Layout processing method, device and medium

Abstract

The embodiment of the invention provides a layout processing method, layout processing equipment and a medium. The method comprises the following steps: determining a plurality of reference splitting strategies corresponding to a plurality of reference layouts respectively; the splitting quality obtained by splitting each reference layout according to the corresponding reference splitting strategy meets a preset condition. The method also includes determining corresponding attribute information of the plurality of reference layouts, the attribute information including attribute values of the plurality of layout attributes. The method further comprises the step of determining a decision tree model used for layout splitting based on the multiple reference splitting strategies and the corresponding attribute information of the multiple reference layouts. The decision tree model includes a plurality of attribute nodes and a plurality of policy nodes. Each attribute node corresponds to an attribute value of one layout attribute. Each strategy node corresponds to one reference splitting strategy. In this way, the division strategy of the layout can be predicted by utilizing the decision tree model obtained according to the reference division strategy, so that a proper layout division mode is found.

Description

[0001] This application is a divisional application of Chinese invention patent application 202410885914.4, filed on July 2, 2024, entitled “Methods, devices and media for layout processing”. Technical Field

[0002] Embodiments of the present disclosure generally relate to the field of integrated circuits, and more particularly, to methods, devices, and media for layout processing. Background Art

[0003] The circuit layout (also referred to as the layout) is a series of graphics converted from the designed and simulated optimized circuit, which contains physical information data related to the device, such as the size of the integrated circuit, the topology definition of each layer, etc. The integrated circuit manufacturer manufactures the mask based on this data. The layout pattern on the mask determines the size of the device or the physical layer of the connection on the chip.

[0004] As the technology nodes of integrated circuit manufacturing processes decrease, the distance between target patterns in integrated circuits decreases, and the density of layout patterns corresponding to the target patterns on the mask increases. Due to the resolution limitation of lithography, it is difficult to use a single mask for lithography imaging for layouts with dense layout patterns. For this reason, it has been proposed to use multiple patterning lithography technology to manufacture advanced processes. The multiple exposure lithography process is to split the layout pattern into multiple different masks, and finally form a complete wafer pattern through multiple exposure and etching iterations. Summary of the invention

[0005] In a first aspect of the present disclosure, a method for layout processing is provided. The method includes: determining multiple reference splitting strategies corresponding to multiple reference layouts respectively. The splitting quality obtained by splitting each reference layout by the corresponding reference splitting strategy meets a predetermined condition. The method also includes determining the corresponding attribute information of the multiple reference layouts, and the attribute information includes the attribute values ​​of multiple layout attributes. The method also includes determining a decision tree model for layout splitting based on the multiple reference splitting strategies and the corresponding attribute information of the multiple reference layouts. The decision tree model includes multiple attribute nodes and multiple strategy nodes. Each attribute node corresponds to the attribute value of a layout attribute. Each strategy node corresponds to a reference splitting strategy.

[0006] In a second aspect of the present disclosure, a method for layout splitting is provided. The method includes: obtaining a decision tree model, the decision tree model including a plurality of attribute nodes and a plurality of strategy nodes. Each attribute node corresponds to an attribute value of a layout attribute among a plurality of layout attributes, and each strategy node corresponds to a reference splitting strategy among a plurality of reference splitting strategies. The method also includes: determining a target splitting strategy for the target layout based on target attribute values ​​of a plurality of layout attributes possessed by the target layout, using the decision tree model.

[0007] In some embodiments, determining a target splitting strategy for a target layout includes: determining a target path corresponding to target attribute values ​​of multiple layout attributes and a target strategy node pointed to by the target path from a decision tree model; and determining a reference splitting strategy indicated by the target strategy node as the target splitting strategy.

[0008] In some embodiments, the layout splitting method also includes: splitting the target layout based on the target splitting strategy; determining the performance index of the decision tree model based on the splitting result of the target layout; and if it is determined that the performance index is lower than the threshold, updating the decision tree model by adjusting the structure of the decision tree model.

[0009] In some embodiments, updating the decision tree model by adjusting the structure of the decision tree model includes: deleting at least one attribute node on a branch of the decision tree model; or adjusting a branch of the decision tree model, the branch including at least one attribute node and at least one policy node.

[0010] In some embodiments, a decision tree model is constructed by: determining multiple reference splitting strategies corresponding to multiple reference layouts respectively, and the splitting quality obtained by splitting each reference layout by the corresponding reference splitting strategy meets predetermined conditions; and determining the decision tree model based on the attribute values ​​of multiple layout attributes of the multiple reference splitting strategies and the multiple reference layouts.

[0011] In a third aspect of the present disclosure, an electronic device is provided. The electronic device includes a processor and a memory coupled to the processor. The memory has instructions stored therein, and when the instructions are executed by the processor, the electronic device executes the method according to the first aspect or the second aspect of the present disclosure.

[0012] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the method according to the first aspect or the second aspect of the present disclosure is implemented.

[0013] It will be understood from the following description that according to an embodiment of the present disclosure, a decision tree model for layout splitting is generated based on multiple reference splitting strategies corresponding to multiple reference layouts and the attribute values ​​of corresponding layout attributes of multiple reference layouts. The attribute node of the decision tree model corresponds to the attribute value of a layout attribute. The strategy node corresponds to a reference splitting strategy. By utilizing the decision tree model thus obtained, the splitting strategy of the layout to be split can be predicted. In this way, an optimized layout splitting result can be obtained, thereby improving the multiple exposure lithography result. Other benefits will be described below in conjunction with the corresponding embodiments.

[0014] It should be understood that the contents described in the summary of the present invention are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0016] Figure 1 A schematic diagram showing an example environment in which various embodiments of the present disclosure can be implemented;

[0017] Figure 2 A flowchart of a method for layout processing according to some embodiments of the present disclosure is shown;

[0018] Figure 3 A schematic diagram of a decision tree model according to some embodiments of the present disclosure is shown;

[0019] Figure 4 A flowchart of a method for determining a splitting strategy of a target layout using a decision tree model according to some embodiments of the present disclosure is shown;

[0020] Figure 5 A flowchart showing a process of determining a splitting strategy for a target layout using a decision tree model and updating the decision tree model according to some embodiments of the present disclosure; and

[0021] Figure 6 A block diagram of an electronic device is shown in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0023] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0024] As briefly mentioned above, due to the resolution limitation of lithography, it is difficult to use a single mask for lithography imaging for layouts with dense patterns. For example, due to the resolution limitation of 193 nanometers (nm) deep ultraviolet (DUV) lithography, design layers with a minimum pitch below 78nm cannot be lithographically imaged using a single mask. With the continuous advancement of technology nodes, starting from nodes such as 16nm, chip manufacturers use multiple exposure technology to manufacture advanced processes.

[0025] One solution for multiple exposure is to abstract the components of the corresponding layers of the chip layout and the distances between the components into a logical graph. The splitting method is abstracted into a graph coloring method. The solution of the graph coloring technology is strongly related to the complexity of the formed graph. The graph coloring problem is a difficult problem that is difficult to determine the existence of a solution. The current graph coloring algorithm is committed to finding a feasible coloring solution at the approximate level by making a limited number of attempts as quickly as possible.

[0026] In order to quickly find the coloring scheme and layout splitting scheme, it is necessary to make path selection based on the distribution characteristics of the graph abstracted from the layout. Since the processes and layers of the chip layout are different, there are large differences between graphs. Therefore, a single layout splitting path selection scheme is difficult to adapt to the needs of various types of layouts. This limitation may lead to significant differences in splitting performance on different layouts, and in severe cases, it may not even be possible to obtain effective splitting results.

[0027] To this end, an embodiment of the present disclosure proposes a method for layout processing. According to an embodiment of the present disclosure, a decision tree model is used to perform layout splitting. For example, a decision tree model can be used to generate a target splitting strategy for a target layout. The decision tree model is obtained based on layout attribute values ​​of multiple reference layouts and multiple reference splitting strategies corresponding to the multiple reference layouts. The decision tree model includes multiple attribute nodes and multiple strategy nodes. Each attribute node corresponds to an attribute value of a layout attribute. Each strategy node corresponds to a reference splitting strategy. In this way, the decision tree model obtained according to the reference splitting strategy can be used to predict the splitting strategy of the layout, so as to find an appropriate layout splitting method.

[0028] As an example, in the process of splitting the target layout, based on the attribute value of the layout attribute of the target layout, the strategy node pointed to by the matching attribute node and the reference splitting strategy of the strategy node can be found from the decision tree model. This reference splitting strategy determination method is simple and fast, and can adapt to different attributes of different layouts. As a result, it can save layout splitting time and improve multiple exposure efficiency.

[0029] Various example implementations of the scheme will be described in detail below with reference to the accompanying drawings.

[0030] See first Figure 1 , which shows a schematic diagram of an example environment 100 in which various embodiments of the present disclosure can be implemented. The example environment 100 can generally include an electronic device 110.

[0031] like Figure 1 As shown, the electronic device 110 obtains multiple reference layouts 102-1, 102-2, ..., and multiple reference splitting strategies 104-1, 102-4, ... corresponding to the multiple reference layouts 102-1, 102-2, .... In this article, the reference layouts 102-1, 102-2, ... can be individually referred to as reference layouts 102, or collectively referred to as reference layouts 102. The reference layout 102 can be a layer of layouts in the layout, also known as a layer of mask layouts. The reference splitting strategies 104-1, 102-4, ... can be individually referred to as reference splitting strategies 104, or collectively referred to as reference splitting strategies 104. The reference splitting strategies of these reference layouts can be splitting strategies with better splitting results that have been previously tested. It should be understood that, although not shown, each reference layout 102 may have one or more reference graphics. These reference graphics may be the same or different. The reference graphics can be arbitrarily distributed on the reference layout. The scope of the present disclosure is not limited in this regard.

[0032] The electronic device 110 can determine a decision tree model 120 based on the multiple reference layouts 102 and the multiple reference splitting strategies 104. In this document, the decision tree model is also referred to as a decision forest model. Figures 2 to 3 Several examples regarding determining the decision tree model 120 are described.

[0033] Next, the electronic device 110 may use the decision tree model 120 to determine a prediction of a splitting strategy for the target layout 142 (also referred to as a layout to be split), that is, a target splitting strategy 144. Using the target splitting strategy 144, the electronic device 110 may split the target layout 142. Alternatively, or in addition, in some example embodiments, the electronic device 110 may also transmit the decision tree model 120 to other layout processing devices. The layout processing device may use the decision tree model 120 to predict the splitting strategy for the layout to be split. It should be understood that, although not shown, one or more target graphics may be included on the target layout 142. In this article, the target graphic refers to a graphic that is expected to correspond to it on the wafer after photolithography. This will be discussed below in conjunction with Figure 4 and Figure 5 Several examples are described regarding determining a target splitting strategy 144 for a target layout 142 using a decision tree model 120 .

[0034] In some embodiments, the electronic device 110 may also interact with a client (not shown in the figure). For example, the electronic device 110 may receive an input message from the client and output a feedback message to the client. In some embodiments, the input message from the client may specify the reference graph 102 and / or specify a reference splitting strategy 104 corresponding to the reference graph 102. The electronic device 110 may select the reference graph 102 and the reference splitting strategy 104 corresponding to the reference graph 102 based on the input message from the client to determine the decision tree model 120.

[0035] In the example environment 100, the electronic device 110 and the electronic device 110 can be any type of device with computing capabilities, including a terminal device or a server device. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a gaming device, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like.

[0036] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and does not imply any limitation on the scope of the present disclosure. Figure 1 The various layouts and the figures therein shown in the drawings are only exemplary and are not intended to limit the scope of the present disclosure. The exemplary embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings.

[0037] Next, several embodiments of determining the decision tree model 120 and determining the target splitting strategy 144 for the target layout 142 using the decision tree model 120 are described. Figure 2 FIG. 2 is a flow chart of a method 200 for layout processing according to some embodiments of the present disclosure. In some embodiments, the method 200 may be performed as follows: Figure 1 The electronic device 110 shown executes. It should be understood that the method 200 may further include additional blocks not shown and / or may omit one (or some) of the blocks shown, and the scope of the present disclosure is not limited in this respect.

[0038] In box 210, the electronic device 110 determines multiple reference splitting strategies 104 corresponding to multiple reference layouts 102 respectively. The splitting quality obtained by splitting each reference layout 102 by the corresponding reference splitting strategy 104 meets the predetermined conditions. That is, the splitting strategy that can obtain the splitting quality that meets the predetermined conditions is used as the reference splitting strategy 104 of the reference layout 102. In this article, the splitting strategy of the layout refers to the rules or methods that indicate how to split the layout. The reference layout 102 can be split into any number of layout parts, for example, two or more layout parts, using the reference splitting strategy 104. In the embodiments below, for the sake of ease of description, the description will be taken as an example of dividing the layout into two layout parts.

[0039] As an example, the layout splitting strategy can indicate the layout splitting direction, for example, from left to right, from top to bottom, from top left to bottom right, and so on. As another example, the layout splitting strategy can indicate the layout splitting position. For example, it can be indicated to split from the middle position of the layout. As another example, it can be indicated to split at a layout position with a certain feature (for example, a long strip of graphics). The layout splitting strategy can also be a combination of the layout splitting direction and the layout splitting position. The splitting strategies described above are merely exemplary and not restrictive. The layout splitting strategy can be set arbitrarily. The scope of the present disclosure is not limited here.

[0040] In some embodiments, the predetermined condition of the splitting quality may indicate that the splitting time of the layout does not exceed the threshold time. The threshold time may be preset or set by the user. That is, the splitting time of the reference layout 102 split by the reference splitting strategy 104 is shorter. Additionally, or alternatively, in some embodiments, the predetermined condition may indicate that the distribution ratio of the layout graphics after splitting is within a predetermined range. For example, the predetermined condition may indicate that the proportion of graphics in the first part of the layout after splitting is close to the proportion of graphics in the second part of the layout. That is, the proportion of layout graphics in the multiple split parts obtained by splitting the reference layout 102 by the reference splitting strategy 104 is close. For example, in some examples, the predetermined condition may indicate that the correct splitting result can be obtained by splitting the reference layout 102 by the reference splitting strategy 104. It should be understood that the various predetermined conditions listed above are merely exemplary and are not intended to limit this solution. More or fewer appropriate predetermined conditions can be adopted according to actual needs. The scope of the present disclosure is not limited here.

[0041] In some embodiments, the electronic device 110 can collect various reference layouts 102. For example, various reference layouts of a certain manufacturer can be collected. For the collected reference layouts 102, any appropriate splitting tool can be used to perform multiple splitting attempts. The optimal splitting scheme with the best splitting quality in multiple splitting attempts can be used as a reference splitting strategy 104. The various splitting strategies can also be sorted according to the splitting quality. A predetermined number of splitting strategies with a high ranking are used as reference splitting strategies 104. For example, N splitting strategies that can obtain the correct splitting results and take the shortest time can be used as reference splitting strategies, where N is a natural number greater than or equal to 1. Alternatively, in some embodiments, multiple splitting strategies that meet predetermined conditions can be used as reference splitting strategies 104. The corresponding reference splitting strategies 104 for multiple reference layouts 102 thus determined can be used to determine the decision tree model 120.

[0042] Alternatively, in some embodiments, the electronic device 110 may receive from a client or other device a plurality of reference layouts 102 and a plurality of reference splitting strategies 104 corresponding to the plurality of reference layouts 102. These reference splitting strategies may be splitting strategies set by the user based on experience, for example, that enable the splitting result to satisfy a predetermined condition.

[0043] At block 220 , the electronic device 110 determines corresponding attribute information of the plurality of reference layouts 102 . The attribute information includes attribute values ​​of the plurality of layout attributes. That is, the electronic device 110 may determine corresponding attribute values ​​of the plurality of layout attributes of each reference layout 102 .

[0044] The layout attributes may include the process node (also called the technology node or process node) of the layout, and its value may be 28nm, 14nm, 12nm, 10nm, 7nm, 5nm, etc. The layout attributes may also include the layout type, such as the type of the layer of the layout, for example, metal layer 0 (M0), M0G, M0C, metal layer 1 (M1), metal layer 2 (M2), via layer 0 (V0), via layer 1 (V1), etc. The layout attributes may also include the object to which the layout is to be supplied, such as different customers or different devices. The layout attributes may also include the graphic information of the layout, such as the size, shape, distribution, etc. of the graphics in the layout. The electronic device 110 may collect the layout graphic information of the reference layout 102, such as the size, shape, distribution, etc. of the graphics. The electronic device 110 may perform feature selection and feature processing on these graphic information or other feature information. This information may also be used as part of the attribute information of the reference layout 102. It should be understood that the layout attributes may include one or more of the above attributes, and the layout attributes may also include any other appropriate attributes. These layout attributes may have other appropriate attribute values. The scope of the present disclosure is not limited here.

[0045] In block 230, the electronic device 110 determines a decision tree model 120 for layout splitting based on the corresponding attribute information of the plurality of reference splitting strategies 104 and the plurality of reference layouts 102. The decision tree model 120 includes a plurality of attribute nodes and a plurality of strategy nodes. Each attribute node corresponds to an attribute value of a layout attribute in the plurality of layout attributes. Each strategy node corresponds to a reference splitting strategy in the plurality of reference splitting strategies.

[0046] In some embodiments, the decision tree model 120 may include attribute nodes of multiple levels. Each level may correspond to a layout attribute. The electronic device 110 may generate these attribute nodes layer by layer. The attribute node of the highest level (also referred to as the first level) is also referred to as the root node or parent node of the decision tree model 120. For example, the electronic device 110 may arbitrarily select a first layout attribute from multiple layout attributes as the layout attribute of the first level. Alternatively, in some embodiments, the electronic device 110 may select a first layout attribute from the group of layout attributes based on the information gain metric of each of the group of layout attributes to be divided. The information gain metric of the layout attribute can be used to measure the degree of reduction in information complexity caused by the layout attribute.

[0047] Specifically, the information gain metric of a layout attribute can be determined based on the ratio between the information gain value of the layout attribute and the intrinsic values ​​of a set of layout attributes. The information gain value of the layout attribute represents the degree of information complexity reduction caused by the layout attribute. The intrinsic values ​​of a set of layout attributes are proportional to the number of attribute values ​​of the corresponding layout attribute.

[0048] As an example, information entropy can be used to determine the information gain value of the layout attribute. For example, the information entropy of the multiple reference layouts 102 can be determined using formula (1):

[0049]

[0050] Where D represents a set of multiple reference layouts 102, Ent(D) represents the information entropy of the set D, and p k represents the proportion of samples of the kth class in the set D, and y represents the number of sample types. For example, these samples can be classified according to various layout attributes. Information entropy can represent the degree of chaos (i.e., uncertainty) of the sample set.

[0051] Assume that the layout attribute a has V possible values ​​a 1 , a 2 ,......,a V , if a is used to partition the set D, V branch nodes (i.e., attribute nodes) will be generated, where the vth branch node includes all nodes in D whose value on the layout attribute a is a v The sample is denoted as D v According to formula (1), D v Considering that different branch nodes contain different numbers of samples, we can assign weights to the branch nodes. The more samples there are, that is, the more samples have the attribute value, the greater the influence of the branch node.

[0052] According to the determined information entropy, the information gain value of the layout attribute can be determined using formula (2):

[0053]

[0054] Where Gain(D,a) represents the information gain value of the layout attribute a. Ent(D) can represent the degree of chaos of the set D. It can reflect the degree of disorder of set D after partitioning using layout attribute a. That is, the information gain value of layout attribute a can represent the reduction in the degree of disorder of set D through the partitioning of layout attribute a, that is, the amount of information increased, so it is called information gain value. Generally speaking, the greater the information gain, the greater the purity improvement obtained by using layout attribute a for partitioning.

[0055] In some embodiments, the information gain value itself can be used as an information gain metric to select a first layout attribute from a group of layout attributes. For example, the layout attribute with the largest information gain value can be selected as the first layout attribute corresponding to the highest first level.

[0056] Alternatively, in some embodiments, the ratio between the information gain value and the intrinsic value of the layout attribute can be used as the information gain metric to select the first layout attribute. For example, the intrinsic value of the layout attribute can be calculated using formula (3):

[0057]

[0058] Where IV(a) represents the intrinsic value of the layout attribute a. The greater the number of possible values ​​of the layout attribute a (i.e., the larger V is), the larger the value of IV(a) is.

[0059] Using the intrinsic value IV(a) and the information gain value Gain(D,a), the information gain measure of the layout attribute a can be determined using formula (4):

[0060]

[0061] Wherein, Gain-ratio(D,a) represents the information gain measure of the layout attribute a. The electronic device 110 can select the first layout attribute based on the information gain measure of each of a set of layout attributes. For example, the layout attribute with the largest information gain measure can be selected as the first layout attribute of the highest level. By using the information gain measure determined by formula (4) to select the layout attribute, the influence of the number of samples corresponding to the layout attribute on the selection result can be reduced. This method can avoid the influence caused by the imbalance of the number of layout attribute samples collected for each reference layout.

[0062] Several examples of determining the first layout attribute of the first level based on the information gain metric are described above. It should be understood that the above-listed equations (1) to (4) are merely exemplary and are not intended to be limiting. Any appropriate calculation method or selection method may be used to select nodes at each level of the decision tree model 120.

[0063] Taking the first layout attribute as the layout type, such as the layer type, as an example, the electronic device 110 can determine at least one attribute node of the first level based on the layer type. For example, the electronic device 110 can generate attribute nodes corresponding to the M0 type, M0C type, V0 type, etc. These attributes are respectively associated with the reference layout 102 corresponding to the M0 type, M0C type, and V0 type.

[0064] Figure 3 FIG. 1 is a schematic diagram of an example decision tree model 120 according to an embodiment of the present disclosure. Figure 3 In the exemplary embodiment, the layout type or layer type is described as an example of the first layout attribute. Figure 3 As shown, according to the first layout attribute of layer type 310, attribute nodes corresponding to different layer types can be generated, such as attribute node 312 corresponding to M0 type, attribute node 314 corresponding to M0C type, attribute node 316 corresponding to V0 type, and so on.

[0065] After constructing a certain attribute node (e.g., the first attribute node of the first level), the electronic device 110 may iteratively perform operations to generate at least one node of the next level of the first attribute node in the decision tree model 120. Next, the process of iteratively generating at least one node of the next level of the first attribute node will be described in detail.

[0066] In some embodiments, the electronic device 110 may select a target layout attribute from a set of layout attributes based on the information gain metric of each of the set of layout attributes to be divided. The set of layout attributes to be divided is at least a part of a plurality of layout attributes and does not include the layout attribute corresponding to the first attribute node. For example, in the case where the attribute node of the layout attribute of the layer type 310 listed above has been constructed, a set of layout attributes may include layout attributes other than the layer type. That is, a set of layout attributes may include the process node of the layout and the object to which the layout is to be supplied.

[0067] Assume that based on the information gain metric of the process node of the layout and the information gain metric of the object to which the layout is to be supplied, it is determined that the target layout attribute is a process node. Next, the electronic device 110 can generate at least one second attribute node corresponding to at least one attribute value in the decision tree model 120 based on at least one attribute value of the target layout attribute. At least one second attribute node is the next level of the first attribute node. For example, the next level of the attribute node 312 may include attribute nodes 322, attribute nodes 324, and attribute nodes 326. These attribute nodes 322, 324, and 326 may correspond to different process node values, such as 14nm, 7nm, 10nm, and so on. The electronic device 110 can remove the target layout attribute from a set of layout attributes to update a set of layout attributes to be divided.

[0068] Similarly, the information gain value of the layout attribute calculated by equation (1) and equation (2) can be used to select the target layout attribute. For another example, the information gain metric calculated by equation (1) to equation (4) can also be used to select the target layout attribute. This article will not go into details here. By iteratively executing the above process, each attribute node of the decision tree model 120 can be constructed.

[0069] In the above, multiple attribute nodes corresponding to the attribute values ​​of different layout attributes of the decision tree model 120 are constructed by calculating the information gain metric. It should be understood that any other appropriate existing decision tree construction method or decision tree construction method that will appear in the future can also be used to construct each attribute node of the decision tree model 120. The embodiments of the present disclosure are not limited in this respect.

[0070] In some embodiments, the electronic device 110 can determine whether the constructed attribute node can be divided. For example, if the reference splitting strategies 104 corresponding to the various reference layouts 102 associated with a certain attribute node are the same, the attribute node cannot be divided. For another example, if the attribute values ​​of the layout attributes that have not been divided of the various reference layouts associated with a certain attribute node are the same, the attribute node cannot be divided. For another example, if there is no reference layout associated with a certain attribute node in multiple reference layouts, the attribute node cannot be divided.

[0071] In some embodiments, if the electronic device 110 determines that a certain attribute node can be further divided, the above method can be used to continue to construct the attribute nodes of the next level. For example, for attribute node 322, the electronic device 110 determines that the attribute node 322 can be further divided, and a similar method can be used to construct the attribute nodes of the next level. For example, attribute node 332 and attribute node 334 of the layout attribute of the object to which the layout is supplied. On the contrary, if a certain attribute node, such as the third attribute node, cannot be divided, the electronic device 110 can generate a policy node of the next level of the third attribute node. Figure 3 As shown, attribute node 324 cannot be divided, then electronic device 110 can construct a policy node 346 at the next level of attribute node 324. Similarly, a policy node 342 at the next level of attribute node 332, a policy node 344 at the next level of attribute node 334, etc. can be constructed. In this article, a policy node may also be referred to as a leaf node, which no longer has a node at the next level.

[0072] Next, the process of constructing a strategy node will be described in detail. In some embodiments, the electronic device 110 can determine the path from the third attribute node to the root node in the decision tree model 120. The root node does not have a node at the previous level. For example, taking the first level listed above as an attribute node corresponding to a certain layer type as an example, the attribute node can be the root node of the third attribute node. Each attribute node of the determined path defines the attribute value of at least one layout attribute among multiple layout attributes. Figure 3 In the example of , a path from attribute node 324 to its root node, namely attribute node 312, can be determined. The path includes the attribute value corresponding to the layout attribute of attribute node 312 (ie, M0 layer) and the attribute value corresponding to the layout attribute of attribute node 324 (ie, 7nm process node).

[0073] The electronic device 110 can determine the first reference splitting strategy corresponding to the path among the multiple reference splitting strategies 104. That is, the reference splitting strategy 104 corresponding to the reference layout 102 having the M0 layer and the 7nm process node among the multiple reference splitting strategies 104 can be determined as the first reference splitting strategy corresponding to the path. The electronic device 110 can generate a reference strategy node at a level below the third attribute node, and the reference strategy node indicates that the first reference splitting strategy is used for the layout having the attribute value of the above-mentioned at least one layout attribute. In this way, we can establish a rule definition for the rules for forming the optimal splitting path based on the optimal splitting path analysis as a strategy node of the decision tree model 120.

[0074] In the above manner, each node of the decision tree model 120 can be constructed. In some embodiments, the decision tree model 120 can be divided into multiple decision trees (also called subtrees) according to the highest level, namely subtree 350, subtree 360 ​​and subtree 370. That is, for the first layout attribute, such as the layer type, corresponding subtrees can be constructed to predict the target splitting strategy of the target layout of the layer type. These subtrees constitute the decision tree model 120. Therefore, in this article, the decision tree model 120 is also referred to as a decision tree forest or a decision forest.

[0075] Alternatively, in some embodiments, a subtree corresponding to the attribute value of a certain layout attribute can be constructed as a decision tree model for a decision tree model for a layout having the attribute value. For example, a decision tree model can be constructed for the attribute value of a process node having 7nm. That is, reference layouts having a process node of 7nm and other layout attributes (e.g., layer type, object supplied to, etc.) can be collected. Using these reference layouts for 7nm and their corresponding reference splitting strategies, a decision tree model for a layout of 7nm can be constructed using a similar method as described above. That is, different decision tree models can be constructed for layouts having attribute values ​​of a certain type of layout attributes to predict splitting strategies respectively.

[0076] It should be understood that Figure 3 The decision tree model 120 shown is merely illustrative and not limiting. Figure 3 The number of nodes, node connection relationships, etc. in can be any other number of nodes and have any other appropriate connection relationships.

[0077] Combination of the above Figure 2 and Figure 3 Several examples of building a decision tree model 120 are described. It should be understood that Figure 2 The order of the boxes shown in is exemplary. Figure 2 The order of each frame can be adjusted. For example, the order of frame 210 and frame 220 can be interchanged. For another example, frame 210 and frame 220 can be executed in parallel. The embodiments of the present disclosure are not limited here.

[0078] In some embodiments, the electronic device 110 may also evaluate and adjust the constructed decision tree model 120. As an example, the electronic device 110 may determine a target splitting strategy for the test layout based on the attribute values ​​of multiple layout attributes of the test layout using the decision tree model 120. The test layout may be one or more test layouts in a pre-collected test set. A reference splitting strategy corresponding to the test layout is also stored in the test set. Splitting the test layout using the reference splitting strategy may obtain a test result that meets a predetermined condition.

[0079] The electronic device 110 may determine the performance index of the decision tree model 120 based on the comparison between the determined target splitting strategy and the reference splitting strategy for the test layout. The electronic device 110 may use a set of test layouts to test the performance of the decision tree model 120. For example, the performance of the decision tree model 120 may be evaluated by using appropriate indicators such as accuracy, precision, recall, F1 value (F1 value is the harmonic mean of precision and recall) as performance indicators.

[0080] In some embodiments, if the performance index of the decision tree model 120 is lower than a threshold value, the electronic device 110 can update the decision tree model 120 by adjusting the structure of the decision tree model 120. The threshold value can be any appropriate value set in advance. For example, the electronic device 110 can delete at least one attribute node on a branch of the decision tree model 120. As another example, the electronic device 110 can adjust a branch of the decision tree model 120, which includes at least one attribute node and at least one strategy node. For example, the branch can be deleted, or a new attribute node can be added to the branch, and so on. The branch or node to be adjusted or deleted can be selected based on the test results. For example, if the target splitting strategies obtained for multiple test layouts with a certain attribute value of a certain layout attribute cannot provide a good splitting result, the attribute node corresponding to the attribute value of the layout attribute can be deleted.

[0081] In some embodiments, in order to prevent overfitting, a pruning operation may also be performed on the constructed decision tree model 120. That is, some unnecessary nodes of the decision tree model 120 may be deleted or the branches of the nodes may be adjusted, and so on.

[0082] Through the above-mentioned model evaluation and adjustment as well as model pruning and other operations, it can be ensured that the constructed decision tree model 120 can provide a relatively accurate target splitting strategy for various layouts, thereby ensuring the subsequent layout splitting and multiple exposure.

[0083] As submitted above, in some embodiments, the constructed decision tree model 120 can be used to predict the target splitting strategy of the target layout. Figure 4 A flowchart of a method 400 for a layout splitting process using a decision tree model 120 according to some embodiments of the present disclosure is described. The method 400 may be performed by an electronic device 110. It should be understood that the method 400 may also include additional blocks not shown and / or may omit one (or some) of the blocks shown, and the scope of the present disclosure is not limited in this respect.

[0084] At block 410, the electronic device 110 obtains a decision tree model 120. The decision tree model 120 includes a plurality of attribute nodes and a plurality of strategy nodes. Each attribute node corresponds to an attribute value of a layout attribute among a plurality of layout attributes. Each strategy node corresponds to a reference splitting strategy among a plurality of reference splitting strategies. For example, the decision tree model 120 may be as follows: Figure 3 As shown. The attribute nodes and strategy nodes of the decision tree model 120 have been combined in the previous text. Figure 2 and Figure 3 The above has been described and will not be repeated here.

[0085] The decision tree model 120 may be constructed by the electronic device 110 using the method 200 or other appropriate methods. Alternatively, the decision tree model 120 may be received by the electronic device 110 from another device, which may use the method 200 or other methods to construct the decision tree model 120. Specifically, the electronic device 110 or another device may determine a plurality of reference splitting strategies 104 corresponding to the plurality of reference layouts 102, respectively. The splitting quality obtained by splitting each reference layout 102 by the corresponding reference splitting strategy 104 satisfies a predetermined condition. The electronic device 110 or another device may determine the decision tree model 120 based on the attribute values ​​of the plurality of reference splitting strategies 104 and the plurality of layout attributes of the plurality of reference layouts 102.

[0086] In box 420 , the electronic device 110 determines a target splitting strategy 144 for the target layout 142 using the decision tree model 120 based on target attribute values ​​of multiple layout attributes of the target layout 142 .

[0087] In some embodiments, the electronic device 110 may determine the target paths corresponding to the target attribute values ​​of the multiple layout attributes and the target strategy nodes pointed to by the target paths from the decision tree model 120. The electronic device 110 may determine the reference splitting strategy indicated by the target strategy node as the target splitting strategy 144. Specifically, the electronic device 110 may determine the target paths corresponding to the target attribute values ​​of the multiple layout attributes and the target strategy nodes pointed to by the target paths from the decision tree model 120. For example, assuming Figure 3 The attribute node 312 in corresponds to the M0 layer, the attribute node 322 corresponds to 14nm, and the attribute node 332 corresponds to the object A. For the target layout 142 of the M0 layer, the 14nm process node, and to be supplied to the object A, the target splitting strategy indicated by the strategy node 342 can be adopted. As an example, the strategy can indicate that the long strip-shaped graphics in the target layout 142 are preferentially split.

[0088] In some embodiments, the electronic device 110 can split the target layout 142 based on the target splitting strategy 144. By using the decision tree model 120 constructed using the reference layout and the reference splitting strategy, the splitting strategy of the layout with the attribute values ​​of various layout attributes can be predicted. This decision tree model 120 can adapt to layouts of various attributes or types, and obtain more effective splitting results for various layouts. For different input layouts, different splitting schemes are selected according to the prediction results of the decision tree model 120, so that better splitting results can be obtained.

[0089] In some embodiments, the electronic device 110 may determine the performance index of the decision tree model 120 based on the splitting result of splitting the target layout 142. For example, the performance index of the decision tree model 120 may be determined based on the time spent on the splitting, the proportion of graphics of different layout parts obtained by the splitting, and the like. If the splitting takes a long time, the performance index is low. If the proportion of graphics of different layout parts obtained by the splitting is quite different, the performance index is low. If it is determined that the performance index is lower than the threshold, the electronic device 110 may update the decision tree model 120 by adjusting the structure of the decision tree model 120. For example, at least one attribute node on a branch of the decision tree model 120 may be deleted. As another example, a branch of the decision tree model 120 may be adjusted, which includes at least one attribute node and at least one policy node.

[0090] By using the feedback of the splitting results to adjust the decision tree model 120, the performance of the decision tree model 120 can be continuously improved so that it can continuously adapt to more types of maps with more different attributes. With the continuous investment of such decision tree model 120, the possibility of predicting the optimal splitting strategy gradually increases.

[0091] Figure 5 FIG. 5 is a flowchart of a process 500 of determining a target splitting strategy 144 of a target layout 142 using a decision tree model 120 and updating the decision tree model 120 according to some embodiments of the present disclosure. Figure 5 As shown, in box 510, the electronic device 110 may perform pre-processing on the target layout 142 (also referred to as a new sample). For example, the electronic device 110 may obtain target attribute values ​​of multiple layout attributes of the target layout 142. These layout attributes may be the same as the multiple layout attributes used to construct the decision tree model 120. For another example, the electronic device 110 may also perform other pre-processing on the target layout 142.

[0092] In block 520, the electronic device 110 may determine the target splitting strategy 144 for the target layout 142 based on the target attribute values ​​of the multiple layout attributes of the target layout 142, using the constructed (also referred to as trained) decision tree model 120. That is, the decision tree model 120 may predict the splitting strategy of the target layout 142. Specifically, the electronic device 110 may determine the target path corresponding to the target attribute values ​​of the multiple layout attributes and the target strategy node pointed to by the target path from the decision tree model 120. For example, assuming Figure 3 312 in the target layout 142 corresponds to the M0 layer, the attribute node 322 corresponds to 14nm, and the attribute node 332 corresponds to the object A. For the target layout 142 to be supplied to the object A at the M0 layer and the 14nm process node, the target splitting strategy indicated by the strategy node 342 may be adopted. For example, the strategy may indicate that the long strip-shaped graphics in the target layout 142 are preferentially split. In block 530, the electronic device 110 may split the target layout 142 based on the target splitting strategy 144.

[0093] By using the decision tree model 120 constructed using the reference layout and the reference splitting strategy, the splitting strategy of the layout with the attribute values ​​of various layout attributes can be predicted. This decision tree model 120 can adapt to layouts of various attributes or types, and obtain more effective splitting results for various layouts. For different input layouts, different splitting schemes are selected according to the prediction results of the decision tree model 120, so that better splitting results can be obtained.

[0094] In some embodiments, the splitting results obtained by splitting the target layout 142 according to the target splitting strategy 144 can in turn be fed back to the electronic device 110. The electronic device 110 can further optimize or adjust the decision tree model based on the feedback. Specifically, Figure 5 As shown, in box 540, the electronic device 110 can determine the performance index of the decision tree model 120 based on the splitting result of splitting the target layout 142 according to the target splitting strategy 144. For example, the performance index of the decision tree model 120 can be determined according to the time spent on splitting, the proportion of graphics of different layout parts obtained by splitting, etc. If the splitting takes a long time, the performance index is low. If the proportion of graphics of different layout parts obtained by splitting is quite different, the performance index is low. For another example, if the target layout 142 cannot be successfully split according to the target splitting strategy 144, the performance index is low.

[0095] At block 550, the electronic device 110 may determine whether the performance indicator is below a threshold. The threshold may be any appropriate value set in advance. If the performance indicator of the decision tree model 120 is below the threshold, then at block 560, the electronic device 110 may update the decision tree model 120 by adjusting the structure of the decision tree model 120. For example, at least one attribute node on a branch of the decision tree model 120 may be deleted. For another example, a branch of the decision tree model including at least one attribute node and at least one policy node may be adjusted.

[0096] By using the feedback of the splitting results to adjust the decision tree model 120, the performance of the decision tree model 120 can be continuously improved so that it can continuously adapt to more types of maps with more different attributes. With the continuous investment of such decision tree model 120, the possibility of predicting the optimal splitting strategy gradually increases.

[0097] It should be understood that method 200, method 400 and process 500 can be used in combination. That is, the electronic device 110 can use method 200 to construct a decision tree model 120. The electronic device 110 can then use the decision tree model 120 to adopt the method to split the target layout, or use process 500 to split the target layout and update the decision tree model 120. In other embodiments, method 200 and method 400 or process 500 can be implemented by different settings. For example, the electronic device 110 can use method 200 to construct a decision tree model 120. The electronic device 110 can transmit the constructed decision tree model 120 to other devices, such as a layout processing device. The layout processing device can use the received decision tree model 120 to predict the splitting strategy of the target layout.

[0098] Figure 6 1 shows a block diagram of a server or electronic device 600 in which one or more embodiments of the present disclosure may be implemented. The electronic device 600 may be used to implement, for example, Figure 1 The electronic device 110 shown. It should be understood that Figure 6 The electronic device 600 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein.

[0099] like Figure 6As shown, the electronic device 600 is in the form of a general electronic device. The components of the electronic device 600 may include, but are not limited to, one or more processors 610 or processing units, a memory 620, a storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processing unit may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 620. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 600.

[0100] The electronic device 600 typically includes a plurality of computer storage media. Such media may be any available media accessible to the electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 may be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data (e.g., training data for training) and may be accessed within the electronic device 600.

[0101] The electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 6 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 620 may include a computer program product 625 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0102] The communication unit 640 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 600 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0103] The input device 650 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 660 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 600 may also communicate with one or more external devices (not shown) through the communication unit 640 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 600, or communicate with any device that allows the electronic device 600 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0104] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which one or more computer instructions are stored, wherein the one or more computer instructions are executed by a processor to implement the method described above.

[0105] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0106] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0107] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0108] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0109] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the marketplace, or to enable other persons of ordinary skill in the art to understand the implementations disclosed herein.

Claims

1. A layout splitting method, comprising: For multiple layout attributes, generate multiple attribute nodes of a decision tree model for layout splitting, each attribute node corresponds to an attribute value of one of the multiple layout attributes; generating a plurality of strategy nodes of the decision tree model, each strategy node corresponding to a reference splitting strategy indicating how to split a layout into at least two layout parts; as well as Based on the target attribute values ​​of the multiple layout attributes of the target layout, the target splitting strategy for the target layout is determined using the decision tree model.

2. The layout splitting method according to claim 1, characterized in that: Generating a plurality of attribute nodes of a decision tree model for layout splitting includes: for a generated first attribute node, iteratively performing the following operations: Based on the information gain metrics of each of the group of layout attributes to be divided, selecting a target layout attribute from the group of layout attributes, the group of layout attributes being at least a part of the plurality of layout attributes and excluding the first layout attribute corresponding to the first attribute node; Based on at least one attribute value of the target layout attribute, generating at least one second attribute node corresponding to the at least one attribute value in the decision tree model, wherein the at least one second attribute node is a next level of the first attribute node; and The first layout attribute is removed from the set of layout attributes to update the set of layout attributes to be divided.

3. The layout splitting method according to claim 2, characterized in that: The information gain metric of the target layout attribute is determined based on the ratio between the information gain value of the target layout attribute and the respective intrinsic values ​​of the set of layout attributes, the information gain value of the target layout attribute represents the degree of reduction in information complexity caused by the target layout attribute, and the respective intrinsic values ​​of the set of layout attributes are proportional to the number of attribute values ​​of the corresponding layout attribute.

4. The layout splitting method according to claim 2, characterized in that: The multiple strategy nodes for generating the decision tree model include: Determine that a third attribute node in the constructed attribute nodes cannot be divided; Determine a path from the third attribute node to a root node in the decision tree model, the root node having no node at an upper level, and each attribute node of the path defining an attribute value of at least one layout attribute among the plurality of layout attributes; Determine a first reference splitting strategy corresponding to the path from a plurality of reference splitting strategies respectively corresponding to a plurality of reference layouts, wherein the first reference layout corresponding to the first reference splitting strategy in the plurality of reference layouts has attribute values ​​of layout attributes defined by each attribute node of the path; and A reference strategy node at a level below the third attribute node is generated, wherein the reference strategy node indicates that the first reference splitting strategy is used for a layout having an attribute value of the at least one layout attribute.

5. The layout splitting method according to claim 4, characterized in that: Determining that the third attribute node cannot be split is based on at least one of the following: The reference splitting strategies corresponding to the reference layouts associated with the third attribute node are the same. The attribute values ​​of the undivided layout attributes of each reference layout associated with the third attribute node are the same, There is no reference layout associated with the third attribute node among the multiple reference layouts.

6. The layout splitting method according to claim 4, characterized in that: The splitting quality of the first reference layout obtained by splitting it according to the corresponding first reference splitting strategy meets a predetermined condition.

7. The layout splitting method according to claim 6, characterized in that: The predetermined condition indicates at least one of the following: The layout splitting time does not exceed the threshold time, The distribution ratio of the split layout graphics is within the predetermined range.

8. The layout splitting method according to claim 1, characterized in that: Determining a target splitting strategy for the target layout includes: Determining, from the decision tree model, a target path corresponding to the target attribute values ​​of the plurality of layout attributes and a target strategy node pointed to by the target path; and The reference splitting strategy indicated by the target strategy node is determined as the target splitting strategy.

9. The layout splitting method according to claim 1, characterized in that: The layout splitting method also includes: Based on the target splitting strategy, split the target territory; Determining a performance indicator of the decision tree model based on a splitting result of splitting the target layout; and If it is determined that the performance indicator is lower than a threshold, the decision tree model is updated by adjusting the structure of the decision tree model.

10. The layout splitting method according to claim 1, characterized in that: The layout splitting method also includes: Based on the attribute values ​​of the plurality of layout attributes of the test layout, using the decision tree model, determining a target splitting strategy for the test layout; Determining a performance indicator of the decision tree model based on a comparison between the target splitting strategy and a reference splitting strategy for the test layout; and If the performance indicator is lower than a threshold, the decision tree model is updated by adjusting the structure of the decision tree model.

11. The layout splitting method according to claim 9 or 10, characterized in that: Updating the decision tree model by adjusting the structure of the decision tree model includes: Deleting at least one attribute node on a branch of the decision tree model; or The branches of the decision tree model are adjusted, wherein the branches include at least one attribute node and at least one strategy node.

12. The layout splitting method according to claim 1, characterized in that: The plurality of layout attributes include at least one of the following: the object to which the layout is to be supplied, The process node of the layout, Layout type.

13. The layout splitting method according to claim 1, characterized in that: The split strategy of the map includes at least one of the following: The direction of the layout splitting, The layout split location.

14. An electronic device, characterized in that: include: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 13 when executed by the at least one processing unit.

15. A computer-readable storage medium, characterized in that: A computer program is stored thereon, characterized in that the computer program can be executed by a processor to implement the method according to any one of claims 1 to 13.

Images