherein the first layout data is used to select at least one layout pattern as an extracted layout pattern sample, such as Figure 2 As shown, Figure 2 A schematic diagram of a layout data provided in an embodiment of the present application, the layout data includes: M1 graphics, M2 graphics and through-hole graphics V1, wherein M1 graphics, M2 graphics and V1 graphics represent graphics of different layers. In this embodiment, Figure 2 The layout data in is used as the first layout data.

[0032] S102: Select at least one layout graphic from the first layout data as an extracted layout graphic sample.

[0033] In the layout data, you can select a Dummy graphic as the extracted Dummy sample, such as Figure 3 As shown, Figure 3A schematic diagram of selecting a layout graphic in layout data is provided in an embodiment of the present application, wherein a Dummy graphic in the layout data is selected and used as the extracted Dummy sample a and Dummy sample b.

[0034] S103: Determine model parameters of a graphic extraction model according to the layout graphic sample to construct the graphic extraction model.

[0035] Determine the model parameters of the graphic extraction model according to the layout graphic sample to construct the graphic extraction model. Among them, the model parameters include model name, model type, model features, etc. Among them, the model feature refers to the definition of the constituent graphics of the layout graphic sample. Multiple features can be defined for the graphics on different layout layers. Each feature can be limited by multiple parameters, such as the layers of each graphic, the number of each graphic, and the corresponding graphic size. The graphic size includes but is not limited to: one or more of the long side length, short side length, the area ratio of the present and the short side ratio. The long side length is the long side length of the graphic circumscribed box, the short side length is the short side length of the graphic circumscribed box, the area ratio of the present and the short side is the ratio of the area of ​​the graphic itself to the area of ​​its circumscribed box, and the long and short side ratio is the ratio of the long side to the short side of the rectangular circumscribed box of the graphic. Model types include precise or loose. The graphic extraction model is a text description containing the model definition, which can be manually written according to the grammatical rules of the model or automatically generated using an algorithm.

[0036] For example, taking the Dummy sample a in step S102 as an example, the model 1 of the graphic extraction model constructed according to the Dummy sample a is defined as follows: DUMMY M1_loose TYPE loose M1 long="1.60 1.60" short="0.80 0.80" sbbr="1.00 1.00" END DUMMY Taking the Dummy sample b in step S102 as an example, the model 2 of the graphic extraction model constructed according to the Dummy sample b is defined as follows: DUMMY M1M2_loose TYPE loose M1 long="4.00 4.00" short="0.80 0.80" sbbr="1.00 1.00" V1 sbbr="1.00 1.00" aspect="1.00 1.00" M2 long="3.5 3.5" short="0.8 0.8" sbbr="1.00 1.00" END DUMMY like Figure 4 As shown, Figure 4 A schematic diagram of selecting a graphic sample from layout data provided in an embodiment of the present application is provided. Figure 4 In the example, only a part of the sample n is selected. Since the sample n is different only in the size of the graphics, the model 3 of the graphics extraction model constructed based on the Dummy sample n is defined as follows: DUMMY M1_loose TYPE loose M1 long="1.60 2.6" short="0.80 1.00" sbbr="1.00 1.00" END DUMMY In the graphic extraction model constructed according to Dummy sample b, the graphic extraction model constructed according to Dummy sample a, and the image extraction model constructed according to Dummy sample n, the middle part between the keyword DUMMY and the keyword END DUMMY corresponds to a specific model. The model name of the graphic extraction model constructed according to Dummy sample a is M1_loose, the model name of the graphic extraction model constructed according to Dummy sample b is M1M2_loose, and the model name of the image extraction model constructed according to Dummy sample n is M1_loose. The keyword TYPE is used to define the model type. For example, TYPE loose indicates that the model type is loose. The model includes a description of the model features, that is, the definition of the constituent graphics of Dummy, wherein multiple features can be defined for graphics on different layers, and each feature can be defined using multiple parameters. For example, in M1 long="1.60 2.6" short="0.80 1.00" sbbr="1.00 1.00", M1 indicates that the feature description is for the graphics on the M1 layer, that is, the layer limitation of the graphics, long="1.60 2.6" short="0.80 1.00" sbbr="1.00 1.00" is the limitation of the graphics size, such as long="1.60 2.6" means that the length of the long side of the circumscribed box of the graphics on M1 must be greater than or equal to 1.60um and less than or equal to 2.6um, that is, the minimum value of long is the smallest value of the long sides of all M1 graphics in the layout graphics sample, and the maximum value is the largest value of the long sides of all M1 graphics in the layout graphics sample, that is, the features of each graphic in the layout graphics sample are merged to form a range as the limiting condition of the feature parameters, such as the extracted model n. When the features such as the length of the graphics are the same, the maximum and minimum values ​​of the extracted model parameters are the same, such as the extracted models 1 and 2. The following parameters can be used to limit the size of the graphic: long represents the length of the long side of the graphic's circumscribed box; short represents the length of the short side of the graphic's circumscribed box; sbbr represents the ratio of the area of ​​the graphic (lead or through hole) itself to the area of ​​its circumscribed box; aspect represents the ratio of the long side to the short side of the rectangular circumscribed box of the graphic (lead or through hole).

[0037] Dummy sample a only involves graphics on the M1 layer, so the graphics extraction model built based on Dummy sample a has only one restriction on the M1 graphics. Dummy sample b involves graphics on three layers, M1, V1, and M2, so the graphics extraction model built based on Dummy sample b contains restrictions on M1 graphics, V1 graphics, and M2 graphics, respectively.

[0038] Furthermore, in some embodiments, the model parameters may also include an adjustment ratio. Different adjustment ratios will result in different parameter ranges in the generated model definition. When the adjustment ratio is greater than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is greater than the extraction range of the graphic extraction model not constructed according to the adjustment ratio; when the adjustment ratio is less than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is smaller than the extraction range of the graphic extraction model not constructed according to the adjustment ratio.

[0039] For example, the model definition of the graphics extraction model when the adjustment scale is 0 is as follows: DUMMY M3_loose TYPE loose M3 long="2.4800 2.4800" short="0.8000 0.8000" sbbr="1.0000 1.0000" END DUMMY The model definition of the graphics extraction model when the adjustment scale is 5 is as follows: DUMMY M3_loose TYPE loose M3 long="2.3560 2.6040" short="0.7600 0.8400" sbbr="0.9500 1.0500" END DUMMY That is, when generating parameters, based on the original size range, the lower limit is reduced by 5% and the upper limit is increased by 5%, 2.3560=2.4800×(1-0.05), 2.6040=2.4800×(1+0.05). The model definition of the graphic extraction model when the adjustment ratio is 10 is as follows: DUMMY M3_loose TYPE loose M3 long="2.2320 2.7280" short="0.7200 0.8800" sbbr="0.9000 1.1000" END DUMMY Furthermore, the keyword TYPE is used to define the model type, which can include loose type and precise type. Figure 5 As shown, Figure 5Another schematic diagram for selecting graphic samples in layout data provided in an embodiment of the present application can construct a graphic extraction model with a precise or loose model type based on Dummy sample d, that is, a precise graphic extraction model constructed based on Dummy sample d or a loose graphic extraction model constructed based on Dummy sample d.

[0040] The model definition of the precise graph extraction model constructed based on the Dummy sample d is as follows: DUMMY M1M2_exact TYPE exact M1 long="1.60 1.60" short="0.80 0.80" sbbr="1.001 .00" M1 long="1.60 1.60" short="0.8 0.8" sbbr="1.00 1.00" V1 long="0.50 0.50" short="0.50 0.50" sbbr="1.00 1.00" aspect="1.001.00" V1 long="0.50 0.50" short="0.50 0.50" sbbr="1.00 1.00" aspect="1.001.00" M2 long="2.00 2.00" short="0.8 0.8" sbbr="1.00 1.00" END DUMMY Among them, TYPE exact indicates that the model type of the model is exact.

[0041] The model definition of the relaxed graph extraction model constructed based on the Dummy sample d is as follows: DUMMY M1M2_loose TYPE loose M1 long="1.60 1.60" short="0.80 0.80" sbbr="1.00 1.00" V1 long="0.50 0.50" short="0.50 0.50" sbbr="1.00 1.00" aspect="1.001.00" M2 long="2.00 2.00" short="0.8 0.8" sbbr="1.00 1.00" END DUMMY Among them, TYPE loose indicates that the model type of the model is loose.

[0042] Exact and loose are the types of models, each corresponding to a matching method. If TYPE exact is defined in the model, exact matching is used when extracting a dummy that matches the model; if TYPE loose is defined in the model, loose matching is used when extracting a dummy that matches the model.

[0043] For precise models, when performing dummy graphic matching, the layout graphics in the matching layout graphic group and the layout graphics in the model need to be matched one-to-one, with the number being neither too many nor too few, and the parameter size also meeting the model definition.

[0044] For loose models, when performing dummy graphics matching, the layout layers in the matching layout graphic group need to be matched one-to-one, but each layer of layout graphics in the matching layout graphic group at least includes the layout in the model, and the parameter size also needs to meet the model definition.

[0045] S104: Acquire second layout data.

[0046] The second layout data is obtained, where the second layout data is the layout data of the Dummy figure to be extracted. The second layout data and the aforementioned first layout data may be the same layout data or different layout data.

[0047] S105: Extracting the layout graphics in the second layout data using the graphics extraction model.

[0048] Before executing step S105, the graphics in the second layout data may be grouped to obtain at least one graphic group, such as Figure 6 As shown, Figure 6 A schematic diagram of grouping graphics in layout data provided in an embodiment of the present application, Figure 6 The layout data to be processed, i.e., the interconnected graphics in the second layout data, include several M1 graphics, M2 graphics, M3 graphics, through-hole graphics V1 and through-hole graphics V2, and the graphics to be processed, i.e., the graphics in the second layout data, are grouped into one group, thereby obtaining graphics group 1, graphics group 2, graphics group 3, graphics group 4, graphics group 5, graphics group 6, graphics group 7, graphics group 8, graphics group 9 and graphics group 10. The construction method of the layout connectivity relationship is: according to the layout connectivity rule, the graphics on different layers are appropriately grouped, and the graphics that are connected to each other form a group. Specifically, the M1 and M2 graphics are connected through the V1 graphics, and the M2 and M3 graphics are connected through the V2 graphics.

[0049] Figure 7A schematic diagram of extracting groups from layout data using a graphic extraction model provided in an embodiment of the present application, wherein c is a graphic extraction model, and the model definition of the graphic extraction model is as follows: DUMMY M1M2_loose TYPE loose M1 long="4.8 4.8" short="0.8 0.8" sbbr="1.00 1.00" V1 sbbr="0.80 0.80" M2 long="5.2 5.2" short="0.8 0.8" sbbr="1.00 1.00"" END DUMMY Taking the graphic extraction model as an example, TYPE loose is defined in the model, that is, the graphic extraction model is a loose graphic extraction model. The graphic extraction model c contains an M1 graphic, two M2 graphics and two V1 graphics. The graphic extraction model c will match the layout graphic group in the layout group that meets the model parameter restrictions of the graphic extraction model c. In the entire group, layout graphic group 1 and layout graphic group 7 match the graphic extraction model c. Therefore, the graphic extraction model c can match the publication graphic group 1 and the layout graphic group 7, and extract the matched layout graphic group. Here, a loose graphic extraction model is used for matching, so the graphic extraction model c is not completely one-to-one corresponding to the layout graphic group 1 and the layout graphic group 7. The model type will be explained separately below.

[0050] After matching the layout graphic groups in the layout data, the matched layout graphic groups in the layout data are deleted from the layout data to be processed to obtain processed layout data to be processed. Figure 8 A schematic diagram of a grouping of extracted layout data and deletion from the layout data provided in an embodiment of the present application, as described above, the graphic extraction model matches the publication graphic group 1 and the layout graphic group 7, deletes the matched layout graphic group 1 and the layout graphic group 7 from the layout data, and obtains the processed layout data.

[0051] Using the precise graph extraction model constructed according to the Dummy sample d in step S103, or the loose graph extraction model constructed according to the Dummy sample d, Fig. 9 The specific method of extracting the layout graphics from the layout data shown is as follows: like Fig. 9 As shown, Fig. 9 Another schematic diagram of grouping graphics in layout data provided by an embodiment of the present application is as follows: Fig. 9The graphics in the layout data shown are grouped, and the specific grouping method is as described above and will not be repeated here.

[0052] When the model type of the graphic extraction model is precise, the precise graphic extraction model is used to match the layout graphic group in the layout data. The layout graphics in the matching layout graphic group and the layout graphics in the model need to be matched one-to-one, with neither too many nor too few, and the parameter size also meets the model definition. Fig.10 As shown, Fig.10 A schematic diagram of extracting a layout pattern group from layout data using an accurate pattern extraction model constructed based on a Dummy sample d provided in an embodiment of the present application. Fig. 9 When the layout data shown is used to extract layout graphics, the layout graphics group that can be extracted needs to meet the following conditions: there are only two M1 graphics, there are only two V1 graphics, there is only one M2 graphics, and the aforementioned graphics all meet the corresponding limit values. The only layout group that meets such conditions is group e, that is, layout graphics group e can be extracted.

[0053] When the model type of the graphic extraction model is loose, the loose graphic extraction model is used to match the layout graphic group in the layout data, and each layer of layout graphics in the matched layout graphic group includes at least the layout graphics in the model. It should be specifically explained here that even if the loose graphic extraction model is used to match the layout data, the layers of each layer of graphics in the matched layout graphic group still need to be consistent with the layers of each layer of graphics in the model. For example, if there are only three layers of graphics, M1, M2, and V1, in the loose graphic extraction model, then the matched layout graphic group must also have and only have three layers of graphics, M1, M2, and V1, but there is no requirement for the number of M1, M2, and V1. Fig.11 As shown, Fig.11 A schematic diagram of extracting a layout graphic from layout data using a loose graphic extraction model constructed based on a Dummy sample d provided in an embodiment of the present application, using a loose graphic extraction model constructed based on a Dummy sample d to extract a layout graphic from layout data Fig. 9 The layout data shown in the figure is used to extract the layout graphics. The layout graphics group that can be extracted needs to meet the following conditions: at least one M1 graphic, at least one V1 graphic, at least one M2 graphic, and the aforementioned graphics all meet the corresponding limit values. The layout groups that meet such conditions are layout graphics group e, layout graphics group h, and layout graphics group i, that is, layout graphics group e, layout graphics group h, and layout graphics group i can be extracted.

[0054] In step S103, the pattern extraction model whose model parameters include the adjusted scale is used to extract the layout pattern in the layout data. Fig.12 , Fig.13 , Fig.14 As shown, Fig.12 A schematic diagram of extracting layout graphics from layout data using a graphics extraction model with an adjustment ratio of 0 provided in an embodiment of the present application; Fig.13 A schematic diagram of extracting layout graphics from layout data using a graphics extraction model with an adjustment ratio of 5 provided in an embodiment of the present application; Fig.14 A schematic diagram of the extraction of layout graphics in layout data using a graphic extraction model with an adjustment ratio of 10 provided in an embodiment of the present application. It can be seen that the extraction range of the layout graphics in the layout data by the graphic extraction model with an adjustment ratio of 5 is greater than the extraction range of the layout graphics in the layout data by the graphic extraction model with an adjustment ratio of 0, and the extraction range of the layout graphics in the layout data by the graphic extraction model with an adjustment ratio of 10 is greater than the extraction range of the layout graphics in the layout data by the graphic extraction model with an adjustment ratio of 5, that is, the larger the adjustment ratio, the larger the extraction range of the graphic extraction model.

[0055] In some embodiments, before using the graphic extraction model to extract the layout graphics in the layout data, an additional adjustment ratio can be set for the graphic extraction model. This adjustment ratio has the same effect as the adjustment ratio in the aforementioned model parameters, that is, when the adjustment ratio is greater than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is greater than the extraction range of the graphic extraction model without the adjustment ratio; when the adjustment ratio is less than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is less than the extraction range of the graphic extraction model without the adjustment ratio. This will not be repeated here. In addition, when the model parameters include the adjustment ratio, the adjustment ratio can also be additionally set for the graphic extraction model, and the adjustment effects are superimposed.

[0056] In the embodiment provided in the present application, firstly obtain the first layout data, wherein the first layout data includes at least one layout graphic, then select at least one layout graphic in the first layout data as an extracted layout graphic sample, wherein the layout graphic sample is one or more layers, and then determine the model parameters of the graphic extraction model according to the layout graphic sample to construct a graphic extraction model, and finally, use the graphic extraction model to extract the layout graphics in the second layout data. The technical solution of the present application uses the layout graphics in the layout data as the extracted layout graphic samples to construct a graphic extraction model, and uses the graphic extraction model to extract the layout graphics in the layout data, which can improve the accuracy of the layout graphic extraction. In some embodiments, after the layout graphics in the layout data are extracted and deleted using the graphic extraction model, there may be leftover layout graphics that need to be extracted and deleted in the processed layout data, such as Fig.15 As shown, Fig.15This is a schematic diagram of a legacy layout graphic in the layout data provided in an embodiment of the present application, where the layout graphic m is a legacy layout graphic that needs to be extracted and deleted. At this time, the layout graphic m can be used to modify the original graphic extraction model.

[0057] For example, the model definition of the original image extraction model is as follows: DUMMY M2_loose TYPE loose M2 long="1.00 1.33" short="0.09 0.11" sbbr="1.00 1.00" END DUMMY The model definition corresponding to the model feature of the layout graphic m is as follows: M2 long="1.50 1.50" short="0.20 0.20sbbr="1.00 1.00" There are two ways to modify the original graphic extraction model. One is to add the model definition corresponding to the model feature of the layout graphic m after the model definition of the original graphic extraction model. The model definition of the modified graphic extraction model is as follows: DUMMY M2_loose TYPE loose M2 long="1.00 1.33" short="0.09 0.11" sbbr="1.00 1.00" END DUMMY DUMMY M2_loose TYPE loose M2 long="1.50 1.50" short="0.20 0.20sbbr="1.00 1.00" END DUMMY Another way is to insert the model definition corresponding to the model feature of the layout graphic m into the model definition of the original graphic extraction model. The model definition of the modified graphic extraction model is as follows: DUMMY M2_loose TYPE loose M2 long="1.00 1.33" short="0.09 0.11" sbbr="1.00 1.00" M2 long="1.50 1.50" short="0.20 0.20sbbr="1.00 1.00" END DUMMY Another way is to merge the model definition corresponding to the model feature of the layout graphic m into the model definition of the original graphic extraction model, update the limited range of the size in the original model, and the model definition of the modified graphic extraction model is as follows: DUMMY M2_loose TYPE loose M2 long="1.00 1.50" short="0.09 0.20" sbbr="1.00 1.00" END DUMMY The above are some specific implementations of the layout pattern extraction method provided in the embodiments of the present application. Based on this, the present application also provides a corresponding device. The device provided in the embodiments of the present application will be introduced from the perspective of functional modularization.

[0058] like Fig.16 As shown, Fig.16 A schematic diagram of the structure of a layout pattern extraction device provided in an embodiment of the present application, the layout pattern extraction device 1600 includes: A first acquisition module 1610 is used to acquire first layout data, where the first layout data includes at least one layout graphic; A first selection module 1620 is used to select at least one layout graphic from the first layout data as an extracted layout graphic sample, wherein the layout graphic sample is one layer or multiple layers; A determination module 1630, configured to determine model parameters of a graphic extraction model according to the layout graphic sample, so as to construct the graphic extraction model; The second acquisition module 1640 is used to acquire second layout data; The extraction module 1650 is used to extract the layout graphics in the second layout data using the graphics extraction model.

[0059] Optionally, the model parameters include model name, model type and model features; The model type includes precise type or loose type; The model features include the layers of the layout graphics, the number of the layout graphics, and the size of the layout graphics; the size of the layout graphics is a fixed size or a range interval size.

[0060] Optionally, the layout graphic extraction device 1600 further includes: A grouping module, used for grouping the layout graphics in the second layout data to obtain at least one layout graphic group; The extraction module 1650 includes: A matching unit, used for matching the graphic extraction model with the layout graphic group to obtain a layout graphic group matching the graphic extraction model; The first extraction unit is used to extract the layout graphic group matching the graphic extraction model.

[0061] Optionally, the grouping module includes: A grouping unit is used to group interconnected layout graphics in the second layout data into one group to obtain at least one layout graphic group.

[0062] Optionally, the extraction module 1650 includes: A second extraction unit, configured to extract layout graphics from the second layout data using the graphics extraction model when the model type of the graphics extraction model is the precise type, and the extracted layout graphics fully meet the definition of the graphics extraction model; The third extraction unit is used to extract the layout graphics in the second layout data using the graphics extraction model when the model type of the graphics extraction model is the loose type, and the extracted layout graphics partially meet the definition of the graphics extraction model.

[0063] Optionally, the model parameters include adjustment ratios; When the adjustment ratio is greater than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is greater than the extraction range of the graphic extraction model not constructed according to the adjustment ratio; When the adjustment ratio is less than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is smaller than the extraction range of the graphic extraction model not constructed according to the adjustment ratio.

[0064] Optionally, the extraction module 1650 includes: A setting unit, configured to set the adjustment ratio for the graphic extraction model; When the adjustment ratio is greater than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is greater than the extraction range of the graphic extraction model without setting the adjustment ratio; When the adjustment ratio is less than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is smaller than the extraction range of the graphic extraction model without setting the adjustment ratio; The fourth extraction unit is used to extract the layout graphics in the second layout data according to the graphics extraction model after setting the adjusted ratio.

[0065] Optionally, the layout graphic extraction device 1600 further includes: The deletion module is used to delete the extracted layout graphics from the second layout data to obtain processed second layout data.

[0066] Optionally, the layout graphic extraction device 1600 further includes: A second selection module, used for selecting at least one layout graphic from the processed second layout data; A modification module is used to modify the graphic extraction model according to the layout graphics selected from the processed second layout data.

[0067] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.

[0068] The device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes the layout graphic extraction method described in any embodiment of the present application.

[0069] The computer storage medium stores codes, and when the codes are executed, the device executing the codes implements the layout graphic extraction method described in any embodiment of the present application.

[0070] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0071] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0072] It should also be noted that the various embodiments in this specification are described in a progressive manner, and the same and similar parts between the various embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the equipment and device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The device embodiments described above are merely schematic, in which the units described as separate components may or may not be physically separated, and the components prompted as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0073] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A layout graphics extraction method, characterized in that: include: Acquire first layout data, wherein the first layout data includes at least one layout graphic; Selecting at least one layout graphic from the first layout data as an extracted layout graphic sample, wherein the layout graphic sample is one layer or multiple layers; Determining model parameters of a graphic extraction model according to the layout graphic sample to construct the graphic extraction model; Acquire second layout data; the second layout data includes at least one layout graphic; The layout graphics in the second layout data are extracted using the graphics extraction model.

2. The method according to claim 1, characterized in that The model parameters include model name, model type and model features; The model type includes precise type or loose type; The model features include the layers of the layout graphics, the number of the layout graphics, and the size of the layout graphics; the size of the layout graphics is a fixed size or a range interval size.

3. The method according to claim 2, characterized in that The extracting the layout graphics in the second layout data by using the graphics extraction model includes: When the model type of the graphic extraction model is the precise type, the graphic extraction model is used to extract the layout graphics in the second layout data, and the extracted layout graphics completely meet the definition of the graphic extraction model; When the model type of the graphic extraction model is the loose type, the graphic extraction model is used to extract the layout graphics in the second layout data, and the extracted layout graphics partially meet the definition of the graphic extraction model.

4. The method according to claim 2, characterized in that: The model parameters also include adjustment ratios; When the adjustment ratio is greater than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is greater than the extraction range of the graphic extraction model not constructed according to the adjustment ratio; When the adjustment ratio is less than 0, the extraction range of the graphic extraction model constructed according to the adjustment ratio is smaller than the extraction range of the graphic extraction model not constructed according to the adjustment ratio.

5. The method according to claim 4, characterized in that The extracting the layout graphics in the second layout data by using the graphics extraction model includes: Setting the adjustment ratio for the graphic extraction model; When the adjustment ratio is greater than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is greater than the extraction range of the graphic extraction model without setting the adjustment ratio; When the adjustment ratio is less than 0, the extraction range of the graphic extraction model after the adjustment ratio is set is smaller than the extraction range of the graphic extraction model without setting the adjustment ratio; The layout graphics in the second layout data are extracted according to the graphics extraction model after setting the adjusted ratio.

6. The method according to any one of claims 1 to 5, characterized in that: Before extracting the layout graphics in the second layout data using the graphics extraction model, the method further includes: Grouping the layout graphics in the second layout data to obtain at least one layout graphic group; The extracting the layout graphics in the second layout data by using the graphics extraction model includes: Matching the graphic extraction model with the layout graphic group to obtain a layout graphic group matching the graphic extraction model; A layout graphic group matching the graphic extraction model is extracted.

7. The method according to claim 6, characterized in that The step of grouping the layout graphics in the second layout data to obtain at least one layout graphic group includes: The interconnected layout graphics in the second layout data are grouped into one group to obtain at least one layout graphic group.

8. The method according to claim 7, characterized in that After extracting the layout graphics in the second layout data using the graphics extraction model, the method further includes: The extracted layout graphics are deleted from the second layout data to obtain processed second layout data.

9. The method according to claim 8, characterized in that After deleting the extracted layout graphics from the second layout data to obtain the processed second layout data, the method further includes: Selecting at least one layout graphic from the processed second layout data; The graphic extraction model is modified according to the layout graphics selected from the processed second layout data.

10. A layout pattern extraction device, characterized in that: include: A first acquisition module, used to acquire first layout data, wherein the first layout data includes at least one layout graphic; A first selection module is used to select at least one layout graphic from the first layout data as an extracted layout graphic sample, wherein the layout graphic sample is one layer or multiple layers; A determination module, used to determine model parameters of a graphic extraction model according to the layout graphic sample, so as to construct the graphic extraction model; A second acquisition module is used to acquire second layout data; the second layout data includes at least one layout graphic; An extraction module is used to extract the layout graphics in the second layout data using the graphics extraction model.

Images