Characteristic prediction system for semiconductor element

Abstract

To provide a characteristic prediction system for a semiconductor element.SOLUTION: A characteristic prediction system for a semiconductor element has a storage unit, an input unit, a processing unit, and a calculation unit. The processing unit has a function of creating a learning data set from first data stored in the storage unit, a function of creating prediction data from second data supplied from the input unit, a function of converting qualitative data (name of material, or composition formula) into quantitative data (characteristic of element, and composition), and a function of extracting or removing the first data and the second data. The first data includes a process list for first to m-th (m is an integer of 2 or more) semiconductor elements, and characteristics of the first to m-th semiconductor elements. The second data includes a process list for an (m+1)-th semiconductor element. By having a function of performing learning and inference of supervised learning, the calculation unit performs the leaning on the basis of the learning data set and inference of the characteristic of the semiconductor element from the prediction data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] 1. Field of the Invention One aspect of the present invention relates to a system for predicting characteristics of a semiconductor device. Another aspect of the present invention relates to a method for predicting characteristics of a semiconductor device.

[0002] In this specification and the like, a semiconductor element refers to an element that can function by utilizing semiconductor characteristics. An example of a semiconductor element is a transistor, a diode, a light-emitting element, or a light-receiving element. Another example of a semiconductor element is a passive element such as a capacitance, a resistor, or an inductor that is formed by a conductive film or an insulating film. Another example of a semiconductor element is a semiconductor device that includes a circuit having a semiconductor element or a passive element. [Background technology]

[0003] In recent years, in fields using artificial intelligence (AI), robotics, and energy fields that handle high power such as power ICs, new semiconductor elements have been developed to solve issues such as increasing computational loads and power consumption. While the integrated circuits and semiconductor elements used in integrated circuits required by the market are becoming more complex, there is a demand for integrated circuits with new functions to be launched quickly. However, the process design, device design, and circuit design in the development of semiconductor elements require the knowledge, know-how, and experience of skilled engineers.

[0004] In recent years, methods have been proposed for optimizing manufacturing processes for semiconductor devices, estimating device characteristics, etc. Patent Document 1 discloses a method for calculating image feature amounts from an SEM image of a cross-sectional shape pattern of a semiconductor device, and estimating the device characteristics of an evaluation pattern from the corresponding relationship between the image feature amounts and the device characteristics. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2007-129059 A Summary of the Invention [Problem to be solved by the invention]

[0006] In the manufacturing process of semiconductor devices, there are many steps to complete the semiconductor device, and the types of steps and processing conditions are diverse. After the semiconductor devices are manufactured through a lengthy process, their characteristics, such as electrical characteristics and reliability test results, are measured using measuring equipment. The causal relationship between the manufacturing process of semiconductor devices and the characteristics of the semiconductor devices is verified one by one through experiments, and the characteristics of the semiconductor devices are improved.

[0007] However, it takes time and money to comprehensively adjust the manufacturing process of semiconductor devices and investigate the causal relationship with the characteristics of the semiconductor devices. Furthermore, it is difficult for a human to understand the huge amount of data. Therefore, optimizing the manufacturing process through experiments requires a great deal of effort.

[0008] In view of the above, an object of one embodiment of the present invention is to provide a system for predicting characteristics of a semiconductor element.Another object of one embodiment of the present invention is to provide a method for predicting characteristics of a semiconductor element.Another object of one embodiment of the present invention is to provide a learning dataset for predicting characteristics of a semiconductor element.

[0009] Note that the description of these problems does not preclude the existence of other problems. Note that one embodiment of the present invention does not necessarily solve all of these problems. Note that problems other than these will become apparent from the description of the specification, drawings, claims, etc., and it is possible to extract problems other than these from the description of the specification, drawings, claims, etc. [Means for solving the problem]

[0010] One aspect of the present invention is a semiconductor element characteristic prediction system that performs supervised learning based on a learning data set and infers the characteristics of the semiconductor element from prediction data based on the learning result. The semiconductor element characteristic prediction system has a storage unit, an input unit, a processing unit, and a calculation unit, and the processing unit has a function of creating a learning data set from first data stored in the storage unit, a function of creating prediction data from second data supplied from the input unit, a function of converting qualitative data into quantitative data, and a function of extracting or removing the first data and the second data, the first data includes a process list of the first semiconductor element to the mth semiconductor element (m is an integer of 2 or more) and the characteristics of the first semiconductor element to the mth semiconductor element, the second data includes a process list of the m+1th semiconductor element, the qualitative data is the name or composition formula of the material, the quantitative data is the characteristics and composition of the element, and the calculation unit has a function of performing supervised learning and inference.

[0011] In the above-mentioned semiconductor element characteristic prediction system, the characteristic of the element is preferably one or more of atomic number, group, period, electron configuration, atomic weight, atomic radius (covalent bond radius, van der Waals radius, ionic radius, or metallic bond radius), atomic volume, electronegativity, ionization energy, electron affinity, dipole polarizability, melting point of an element, boiling point of an element, lattice constant of an element, density of an element, and thermal conductivity of an element.

[0012] In the above-mentioned system for predicting semiconductor element characteristics, the semiconductor element characteristics are preferably changes over time in ΔVsh obtained in a reliability test (+GBT stress test, +DBT stress test, -GBT stress test, +DGBT stress test, +BGBT stress test, or -BGBT stress test). Alternatively, in the above-mentioned system for predicting semiconductor element characteristics, the semiconductor element characteristics are preferably Id-Vg characteristics or Id-Vd characteristics.

[0013] In the above-described semiconductor device characteristic prediction system, the processing unit preferably has a function of converting the qualitative data into a numerical value using label encoding. Effect of the Invention

[0014] According to one aspect of the present invention, a system for predicting characteristics of a semiconductor device can be provided. According to another aspect of the present invention, a method for predicting characteristics of a semiconductor device can be provided. According to another aspect of the present invention, a learning dataset for predicting characteristics of a semiconductor device can be provided.

[0015] The effects of one embodiment of the present invention are not limited to the effects listed above. The effects listed above do not preclude the existence of other effects. The other effects are effects not mentioned in this section, which will be described below. Effects not mentioned in this section can be derived by a person skilled in the art from descriptions in the specification, drawings, etc., and can be appropriately extracted from these descriptions. One embodiment of the present invention has at least one of the effects listed above and / or other effects. Therefore, one embodiment of the present invention may not have the effects listed above in some cases. [Brief description of the drawings]

[0016] [Figure 1] 1A and 1B are diagrams illustrating an example of a characteristic prediction system for a semiconductor device. [Diagram 2] FIG. 2 is a flowchart showing an example of a method for predicting characteristics of a semiconductor device. [Diagram 3] 3A and 3B are diagrams for explaining the configuration of a neural network. [Figure 4] 4A and 4B are diagrams illustrating the learning data set. [Diagram 5] Fig. 5A is a diagram illustrating the results obtained in a reliability test of a semiconductor element, and Fig. 5B is a diagram illustrating the Id-Vg characteristics of the semiconductor element. [Figure 6]6A to 6C are diagrams for explaining a method for creating input data. [Figure 7] 7A and 7B are diagrams for explaining a method for creating input data. [Figure 8] FIG. 8 is a diagram illustrating a computer device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] The embodiments will be described in detail with reference to the drawings. However, the present invention is not limited to the following description, and it will be easily understood by those skilled in the art that the modes and details of the present invention can be modified in various ways without departing from the spirit and scope of the present invention. Therefore, the present invention should not be interpreted as being limited to the description of the embodiments shown below.

[0018] In the configuration of the invention described below, the same parts or parts having similar functions are denoted by the same reference numerals in different drawings, and the repeated explanations are omitted. In addition, when referring to similar functions, the same hatch pattern may be used and no particular reference numeral may be used.

[0019] In addition, for ease of understanding, the position, size, range, etc. of each component shown in the drawings may not represent the actual position, size, range, etc. Therefore, the disclosed invention is not necessarily limited to the position, size, range, etc. disclosed in the drawings.

[0020] In addition, it should be noted that the ordinal numbers "first," "second," and "third" used in this specification and elsewhere are used to avoid confusion of components and are not intended to limit the numbers.

[0021] (Embodiment 1) In this embodiment, a system for predicting characteristics of a semiconductor element and a method for predicting characteristics of a semiconductor element according to one embodiment of the present invention will be described with reference to FIGS. 1A to 8. FIG.

[0022] A system for predicting characteristics of a semiconductor element according to one embodiment of the present invention is a system capable of predicting characteristics of the semiconductor element based on information about the semiconductor element. Also, a method for predicting characteristics of a semiconductor element according to one embodiment of the present invention is a method for predicting characteristics of a semiconductor element by using machine learning.

[0023] <Semiconductor device characteristic prediction system> Fig. 1A is a diagram showing a configuration of a characteristic prediction system 100. In other words, Fig. 1A can also be said to be an example of the configuration of a characteristic prediction system for a semiconductor element, which is one aspect of the present invention.

[0024] The characteristic prediction system 100 may be provided in an information processing device such as a personal computer used by a user. Alternatively, a processing unit of the characteristic prediction system 100 may be provided in a server, and the system may be accessed and used from a client PC via a network.

[0025] 1A, the characteristic prediction system 100 includes an input unit 101, a processing unit 102, a calculation unit 103, an output unit 104, and a storage unit 105. The input unit 101, the processing unit 102, the calculation unit 103, the output unit 104, and the storage unit 105 may be connected to each other via a transmission path.

[0026] The storage unit 105 stores data on information relating to each of the multiple semiconductor elements. Examples of the information on the semiconductor elements include a process list for the semiconductor elements, characteristics of the semiconductor elements, and information on the shape of the semiconductor elements. Hereinafter, data on the process list for the semiconductor elements may be simply referred to as a process list for the semiconductor elements. Data on the characteristics of the semiconductor elements may be simply referred to as characteristics of the semiconductor elements. Data on information relating to the shape of the semiconductor elements may be simply referred to as information on the shape of the semiconductor elements.

[0027] In the process list for semiconductor devices, a plurality of processes are set in the order of the manufacturing process of the semiconductor devices, and processing conditions are specified for each process.

[0028] The characteristics of the semiconductor element are electrical characteristics of the semiconductor element obtained by actual measurement using a measuring device, the results of a reliability test, etc. The data on the characteristics of the semiconductor element are, for example, measurement data of the electrical characteristics of the semiconductor element, data obtained by performing a reliability test, etc.

[0029] The information on the shape of a semiconductor element includes the position, size, range, etc. of the constituent elements of the semiconductor element. The data on the shape of a semiconductor element includes, for example, numerical data representing the position, size, range, etc. of the constituent elements of the semiconductor element, image data of the semiconductor element and its surroundings, etc. Specifically, the data includes measurement data such as channel length and channel width, observation images obtained by a scanning electron microscope (SEM), observation images obtained by a transmission electron microscope (TEM), etc.

[0030] The storage unit 105 stores at least the process list and characteristics of each of the multiple semiconductor elements. It is preferable that an ID is assigned to each process list of the semiconductor elements stored in the storage unit 105. Here, the ID assigned to the process list of the semiconductor element is referred to as a process list ID. The characteristics of the semiconductor elements stored in the storage unit 105 are associated with the process list ID. In other words, the characteristics of the semiconductor elements may be read and written based on the process list ID.

[0031] The storage unit 105 may store information relating to the shape of each of the plurality of semiconductor elements. In this case, it is preferable that the information relating to the shape of the semiconductor elements stored in the storage unit 105 is associated with a process list ID. In this case, the information relating to the shape of the semiconductor elements may be read and written based on the process list ID.

[0032] The process list for the multiple semiconductor elements and the characteristics of the multiple semiconductor elements are stored in the storage unit 105 via the input unit 101, a storage medium, communication, etc. Information regarding the shapes of the multiple semiconductor elements may also be stored in the storage unit 105 via the input unit 101, a storage medium, communication, etc.

[0033] The process list for the multiple semiconductor elements and the characteristics of the multiple semiconductor elements are preferably stored in the storage unit 105 as text data. In particular, the characteristics of the multiple semiconductor elements are preferably stored in the storage unit 105 as numerical data or two-variable data. In this specification and the like, two-variable data refers to a collection of data relating to two variables. Note that the two-variable data may be a collection of data obtained by extracting data relating to two variables from multi-variable data of three or more variables.

[0034] When the process list for a plurality of semiconductor elements and the characteristics of a plurality of semiconductor elements are image data, they may be stored in storage unit 105 as image data, but it is preferable that the image data is converted into text data before being stored in storage unit 105. Since the data size of text data is smaller than the data size of image data, the load on storage unit 105 can be reduced by converting image data into text data before storing it in storage unit 105.

[0035] The characteristic prediction system 100 may have an optical character recognition (OCR) function. This makes it possible to recognize characters included in image data and create text data. For example, the processing unit 102 may have this function. Alternatively, the characteristic prediction system 100 may further have a character recognition unit having this function.

[0036] The memory unit 105 may have a function of storing a trained model (also called an inference model).

[0037] The input unit 101 has a function for a user to input data IN2. The data IN2 is text data or image data. The input unit 101 may be an input device such as a keyboard, a mouse, a touch sensor, a scanner, or a camera. The data IN2 may be stored in the storage unit 105.

[0038] When data IN2 is image data, the characteristic prediction system 100 has the above-mentioned OCR function, so that it can recognize characters contained in the image data and create text data. For example, when the OCR function is provided in the processing unit 102, data IN2 may remain as image data. Alternatively, when the OCR function is provided in a location other than the processing unit 102 of the characteristic prediction system 100, text data converted from image data may be used as data IN2.

[0039] The processing unit 102 has a function of generating a learning dataset DS from data IN1 supplied from the storage unit 105. The learning dataset DS is a learning dataset for supervised learning. The processing unit 102 also has a function of generating prediction data DI from data IN2 supplied from the input unit 101. The prediction data DI is data for predicting the characteristics of a semiconductor element.

[0040] The data IN1 is a data group used when creating the learning dataset DS. The data group includes some or all of the information related to each of the multiple semiconductor elements stored in the storage unit 105.

[0041] Here, some or all of the multiple semiconductor elements are represented as semiconductor elements 30_1 to 30_m (m is an integer equal to or greater than 2). In this case, the process lists of semiconductor elements 30_1 to 30_m are represented as process lists 10_1 to 10_m, respectively. Furthermore, the characteristics of semiconductor elements 30_1 to 30_m that are actually measured using a measuring device are represented as characteristics 20_1 to 20_m, respectively. In other words, characteristics 20_1 to 20_m are characteristics that are actually measured using a measuring device for the semiconductor elements fabricated according to process lists 10_1 to 10_m, respectively.

[0042] Hereinafter, process lists 10_1 to 10_m may be collectively referred to as a plurality of process lists 10. Furthermore, characteristics 20_1 to 20_m may be collectively referred to as a plurality of characteristics 20. Furthermore, semiconductor elements 30_1 to 30_m may be collectively referred to as a plurality of semiconductor elements 30.

[0043] Data IN1 includes, for example, data of process lists 10_1 to 10_m and data of characteristics 20_1 to 20_m. Data IN1 may also include data on information regarding the shapes of semiconductor elements associated with the process list IDs of each of process lists 10_1 to 10_m. Hereinafter, data of process lists 10_1 to 10_m may be simply referred to as process lists 10_1 to 10_m. Data of characteristics 20_1 to 20_m may be simply referred to as characteristics 20_1 to 20_m.

[0044] Data IN2 is information about a semiconductor element designated by a user for predicting the characteristics of the semiconductor element. Data IN2 includes, for example, a process list designated for predicting the characteristics of the semiconductor element. The process list designated for predicting the characteristics of the semiconductor element is process list 11. Data IN2 may also include information about the shape of the semiconductor element associated with the process list ID of process list 11.

[0045] Moreover, the processing unit 102 has a function of converting qualitative data (also called categorical data, etc.) into numerical values. In other words, the processing unit 102 has a function of converting qualitative data into quantitative data (also called quantitative data, etc.). For example, the processing unit 102 is preferably equipped with label encoding, one-hot encoding, target encoding, etc.

[0046] The qualitative data is included in the data IN1 and the data IN2. The qualitative data includes, for example, data related to the apparatus, data related to the material, etc. The quantification of the qualitative data related to the apparatus and the qualitative data related to the material will be described later.

[0047] The calculation unit 103 has a function of performing machine learning. For example, the calculation unit 103 has a function of performing supervised learning based on the learning dataset DS. The calculation unit 103 also has a function of inferring the characteristics of a semiconductor element from the prediction data DI based on the learning result of the supervised learning. By performing supervised learning as machine learning, it is possible to improve the accuracy of inferring the characteristics of a semiconductor element. Note that a trained model may be generated by performing the supervised learning.

[0048] For the supervised learning, it is preferable to use a neural network (particularly, deep learning). As the deep learning, it is preferable to use, for example, a convolutional neural network (CNN), a recurrent neural network (RNN), an autoencoder (AE), a variational autoencoder (VAE), a random forest, a support vector machine, gradient boosting, generative adversarial networks (GAN), or the like.

[0049] The output of the calculation unit 103 is set as the characteristics of the semiconductor element. In other words, the output of the neural network is set as the characteristics of the semiconductor element. By using the actual measured value as the output of the neural network, the characteristics of the semiconductor element can be predicted by learning the machine learning model and then inputting the process list of any semiconductor element to the neural network.

[0050] In addition, a product-sum operation is performed in a neural network. When the product-sum operation is performed by hardware, it is preferable that the calculation unit 103 has a product-sum operation circuit. As the product-sum operation circuit, a digital circuit or an analog circuit may be used. In addition, the product-sum operation may be performed on software using a program.

[0051] The calculation unit 103 may have a function of performing semi-supervised learning as machine learning. The characteristics of the semiconductor element are given to the learning data as teacher data (also called teacher signal, correct label, etc.), but in order to prepare the teacher data, it is necessary to actually manufacture the semiconductor element and measure the characteristics of the semiconductor element. Compared to supervised learning, semi-supervised learning requires a smaller amount of learning data included in the learning data set, so that inference can be performed while reducing the time spent on creating the learning data.

[0052] The output unit 104 has a function of supplying information. The information is a prediction result of the characteristics of the semiconductor element calculated by the calculation unit 103 or information related to the prediction result. The information is supplied as visual information such as a character string, a numerical value, a graph, etc. The output unit 104 is, for example, an output device such as a display. Note that the characteristic prediction system 100 does not necessarily have to include the output unit 104.

[0053] The above constitutes a semiconductor device characteristic prediction system.

[0054] It should be noted that the characteristic prediction system 100 is not limited to the above configuration. For example, as shown in FIG. 1B, the characteristic prediction system 100 may have a storage unit 106 in addition to the input unit 101, the processing unit 102, the calculation unit 103, the output unit 104, and the memory unit 105.

[0055] The storage unit 106 has a function of storing the trained model generated by the calculation unit 103. By including the storage unit 106 in the characteristic prediction system 100, it is possible to predict the characteristics of a semiconductor element based on the trained model. Therefore, by generating the trained model in advance, it is not necessary to perform supervised learning when predicting the characteristics of a semiconductor element. Therefore, it is possible to reduce the time required to predict the characteristics of a semiconductor element.

[0056] The storage unit 106 is connected to the calculation unit 103 via a transmission line. Note that the storage unit 106 may be connected to each of the input unit 101, the processing unit 102, the output unit 104, and the memory unit 105 via a transmission line.

[0057] The storage unit 106 may be provided within the memory unit 105. The memory unit 105 may also function as the storage unit 106.

[0058] The above is a description of the configuration of the characteristic prediction system 100. By using the semiconductor element characteristic prediction system according to one aspect of the present invention, it is possible to predict the characteristics of a semiconductor element from information relating to the semiconductor element. For example, it is possible to predict the characteristics of a semiconductor element from a process list for the semiconductor element. In addition, for example, it is possible to extract processes that have a large contribution to the characteristics of a semiconductor element from the process list for the semiconductor element.

[0059] <Method for predicting semiconductor device characteristics> Fig. 2 is a flowchart illustrating the flow of processing executed by the characteristic prediction system 100. In other words, Fig. 2 can also be said to be a flowchart illustrating an example of a method for predicting characteristics of a semiconductor element, which is one embodiment of the present invention.

[0060] The method for predicting the characteristics of a semiconductor device includes steps S001 to S007. Steps S001 to S003 are steps related to learning in supervised learning, and steps S004 to S007 are steps related to inference in supervised learning.

[0061] Step S001 is a step of inputting first data into processing unit 102. The first data corresponds to data IN1 described above. That is, the first data includes information on semiconductor elements 30_1 to 30_m. Specifically, the first data includes process lists 10_1 to 10_m and characteristics 20_1 to 20_m. The first data may include information on the shapes of the semiconductor elements associated with the process list IDs of process lists 10_1 to 10_m.

[0062] Step S002 is a process of creating a training dataset from the first data. Step S002 is performed by the processing unit 102 shown in Figures 1A and 1B. The training dataset corresponds to the above-mentioned training dataset DS.

[0063] Step S002 also includes a step of digitizing the qualitative data included in the first data. The qualitative data is, for example, qualitative data related to an apparatus, qualitative data related to a material, etc. The data obtained by digitization is included in the learning dataset.

[0064] Step S003 is a step of performing supervised learning based on the learning data set. Step S003 is performed by the calculation unit 103 shown in FIG. 1A and FIG. 1B. It is preferable to use a neural network (particularly, deep learning) as the algorithm (also called a learning method) of the supervised learning. Note that a trained model for predicting the characteristics of a semiconductor element may be generated by the supervised learning.

[0065] Step S004 is a step of inputting second data into the processing unit 102. The second data corresponds to the above-mentioned data IN2. That is, the second data includes information on the semiconductor element designated by the user for predicting the characteristics of the semiconductor element. Specifically, the second data includes the process list 11.

[0066] When the semiconductor element is produced according to process list 11, the second data may include information regarding the shape of the semiconductor element, characteristics of the semiconductor element, and the like.

[0067] Although step S004 is preferably performed after steps S003 have been performed, it may be performed simultaneously with step S001, or may be performed while steps S001 to S003 are being performed.

[0068] Step S005 is a process of creating prediction data for the characteristics of the semiconductor element from the second data. Step S005 is performed by the processing unit 102 shown in Figures 1A and 1B. That is, the prediction data for the characteristics of the semiconductor element corresponds to the above-mentioned prediction data DI.

[0069] Step S005 also includes a step of digitizing the qualitative data included in the second data. The qualitative data is, for example, qualitative data related to the device, qualitative data related to the material, etc. The data obtained by digitization is included in the prediction data for the characteristics of the semiconductor element.

[0070] Although step S005 is preferably performed after steps S003 have been performed, step S005 may be performed simultaneously with step S001, or may be performed while steps S001 to S003 are being performed.

[0071] Step S006 is a process of inferring the characteristics of the semiconductor element from the prediction data of the characteristics of the semiconductor element based on the learning result of the supervised learning performed in step S003. In other words, step S006 is a process of inferring the characteristics of the semiconductor element from the prediction data of the characteristics of the semiconductor element using the trained model. Step S006 is performed by the calculation unit 103 shown in FIG. 1A and FIG. 1B.

[0072] Step S007 is a step of outputting third data. Step S007 is performed by the output unit 104 shown in Figures 1A and 1B. The third data includes the result of the inference or information related to the result of the inference.

[0073] In this way, the characteristics of the semiconductor device can be predicted. Note that, instead of step S007, a step of storing the result of the above inference or information related to the result of the above inference in the storage unit 105 shown in FIG. 1A or the like may be performed. Alternatively, step S007 may not be performed.

[0074] The steps related to supervised learning (steps S001 to S003) may be performed each time information about the semiconductor element is stored in the memory unit 105, or may be performed periodically at a predetermined timing (for example, once a day or once a week).

[0075] The method for predicting the characteristics of a semiconductor element is not limited to the above method. For example, the method for predicting the characteristics of a semiconductor element may include, after step S003, a step of storing the trained model generated in step S003. The trained model is stored in the storage unit 106 shown in FIG. 1B. By generating the trained model in advance, steps S001 to S003 can be omitted when predicting the characteristics of a semiconductor element. Therefore, the time required to predict the characteristics of a semiconductor element can be shortened.

[0076] <<Neural Networks>> Here, we will explain neural networks that can be used for supervised learning.

[0077] As shown in FIG. 3A, the neural network NN can be configured with an input layer IL, an output layer OL, and a hidden layer HL. The input layer IL, the output layer OL, and the hidden layer HL each have one or more neurons (units). The hidden layer HL may be one layer or two or more layers. A neural network having two or more hidden layers HL can also be called a deep neural network (DNN). Learning using a deep neural network can also be called deep learning.

[0078] Input data is input to each neuron in the input layer IL. An output signal from a neuron in the previous or next layer is input to each neuron in the hidden layer HL. An output signal from a neuron in the previous layer is input to each neuron in the output layer OL. Each neuron may be connected to all neurons in the previous or next layer (fully connected), or may be connected to only a portion of the neurons.

[0079] FIG. 3B shows an example of a computation by a neuron. Here, neuron N and two neurons in the previous layer that output signals to neuron N are shown. Neuron N receives the output x 1 and the output of the other neuron in the previous layer, x 2 is input. Then, in neuron N, the output is x 1 and weight w 1 The multiplication result (x 1 w 1 ) and output x 2 and weight w 2 The multiplication result (x 2 w 2 ) x 1 w 1 +x 2 w 2 After is calculated, a bias b is added if necessary to get the value a=x 1 w 1 +x 2 w 2+b is obtained. The value a is then transformed by the activation function h, and an output signal y=ah is output from the neuron N. As the activation function h, for example, a sigmoid function, a tanh function, a softmax function, a ReLU function, a threshold function, etc. can be used.

[0080] In this way, the operations performed by neurons include summing the products of the outputs of neurons in the previous layer and the weights, that is, multiplication and addition operations (x 1 w 1 +x 2 w 2 ). This product-sum operation may be performed on software using a program, or may be performed by hardware. When the product-sum operation is performed by hardware, a product-sum operation circuit may be used. As this product-sum operation circuit, a digital circuit or an analog circuit may be used. When an analog circuit is used for the product-sum operation circuit, it is possible to reduce the circuit scale of the product-sum operation circuit or the number of accesses to memory, thereby improving the processing speed and reducing power consumption.

[0081] The product-sum circuit may be formed using transistors including silicon (such as single crystal silicon) in a channel formation region (hereinafter also referred to as Si transistors) or transistors including an oxide semiconductor in a channel formation region (hereinafter also referred to as OS transistors). In particular, OS transistors have an extremely small off-state current and are therefore suitable as transistors that constitute the analog memory of the product-sum circuit. Note that the product-sum circuit may be formed using both Si transistors and OS transistors.

[0082] When the product-sum calculation is performed by hardware, the product-sum calculation circuit may be included in the calculation unit 103 of the characteristic prediction system 100 .

[0083] The above is a description of the neural network. In one embodiment of the present invention, it is preferable to use deep learning. In other words, it is preferable to use a neural network having two or more hidden layers HL.

[0084] The above is a description of one example of a method for predicting the characteristics of a semiconductor device.

[0085] <Details of the method for predicting the characteristics of semiconductor elements> The method for predicting the characteristics of a semiconductor device will be described in detail below with reference to FIGS. 4A to 7B.

[0086] <<Structure of semiconductor element>> First, the structure of a semiconductor element will be described. Here, a transistor will be described as an example of the semiconductor element.

[0087] Transistors are classified into various types according to the positional relationship and shape of the components. For example, transistor structures are classified into bottom-gate type structures and top-gate type structures according to the positional relationship between the substrate, gate, and channel formation region. A transistor structure in which the gate is provided between the channel formation region and the substrate is called a bottom-gate type structure. On the other hand, a transistor structure in which the channel formation region is provided between the gate and the substrate is called a top-gate type structure.

[0088] Furthermore, transistor structures are classified into bottom-contact and top-contact structures according to the connection points between the source and drain and the semiconductor layer forming the channel. A transistor structure in which the source and drain and the semiconductor layer forming the channel are connected on the substrate side is called a bottom-contact structure. A transistor structure in which the source and drain and the semiconductor layer forming the channel are connected on the opposite side to the substrate is called a top-contact structure.

[0089] That is, the transistor structures are classified into a BGBC (bottom gate bottom contact) type structure, a BGTC (bottom gate top contact) type structure, a TGTC (top gate top contact) type structure, and a TGBC (top gate bottom contact) type structure.

[0090] In addition to the four structures mentioned above, other transistor structures include a dual-gate structure in which the gates are located both above and below the semiconductor layer, and a Top-Gate Self-Align (TGSA) structure in which the source and drain are self-aligned to the gate pattern.

[0091] The structures of the semiconductor elements 30_1 to 30_m are preferably the same or similar. For example, when the semiconductor elements 30_1 to 30_m are transistors, the structures of the semiconductor elements 30_1 to 30_m are preferably BGBC type structure, BGTC type structure, TGTC type structure, TGBC type structure, dual gate type structure, or TGSA type structure. By making the structures of the semiconductor elements the same, it is possible to improve the prediction accuracy of the characteristics of the semiconductor elements.

[0092] The structures of the semiconductor elements 30_1 to 30_m may be different. When the semiconductor elements 30_1 to 30_m are transistors, for example, a part of the structure of the semiconductor elements 30_1 to 30_m may be a TGTC type structure, and the rest may be a TGSA type structure. By combining a plurality of structures, it becomes possible to predict the characteristics of the semiconductor elements with high versatility.

[0093] The above is a description of the structure of the semiconductor element.

[0094] <<Characteristics of semiconductor elements>> Next, the characteristics of the semiconductor element will be described.

[0095] In this specification and the like, the characteristics of a semiconductor element refer to the electrical characteristics of the semiconductor element. Examples of the characteristics of a semiconductor element include drain current (Id)-gate voltage (Vg) characteristics, drain current (Id)-drain voltage (Vd) characteristics, capacitance (C)-gate voltage (V) characteristics, and the like.

[0096] The characteristics of the semiconductor element may be the results obtained by a reliability test, such as the change over time of the on-current (Ion) (also referred to as the stress time dependency of Ion), the change over time of ΔVsh (also referred to as the stress time dependency of ΔVsh), etc.

[0097] ΔVsh is the amount of change in the shift voltage (Vsh), which is defined as the Vg at which the tangent to the maximum slope of the drain current (Id)-gate voltage (Vg) curve of a transistor intersects with the line Id=1 pA.

[0098] Reliability tests include +GBT (Gate Bias Temperature) stress tests, +DBT (Drain Bias Temperature) stress tests, -GBT stress tests, +DGBT (Drain Gate Bias Temperature) stress tests, +BGBT (Back Gate Bias Temperature) stress tests, and -BGBT stress tests.

[0099] Since a reliability test may require a long measurement time, it takes time to obtain the results of the reliability test. Furthermore, the measurement device is occupied during the measurement period. In this regard, the results of the reliability test can be predicted by using a semiconductor element characteristic prediction system according to one embodiment of the present invention. Therefore, by determining whether or not to perform a reliability test based on the predicted result, it is possible to omit part of the reliability test. Alternatively, the priority order of the reliability tests can be determined. This allows the measurement device to be used effectively.

[0100] In this specification and the like, the characteristics of a semiconductor element also include characteristic values ​​calculated from the measurement results of the electrical characteristics of the semiconductor element. Examples of the characteristic values ​​include threshold voltage (Vth), Vsh, subthreshold swing value (S value), Ion, and field effect mobility (μFE). Here, the subthreshold swing value (S value) refers to the amount of change in gate voltage in the subthreshold region that changes the drain current by one order of magnitude with a constant drain voltage. Hereinafter, the characteristic values ​​calculated from the measurement results of the electrical characteristics of a semiconductor element may be referred to as the characteristic values ​​of the semiconductor element, or simply as the characteristic values.

[0101] The characteristics of a semiconductor element also include temperature characteristics. Examples of the temperature characteristics include temperature characteristics of a threshold voltage and temperature dependence of capacitance characteristics. Temperature characteristics need to be measured at a plurality of different temperatures, and therefore it takes time to evaluate the temperature characteristics. By using the characteristic prediction system for a semiconductor element according to one embodiment of the present invention, it is possible to predict the temperature characteristics without manufacturing the semiconductor element and performing measurements to evaluate the temperature characteristics.

[0102] When the characteristics of the semiconductor element are characteristic values, the characteristics of the semiconductor element are stored as numerical data in storage unit 105. When the characteristics of the semiconductor element are electrical characteristics or temperature characteristics, the characteristics of the semiconductor element are stored as two-variable data in storage unit 105. In other words, the characteristics of the semiconductor element stored in storage unit 105 are quantified.

[0103] For example, when the characteristic of the semiconductor element is a change over time in ΔVsh obtained in a reliability test, a collection of data relating to time and ΔVsh is stored in the storage unit 105. Also, when the characteristic of the semiconductor element is an Id-Vg characteristic, a collection of data relating to Vg and Id is stored in the storage unit 105.

[0104] The above is a description of the characteristics of the semiconductor element.

[0105] <<Learning Data Set>> Here, we will explain the training dataset for supervised learning.

[0106] 4A and 4B are diagrams showing the configuration of a training dataset 50. The training dataset 50 corresponds to the training dataset DS generated by the processing unit 102. The training dataset 50 has training data 51_1 to training data 51_m. Training data 51_i (i is an integer between 1 and m) has input data 52_i and teacher data 53_i. The training data 51_i includes information related to the semiconductor element 30_i.

[0107] The learning dataset 50 is generated from data IN1 input to the processing unit 102 shown in Figures 1A and 1B. Therefore, the learning dataset 50 is generated by extracting, processing, converting, selecting, removing, or the like from the data included in the data IN1.

[0108] In this embodiment, the teaching data is information about the semiconductor element, which is the characteristics of the semiconductor element. That is, the target of prediction in this embodiment is the characteristics of the semiconductor element.

[0109] In addition, in this embodiment, the input data is preferably created from a process list of a semiconductor element, among the information related to the semiconductor device. In other words, the input data preferably includes a part of the process list of a semiconductor element, among the information related to the semiconductor device. The characteristics of the semiconductor element to be predicted are affected by the type of semiconductor material used in the layer in which the channel is formed, the type of conductive material used in the layer that functions as a gate electrode, the type of insulating material used in the layer that functions as a gate insulating film, the film thickness of each of these layers, the film formation conditions of each of these layers, etc. Note that the type of material used in the layers, the film thickness of the layers, the film formation conditions of the layers, etc. are included in the process list of the semiconductor element. Therefore, the input data is preferably created from the process list of the semiconductor element.

[0110] The data included in the training dataset for supervised learning is preferably quantitative data. In other words, the data is preferably quantified. Compared to a case where the training dataset includes non-numeric data (qualitative data), the data included in the training dataset is quantified, which can prevent the machine learning model from becoming complicated.

[0111] 4A, input data 52_1 to input data 52_m are generated from process lists 10_1 to 10_m, respectively. Moreover, training data 53_1 to training data 53_m are generated from characteristics 20_1 to 20_m, respectively.

[0112] 4B, the input data 52_1 to 52_m may be generated from the process lists 10_1 to 10_m and information on the shapes of the semiconductor elements 30_1 to 30_m, respectively. By adding information on the shapes of the semiconductor elements 30_1 to 30_m to the input data 52_1 to 52_m, respectively, it is possible to improve the prediction accuracy of the characteristics of the semiconductor elements.

[0113] It is preferable that the number of steps in each of the process lists 10_1 to 10_m is the same. This makes it easier to create a learning data set or prediction data. When creating a learning data set or prediction data, the process lists are selected. For example, a part of the process list is extracted, or another part of the process list is removed. Therefore, the number of steps in each of the process lists 10_1 to 10_m may be different.

[0114] As described above, the characteristics 20_1 to 20_m are digitized data, and therefore can be included in the teacher data 53_1 to 53_m, respectively, without any particular conversion.

[0115] When the characteristics 20_1 to 20_m are two-variable data, one or more characteristic points may be extracted from the two-variable data and included in the teacher data 53_1 to 53_m, respectively. Also, multiple points may be extracted from the two-variable data so that the values ​​of one of the two variables are equally spaced, and included in the teacher data 53_1 to 53_m, respectively.

[0116] Fig. 5A is a diagram for explaining the results obtained in a reliability test of a semiconductor element. In Fig. 5A, the horizontal axis is the elapsed time (also called stress time) [h] from the start of measurement, and the vertical axis is ΔVsh [mV]. For example, the values ​​of ΔVsh from time A1 to time A10 and at time A1 to time A10 may be extracted and used as training data.

[0117] Note that some or all of the times A1 to A10 may have a characteristic value of ΔVsh. Alternatively, the times A1 to A10 may be equally spaced. Alternatively, some of the times A1 to A10 may be a first interval, and the remaining times A1 to A10 may be a second interval different from the first interval.

[0118] Furthermore, the number of sets of extracted times and values ​​of ΔVsh at those times is not limited to 10, but may be 1 to 9 or 11 or more.

[0119] FIG. 5B is a diagram illustrating the Id-Vg characteristic of a semiconductor element. In the Id-Vg curve, the value of the drain current when the gate voltage is 0V is one of the characteristic points. For example, the gate voltage is set to voltage B4. Voltages B1 to B3 are specified as voltages lower than voltage B4. Voltages B5 to B10 are specified as voltages higher than voltage B4. For example, voltages B1 to B10 and the values ​​of the drain current at voltages B1 to B10 may be extracted and used as teacher data. Alternatively, one of voltages B1 to B10 excluding voltage B4 may be set to 0V.

[0120] Furthermore, the number of pairs of extracted voltages and values ​​of drain currents at those voltages is not limited to 10, but may be 1 to 9 or 11 or more.

[0121] <<How to create input data>> Here, a method for generating the input data 52_1 to 52_m shown in FIG. 4A will be described.

[0122] First, a method for creating the input data 52_1 will be described. Here, an example in which the input data 52_1 is created from the process list 10_1 will be described with reference to Figs. 6A to 6C.

[0123] In the process list, a plurality of processes are set in the order of the process of manufacturing the semiconductor device, such as film formation, cleaning, resist coating, exposure, development, processing, heat treatment, inspection, and substrate transfer.

[0124] Further, processing conditions are specified for each of the multiple processes set in the process list. For example, processing conditions for a film formation process include an apparatus, a material, a film thickness, a temperature, a pressure, an electric power, a flow rate, and the like. Note that the processing conditions for the film formation process may affect the characteristics of a semiconductor element. Furthermore, even in processes other than film formation, the processing conditions, the presence or absence of a process, the order of processes, and the like may affect the characteristics of a semiconductor element.

[0125] The processing conditions are a mixture of qualitative and quantitative data, and are expressed in various scales. In order to express the similarity of the features in each process, for example, the qualitative data on materials can be converted into quantitative data such as the physical properties of each material, and the set of the data can be used as the features.

[0126] Here, it is assumed that the process list 10_1 has n processes (n is an integer of 2 or more). For example, in the process list 10_1 shown in Fig. 6A, the first process is a substrate transfer process, the jth process (j is an integer of 2 or more and (n-4) or less) is a film formation process, the (j+1)th process is a processing process, the (j+2)th process is a film formation process, the (j+3)th process is a heat treatment process, and the nth process is a substrate transfer process. Note that No. shown in Figs. 6A and 6B is the process number.

[0127] The process conditions specified in the jth process (film formation process) are condition 1 to condition p (p is an integer equal to or greater than 1). The process conditions specified in the (j+1)th process (processing process) are condition 1 to condition q (q is an integer equal to or greater than 1). The process conditions specified in the (j+2)th process (film formation process) are condition 1 to condition r (r is an integer equal to or greater than 2). The process conditions specified in the (j+3)th process (heat treatment process) are condition 1 to condition s (s is an integer equal to or greater than 1).

[0128] First, some processes are extracted from the n processes included in the process list 10_1. The extracted processes are, for example, processes that are estimated to have a large contribution from the characteristics of semiconductor elements. Also, for example, processes that have many changes in conditions. By extracting some of the processes included in the process list 10_1, the number of parameters in machine learning can be reduced. In other words, the number of neurons included in the input layer in supervised learning using a neural network can be reduced. This optimizes the number of hidden layers and the number of neurons in the hidden layers, and reduces the amount of calculation or calculation time for learning or inference. In addition, overlearning may be prevented.

[0129] For example, if the process conditions specified in the jth process (film formation process) are often changed among the process lists 10_1 to 10_m, the jth process (film formation process) may be extracted from the process list 10_1. Also, if it is estimated that the (j+3)th process (heat treatment process) is highly influenced by the characteristics of the semiconductor element, the (j+3)th process (heat treatment process) may be extracted from the process list 10_1.

[0130] Alternatively, some of the processes different from the above may be removed from the n processes included in the process list 10_1. The processes to be removed are, for example, processes that are estimated to have a small contribution from the semiconductor characteristics. Also, for example, processes whose processing conditions have not been changed. By removing some of the processes different from the above, the number of parameters in machine learning can be reduced. In other words, the number of neurons included in the input layer in supervised learning using a neural network can be reduced. This optimizes the number of layers in the hidden layer and the number of neurons in the hidden layer, thereby reducing the amount of calculation or calculation time for learning or inference. In addition, overlearning may be prevented in some cases.

[0131] For example, it is estimated that the substrate transfer process (the first process and the nth process) does not affect the characteristics of the semiconductor element. Therefore, it is advisable to remove the substrate transfer process (the first process and the nth process) from the process list 10_1. Also, for example, if the processing conditions specified in the (j+1)th process (processing process) and the processing conditions specified in the (j+2)th process (film formation process) are the same among the process lists 10_1 to 10_m, it is advisable to remove the (j+1)th process (processing process) and the (j+2)th process (film formation process) from the process list 10_1.

[0132] As a result, some processes are extracted from the process list 10_1. Alternatively, some processes different from the above are removed from the process list 10_1. FIG. 6B shows an example in which the j-th process, the (j+3)-th process, etc. are extracted. Note that the example shown in FIG. 6B also applies to a case in which the 1st process, the (j+1)-th process, the (j+2)-th process, the n-th process, etc. are removed.

[0133] Next, data of processing conditions included in the process list 10_1 from which some processes have been extracted, or in the process list 10_1 from which some processes different from the extracted some processes have been removed, are quantified.

[0134] As described above, for example, the process conditions of the film forming process include the apparatus, material, film thickness, temperature, pressure, power, flow rate, etc. Since the film thickness, temperature, pressure, power, flow rate, etc. are set as values, these process conditions are digitized data. Therefore, these process conditions can be included in the input data 52_1 without any special conversion.

[0135] It is preferable that the units of the set values ​​of the processing conditions are the same. By standardizing the units, the amount of data included in the learning dataset 50 can be reduced. Therefore, the time spent on data transmission / reception, learning, inference, etc. can be reduced.

[0136] Equipment data may be included in the process list as qualitative data, such as the name of the equipment (including abbreviations and names), the method used by the equipment, etc.

[0137] Furthermore, data on materials may be included in the process list as qualitative data, such as the name of the material (including abbreviations and names), composition formula, and the like.

[0138] As described above, it is preferable that the data included in the learning data set used in supervised learning is quantified, and therefore it is preferable to quantify the qualitative data included in the process list.

[0139] [Quantification of qualitative data on the device] Here, the digitization of qualitative data related to the equipment will be described. Note that the description will be given using an example in which the name of the equipment is input as qualitative data related to the equipment in the condition 1 of the film formation process.

[0140] Film formation equipment includes equipment capable of forming films using the chemical vapor deposition (CVD) method (sometimes called CVD equipment), equipment capable of forming films using the sputtering method (sometimes called sputtering equipment), and equipment capable of forming films using the atomic layer deposition (ALD) method (sometimes called ALD equipment).

[0141] CVD methods can be classified into plasma enhanced CVD (PECVD), which uses plasma, thermal CVD (TCVD), which uses heat, and photo CVD (Photo CVD), which uses light. Therefore, in CVD methods, the CVD equipment may differ depending on the technique. In other words, there may be multiple CVD equipment available. The same applies to sputtering equipment, ALD equipment, etc.

[0142] The data related to the equipment (here, the equipment name) input as the processing conditions is qualitative data. Therefore, it is preferable to use label encoding to digitize the qualitative data related to the equipment. For example, it is good to manage the equipment name by ID. It is good to assign an ID different from the process list ID to each equipment name. Here, the ID assigned to the equipment name is referred to as the equipment ID.

[0143] 7A illustrates an example of a correspondence table between device names and device IDs. For example, if the device name is CVD1, the device ID is 1. If the device name is CVD2, the device ID is 2. If the device name is SP1, the device ID is 3. By converting the device name into a device ID, the device name can be treated as numerical data.

[0144] The correspondence table may be stored in the storage unit 105. In addition, every time an available device is increased, a new device name and a device ID associated with the new device name may be added to the correspondence table via the input unit 101, a storage medium, communication, or the like.

[0145] Although the method of digitizing the qualitative data related to the device using Label Encoding has been described, the method of digitizing the qualitative data related to the device is not limited to this. One-hot Encoding (also called 1 of K Encoding) may be used to digitize the qualitative data related to the device.

[0146] For example, if the number of devices that can be used in a film formation process is t (t is an integer equal to or greater than 1), the device names can be expressed as a t-dimensional one-hot vector. If the number of devices that can be used in each process is not large, they can be expressed as a low-dimensional vector. This makes it possible to reduce the amount of calculation or time required for learning or inference.

[0147] Further, as a method for converting qualitative data relating to a device into a numerical value, other methods such as Target Encoding may be used.

[0148] The above is an explanation of how to convert qualitative data related to the device into numerical values.

[0149] [Quantification of qualitative data on materials] Here, the quantification of qualitative data related to a material will be described. An example will be described in which the name of a material (including an abbreviation, a name, etc.) is input as qualitative data related to the material in the condition 2 of the film formation process. The material is an inorganic material.

[0150] The crystal structure, film quality, etc. of materials used in semiconductor elements change depending on processing conditions. Furthermore, they also change depending on the material used as the film to be formed and the roughness of the surface to be formed. Therefore, when using a database or the like to convert the name of the material, which is qualitative data, into the physical properties of the material, which are quantitative data (crystal structure, density, dielectric constant, etc.), there is a risk that the prediction accuracy of the characteristics of the semiconductor element will decrease. Therefore, in this embodiment, the qualitative data on the material (here, the name of the material) is converted into the constituent elements and composition.

[0151] First, convert the name of the material into a composition formula. For example, if "silicon oxide" is entered as condition 2 of the film formation process, convert it into "SiO 2 The conversion from the material name to the composition formula may be performed using a concept dictionary or a database, or a correspondence table between the material name and the composition formula that has been created in advance may be used.

[0152] Next, the composition formula is converted into the constituent elements and composition. For example, if the material is composed of element M1, element M2, element M3, and element M4, and has a composition of M1:M2:M3:M4=w:x:y:z, the composition formula is converted into "M1, M2, M3, M4, w:x:y:z" or "M1, w, M2, x, M3, y, M4, z".

[0153] It is preferable to standardize the composition. For example, the composition may be standardized so that w+x+y+z=1 is satisfied. This makes it possible to distinguish between materials that have the same combination of constituent elements but different compositions.

[0154] If a material is composed of one element, M2, M3, M4, x, y, and z should be written as zero. Similarly, if a material is composed of two elements, M3, M4, y, and z should be written as zero. If a material is composed of three elements, M4 and z should be written as zero.

[0155] Specifically, the composition formula is "SiO 2 ", convert it to "Si, O, 0, 0, 0.333:0.667:0:0" or "Si, 0.333, O, 0.667, 0, 0, 0, 0".

[0156] In the above, the number and composition of elements are described so as to be applicable to materials having four or less kinds of constituent elements, but this is not limited thereto. For example, the number and composition of elements may be described so as to be applicable to materials having five or more kinds of constituent elements. Alternatively, for example, when the constituent elements of a material used in a semiconductor device are three or less kinds, the composition formula may be converted to "M1, M2, M3, w:x:y" or "M1, w, M2, x, M3, y". This can reduce the number of parameters in machine learning. This optimizes the number of layers in the hidden layer and the number of neurons in the hidden layer, and can reduce the amount of calculation or calculation time of learning or inference.

[0157] Next, the element is converted into its properties, such as atomic number, group, period, electron configuration, atomic weight, atomic radius, atomic volume, electronegativity, ionization energy, electron affinity, dipole polarizability, melting point of an element, boiling point of an element, lattice constant of an element, density of an element, thermal conductivity of an element, etc. The atomic radius may be one or more selected from the covalent bond radius, van der Waals radius, ionic radius, and metallic bond radius.

[0158] In particular, it is preferable to select the atomic number or electron configuration and electronegativity as the characteristics of the element to be converted. When a material is composed of a single element, the characteristics of the material are likely to be expressed in the atomic number and electronegativity. When a material is composed of two or more elements, the electronegativity is likely to be expressed in the bonding style between different elements. For example, between elements with similar electronegativity, covalent bonding or metallic bonding is dominant. On the other hand, between elements with greatly different electronegativity, ionic bonding is dominant.

[0159] Fig. 7B illustrates an example of a correspondence table between elements and their properties. In Fig. 7B, the properties of elements include atomic number, electron configuration, electronegativity, melting point (K) of a simple substance, etc. Conversion from an element to its properties may be performed using a database or a correspondence table between elements and their properties that has been created in advance.

[0160] Specifically, when selecting atomic number and electronegativity as the properties of an element, "Si" is converted to "14, 1.90" and "O" is converted to "8, 3.44".

[0161] As a result of the above, "silicon oxide" input as condition 2 for the film formation process can be converted to "14, 1.90, 8, 3.44, 0, 0, 0, 0, 0.333:0.667:0:0" or "14, 1.90, 0.333, 8, 3.44, 0.667, 0, 0, 0, 0, 0, 0." Therefore, qualitative data regarding materials can be quantified.

[0162] From the above, it is possible to predict the characteristics of semiconductor elements from first principles. Furthermore, even if a material that has never been used before is used in the semiconductor element, it is possible to predict the characteristics of the semiconductor element without reducing accuracy. Furthermore, even if a material that is not listed in a database or the like is used in the semiconductor element, it is possible to predict the characteristics of the semiconductor element without reducing accuracy.

[0163] The name of the material may be converted directly into the constituent elements and composition without going through the composition formula.

[0164] This concludes the explanation of how to convert qualitative data related to materials into numerical values.

[0165] As a result, input data 52_1 consisting of digitized data as shown in Fig. 6C can be created. Specifically, the input data 52_1 includes data on the processing conditions shown in Fig. 6C. The input data 52_1 may also include a process number.

[0166] The order of the process of selecting (extracting or removing) the process list and the process of converting qualitative data into quantitative data is not limited to the above. For example, input data 52_1 may be created from process list 10_1 by selecting (extracting or removing) the process list after converting qualitative data into quantitative data.

[0167] In this manner, the learning data 51_1 including digitized data can be generated. The learning data 51_2 to 51_m have the same configuration as the learning data 51_1. That is, the learning data 51_2 to 51_m can be generated by the above method.

[0168] 4A shows a case where the input data 52_1 to the input data 52_m are generated from the process lists 10_1 to 10_m, respectively, but is not limited to this. For example, as shown in FIG. 4B, the input data 52_1 to the input data 52_m may be generated from the process lists 10_1 to 10_m and information on the shapes of the semiconductor elements 30_1 to 30_m, respectively.

[0169] In addition, input data 52_1 to input data 52_m may be created from process lists 10_1 to 10_m and first characteristics of semiconductor elements 30_1 to 30_m, respectively, and teacher data 53_1 to teacher data 53_m may be created from second characteristics of semiconductor elements 30_1 to 30_m, respectively.

[0170] In the above, the first characteristic and the second characteristic are different. For example, the first characteristic may be a characteristic value of the semiconductor element, and the second characteristic may be a result of a reliability test of the semiconductor element. There are many factors that affect the reliability of the semiconductor element, and each factor is intricately intertwined, making it difficult to predict based on experience. Therefore, the reliability of the semiconductor element is suitable as a subject to be estimated. In addition, the characteristic value of the semiconductor element indirectly includes information such as the manufacturing process of the semiconductor element. Therefore, by adding the characteristic value of the semiconductor element to the input data, the information is provided to supervised learning, and the accuracy of prediction of the characteristics of the semiconductor element can be improved.

[0171] The learning dataset 50 may be composed of only data of semiconductor elements having the same or similar structure. In other words, the learning dataset 50 may be created for each structure of the semiconductor element. This can improve the accuracy of prediction of the characteristics of the semiconductor element. The learning dataset 50 may also be composed of data of semiconductor elements regardless of their structure. This allows for highly versatile prediction of the characteristics of the semiconductor element.

[0172] This concludes the explanation of the learning dataset. By training a machine learning model using input data and training data, it is possible to predict the characteristics of semiconductor devices.

[0173] <<Data for predicting the characteristics of semiconductor elements>> Here, the prediction data for the characteristics of the semiconductor element will be described.

[0174] The prediction data for the characteristics of the semiconductor element is generated from the data IN2 input to the processing unit 102 shown in Figures 1A and 1B. Therefore, the prediction data for the characteristics of the semiconductor element is generated by extracting, processing, converting, selecting, removing, etc., the data included in the data IN2.

[0175] The data IN2 includes at least information related to the semiconductor device, and may also include characteristics of the semiconductor device.

[0176] The prediction data of the semiconductor element characteristics may have the same configuration as the input data of the learning data described above. For example, when the input data 52_1 to 52_m are generated from the process lists 10_1 to 10_m, respectively, the prediction data of the semiconductor element characteristics may be generated from the process list 11. Also, when the input data 52_1 to 52_m are generated from the process lists 10_1 to 10_m, respectively, and the characteristics of the semiconductor elements 30_1 to 30_m, the prediction data of the semiconductor element characteristics may be generated from the process list 11 and the characteristics of the semiconductor elements associated with the process list ID of the process list 11.

[0177] The above is an explanation of the prediction data for the characteristics of the semiconductor device.

[0178] According to one embodiment of the present invention, the characteristics of a semiconductor element can be predicted without using the physical properties of materials contained in the semiconductor element. In addition, by using past experimental data, the optimization of the structure of a semiconductor element can be accelerated by virtual screening. Even if a person views the data and finds it to be not interpolative, it may be possible to consider it to be interpolative due to the nonlinear or high-order expression of the machine learning model. In addition, by cutting out and examining the expression obtained by the machine learning model in fragments, it is possible to learn rules that were not previously noticed.

[0179] <Computer equipment> In this section, a computer device having a semiconductor element characteristic prediction system according to one embodiment of the present invention will be described with reference to FIG.

[0180] 8 is a diagram illustrating a computer device having a semiconductor element characteristic prediction system. The computer device 1000 has an arithmetic unit 1001, a memory 1002, an input / output interface 1003, a communication device 1004, and a storage 1005. The computer device 1000 is electrically connected to a display device 1006a and a keyboard 1006b via the input / output interface 1003.

[0181] The computer device 1000 may be an information processing device such as a personal computer used by a user. In this case, the arithmetic device 1001 includes the processing unit 102 and the arithmetic unit 103 shown in Fig. 1A and Fig. 1B. The storage 1005 includes the memory unit 105 and / or the storage unit 106 shown in Fig. 1A and Fig. 1B. The display device 1006a corresponds to the output unit 104 shown in Fig. 1A and Fig. 1B. The keyboard 1006b corresponds to the input unit 101 shown in Fig. 1A and Fig. 1B.

[0182] The trained model may be stored in memory 1002 or in storage 1005.

[0183] The computer device 1000 may also be connected to a database 1011, a remote computer 1012, and a remote computer 1013 via a network. The computer device 1000 is electrically connected to a network interface 1007 via a communication device 1004. The network interface 1007 is also electrically connected to the database 1011, the remote computer 1012, and the remote computer 1013 via a network.

[0184] Here, the above network includes a local area network (LAN) and the Internet. The above network can use either one or both of wired and wireless communication. When wireless communication is used in the above network, various communication means can be used, such as short-range communication means such as Wi-Fi (registered trademark) and Bluetooth (registered trademark), communication means conforming to the third generation mobile communication system (3G), communication means conforming to LTE (sometimes called 3.9G), communication means conforming to the fourth generation mobile communication system (4G), or communication means conforming to the fifth generation mobile communication system (5G).

[0185] As described above, the processing unit of the semiconductor device characteristic prediction system may be provided in a server, and the server may be accessed and used by a client PC via a network. For example, the computer device 1000 may be regarded as the client PC, and the remote computer 1012 and / or the remote computer 1013 may be regarded as the server.

[0186] In this case, the processing unit 102 and the calculation unit 103 shown in Fig. 1A and Fig. 1B are provided in the remote computer 1012 and / or the remote computer 1013. That is, the calculation device of the remote computer 1012 and / or the remote computer 1013 includes the processing unit 102 and the calculation unit 103. In addition, the database 1011 includes the memory unit 105 and / or the storage unit 106 shown in Fig. 1A and Fig. 1B.

[0187] As described above, one aspect of the present invention can provide a system for predicting characteristics of a semiconductor element. Another aspect of the present invention can provide a method for predicting characteristics of a semiconductor element. Another aspect of the present invention can provide a learning dataset for predicting characteristics of a semiconductor element.

[0188] This embodiment can be carried out by combining parts thereof as appropriate. [Explanation of symbols]

[0189] IN1: data, IN2: data, 10: multiple process lists, 10_m: process list, 10_1: process list, 11: process list, 20: multiple characteristics, 20_m: characteristics, 20_1: characteristics, 30: multiple semiconductor elements, 30_i: semiconductor element, 30_m: semiconductor element, 30_1: semiconductor element, 50: learning data set, 51_i: learning data, 51_m: learning data, 51_1: learning data, 51_2: learning data, 52_i: input data, 52_m: input data, 52_1: input data, 53_i: teacher data, 53_m : Teacher data, 53_1: Teacher data, 100: Property prediction system, 101: Input unit, 102: Processing unit, 103: Calculation unit, 104: Output unit, 105: Memory unit, 106: Storage unit, 1000: Computer device, 1001: Calculation device, 1002: Memory, 1003: Input / output interface, 1004: Communication device, 1005: Storage, 1006a: Display device, 1006b: Keyboard, 1007: Network interface, 1011: Database, 1012: Remote computer, 1013: Remote computer

Claims

1. A system for predicting semiconductor device characteristics, comprising: performing supervised learning based on a learning data set; and, based on a result of the learning, inferring characteristics of the semiconductor device from prediction data, the system comprising: The semiconductor device characteristic prediction system includes a storage unit, an input unit, a processing unit, and a calculation unit, The processing unit has a function of creating the learning data set from the first data stored in the storage unit, a function of creating the prediction data from the second data supplied from the input unit, a function of converting qualitative data into quantitative data, and a function of extracting or removing from the first data and the second data, the first data includes m sets (m is an integer of 2 or more) of a process list for a first semiconductor element and characteristics of the first semiconductor element manufactured in accordance with the process list for the first semiconductor element; the second data includes a process list for a second semiconductor device; The qualitative data is the name or composition formula of the material; The quantitative data is elemental properties and composition; The calculation unit has a function of performing learning and inference of the supervised learning. A system for predicting semiconductor device characteristics.

2. In claim 1, The properties of the element are one or more of the atomic number, group, period, electron configuration, atomic weight, atomic radius, atomic volume, electronegativity, ionization energy, electron affinity, dipole polarizability, melting point of the element, boiling point of the element, lattice constant of the element, density of the element, and thermal conductivity of the element. A system for predicting semiconductor device characteristics.

3. In claim 2, The atomic radius is one of a covalent radius, a van der Waals radius, an ionic radius, or a metallic radius; A system for predicting semiconductor device characteristics.

4. In any one of claims 1 to 3, The characteristic of the semiconductor element is a change over time in ΔVsh obtained in any one of a +GBT stress test, a +DBT stress test, a −GBT stress test, a +DGBT stress test, a +BGBT stress test, and a −BGBT stress test. A system for predicting semiconductor device characteristics.

5. In any one of claims 1 to 3, The characteristic of the semiconductor element is an Id-Vg characteristic or an Id-Vd characteristic. A system for predicting semiconductor device characteristics.

6. In any one of claims 1 to 5, The processing unit has a function of converting the qualitative data into a numerical value using Label Encoding. A system for predicting semiconductor device characteristics.

Images