Information processing system and information processing method

Abstract

To provide a novel information processing system and an information processing method that are excellent in convenience, usefulness, and reliability.SOLUTION: In the information processing system having a first component, a second component, and a third component, the first component 30 receives a sentence TXT written in a natural language and an inquiry sentence QUE for retrieving a design asset and delivers the sentences to the third component 21, and provides a code Code_1 and emphasizes a part related to the code to provide a design asset DAST. The second component 20 generates an intermediate code IntC_1 from the text according to an instruction text PT_1 and passes it to the third component. The third component classifies the sentences into predetermined classes, generates an instruction sentence, passes it to the second component, uses the passed intermediate code as an argument according to the syntax, generates a code from the instruction, and passes it to the first component.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] One aspect of the present invention relates to an information processing system and an information processing method.

[0002] Note that one embodiment of the present invention is not limited to the above technical field. The technical field of one embodiment of the invention disclosed in this specification relates to an object, a method, or a manufacturing method. Alternatively, one embodiment of the present invention relates to a process, a machine, a manufacture, or a composition of matter. Therefore, more specifically, examples of the technical field of one embodiment of the present invention disclosed in this specification include a semiconductor device, a display device, a light-emitting device, a power storage device, a memory device, a driving method thereof, or a manufacturing method thereof. [Background technology]

[0003] In recent years, the development of language models using neural networks has been actively carried out, and large-scale language models (LLMs) in particular have attracted attention. Large-scale language models are natural language processing models trained using large amounts of data. The large-scale language model can realize a dialogue model that responds to user instructions, for example. Non-Patent Document 1 discloses GPT-4 (Generative Pre-trained Transformer 4) (registered trademark) as a large-scale language model, and ChatGPT as a dialogue model.

[0004] The capabilities of natural language processing models have increased dramatically through the use of large-scale language models. However, due to the size of language models, it is difficult to incorporate and operate language models on one's own in terms of equipment and costs. Therefore, one way of using language models is to use external services that provide language models. [Prior art documents] [Non-patent literature]

[0005] [Non-Patent Document 1] Summary of ChatGPT / GPT-4 Research and Perspective Towards the Future of Large Language Models, Yiheng Liu et al. (Submitted on 4 Apr 2023, [online], Internet<URL:https: / / arxiv.org / abs / 2304.01852> Summary of the Invention [Problem to be solved by the invention]

[0006] An object of one embodiment of the present invention is to provide a novel information processing system with excellent convenience, usefulness, or reliability.An object of one embodiment of the present invention is to provide a novel information processing method with excellent convenience, usefulness, or reliability.Another object of the present invention is to provide a novel information processing system, a novel information processing method, or a novel semiconductor device.

[0007] 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]

[0008] (1) One aspect of the present invention is an information processing system having a first component, a second component, and a third component.

[0009] The first component has a function of receiving a sentence written in a natural language and a query sentence for searching a design asset, and transferring the sentence and the query sentence to the third component. The first component also has a function of providing code, and a function of providing the design asset with highlighting a portion related to the code.

[0010] The second component has a function to perform processing using a large-scale language model, and also has a function to generate intermediate code from the text according to the directives and pass it to the third component.

[0011] The third component has a function of performing processing using a large-scale language model, and the third component has a function of classifying a sentence into a predetermined class. When the sentence is classified into one class, the third component has a function of generating an instruction sentence and passing it to the second component. The instruction sentence includes the sentence and a template sentence.

[0012] The third component has a function of performing processing using the first database.

[0013] The first database includes a first record, and the first record includes an instruction, a syntax associated with the instruction, a template associated with the instruction, and a class associated with the instruction. The template includes a first instruction for analyzing a sentence and extracting predetermined information, a second instruction for converting the extracted information into an intermediate code using a conversion rule, and the conversion rule.

[0014] The first database also has a function of responding to a query specifying a class with a command, a syntax, and a template sentence.

[0015] The third component has a function of using the intermediate code passed to it as an argument according to the syntax to generate code from instructions and pass it to the first component.

[0016] The third component has a function of performing processing using the second database, and the second database has a function of responding to a query with the design assets. Also, the third component has a function of transferring the design assets to the first component.

[0017] (2) Also, according to one aspect of the present invention, there is provided the information processing system, wherein the query statement includes a design specification. The second database includes a second record, and the second record includes a design asset and a design specification associated with the design asset.

[0018] This allows a user to operate the software using a sentence written in a natural language. Furthermore, a user can operate the software even if the user is not familiar with the operation. Furthermore, a user can operate the software without referring to an operation manual. Furthermore, a user can generate code related to the operation using a sentence written in a natural language. Furthermore, a user can use a programming language using a sentence written in a natural language. Furthermore, a circuit design asset can be searched, and parts related to the code can be highlighted and provided to the user. Furthermore, a user can refer to the circuit design asset. Furthermore, even an inexperienced user can use a design tool that is designed for a user with a high level of specialized knowledge. As a result, a novel information processing system that is excellent in convenience, usefulness, and reliability can be provided.

[0019] (3) Moreover, one aspect of the present invention is the information processing system described above, wherein the second component has a function of generating a message requesting supplemental information in accordance with the instruction text and passing the message to the third component.

[0020] The third component has a function of passing the message to the first component when the message is received. The template text also includes a third instruction for generating a message when the information cannot be sufficiently extracted.

[0021] The first component also has a function of providing a message when it receives the message, and a function of providing design assets by highlighting parts related to the command.

[0022] (4) Moreover, one aspect of the present invention is the information processing system described above, wherein the first component has a function of receiving the supplemental text and transferring the supplemental text to the third component.

[0023] In addition, the third component has a function of adding supplementary text to the text, updating the instruction text, and passing the instruction text to the second component.

[0024] This allows the user to supplement and correct the text by using the supplemental text written in natural language. The user can also supplement and correct the operation of the software. The user can also supplement and correct the operation of the software even if the user is not familiar with the operation. The user can also supplement and correct the operation of the software without referring to the operation manual. The user can also supplement and correct the code related to the operation by using the supplemental text written in natural language. The user can also supplement and correct the description of the programming language by using the supplemental text written in natural language. The design assets of the circuit can be searched, and the part related to the command can be highlighted and provided to the user. The user can also refer to the design assets of the circuit. The design tool created for users with high level of specialized knowledge can be used even by users with little experience. As a result, a novel information processing system excellent in convenience, usefulness, and reliability can be provided.

[0025] (5) Another embodiment of the present invention is an information processing method having first to eighth steps.

[0026] In the first step, the first component accepts a sentence and a query statement for searching an engineering resource, and passes the sentence and the query statement to the second component.

[0027] In the second step, the second component queries the first database using the query statement to obtain the design assets, and passes the design assets to the first component.

[0028] In the third step, the second component uses a large-scale language model to classify the sentences into predefined classes.

[0029] In a fourth step, when the sentence is classified into a class, the second component queries the second database by specifying the class to obtain the command, the syntax, and the template sentence, where the second database includes records including the command, the syntax associated with the command, the template sentence associated with the command, and the class associated with the command.

[0030] In a fifth step, the second component generates an instruction statement and passes it to the third component. The instruction statement includes a sentence and a template sentence, and the template sentence includes a first instruction for analyzing the sentence and extracting predetermined information, a second instruction for converting the extracted information into an intermediate code using a conversion rule, and the conversion rule.

[0031] In the sixth step, the third component generates an intermediate code from the sentence using a large-scale language model according to the instruction sentence, and passes it to the second component.

[0032] In the seventh step, the second component generates code and passes it to the first component, where the code includes an instruction that uses the intermediate code passed to the first component as an argument according to the syntax.

[0033] In the eighth step, the first component provides code and design assets with relevant parts of the code highlighted.

[0034] This allows a user to operate the software using a sentence written in a natural language. Furthermore, a user can operate the software even if the user is not familiar with the operation. Furthermore, a user can operate the software without referring to an operation manual. Furthermore, a user can generate code related to the operation using a sentence written in a natural language. Furthermore, a user can use a programming language using a sentence written in a natural language. Furthermore, a circuit design asset can be searched, and a part related to the code can be highlighted and provided to the user. Furthermore, a user can refer to the circuit design asset. Furthermore, even an inexperienced user can use a design tool that is designed for a user with a high level of specialized knowledge. As a result, a novel information processing method that is excellent in convenience, usefulness, and reliability can be provided.

[0035] (6) Another embodiment of the present invention is an information processing method including first to fourteenth steps.

[0036] In the first step, the first component accepts a sentence and a query statement for searching an engineering resource, and passes the sentence and the query statement to the second component.

[0037] In the second step, the second component queries the first database using the query statement to obtain the design assets, and passes the design assets to the first component.

[0038] In the third step, the second component uses a large-scale language model to classify the sentences into predefined classes.

[0039] In a fourth step, when the sentence is classified into a class, the second component queries the second database by specifying the class to obtain the command, the syntax, and the template sentence, where the second database includes records including the command, the syntax associated with the command, the template sentence associated with the command, and the class associated with the command.

[0040] In the fifth step, the second component generates an instruction sentence and passes it to the third component. The instruction sentence includes a sentence and a template sentence, and the template sentence includes a first instruction for analyzing the sentence and extracting predetermined information, a second instruction for converting the extracted information into an intermediate code using a conversion rule, and a third instruction for generating a message requesting supplemental information when the information cannot be sufficiently extracted and passing it to the second component.

[0041] In the sixth step, the third component generates an intermediate code from the sentence using a large-scale language model according to the instruction sentence, and passes it to the second component.

[0042] If sufficient information cannot be extracted in the seventh step, proceed to the eighth step; otherwise, proceed to the thirteenth step.

[0043] In the eighth step, the third component generates a message requesting supplemental information according to the instruction text and passes it to the second component.

[0044] In the ninth step, the second component passes the message to the first component.

[0045] In the tenth step, the first component provides the message and the design assets in which the parts relevant to the instruction are highlighted, and waits for input of supplemental text.

[0046] In an eleventh step, the first component accepts the supplemental text and passes the supplemental text to the second component.

[0047] In the twelfth step, the second component adds supplementary text to the text, updates the instruction text, and proceeds to the sixth step.

[0048] In a thirteenth step, the second component generates code and passes it to the first component, where the code includes an instruction that uses the intermediate code passed to the first component as an argument according to the syntax.

[0049] In a fourteenth step, the first component provides code and design assets with relevant portions of the code highlighted.

[0050] This allows the user to supplement and correct the text by using the supplemental text written in natural language. The user can also supplement and correct the operation of the software. The user can also supplement and correct the operation of the software even if the user is not familiar with the operation. The user can also supplement and correct the operation of the software without referring to the operation manual. The user can also supplement and correct the code related to the operation by using the supplemental text written in natural language. The user can also supplement and correct the description of the programming language by using the supplemental text written in natural language. The design assets of the circuit can be searched, and the part related to the command can be highlighted and provided to the user. The user can also refer to the design assets of the circuit. The design tool created for users with high level of specialized knowledge can be used even by users with little experience. As a result, a novel information processing method excellent in convenience, usefulness, and reliability can be provided.

[0051] In the drawings accompanying this specification, components are classified by function and shown in block diagrams as independent blocks; however, in actuality, it is difficult to completely separate components by function, and one component may be involved in multiple functions. Effect of the Invention

[0052] According to one aspect of the present invention, a novel information processing system having excellent convenience, usefulness, or reliability can be provided. Also, one aspect of the present invention can provide a novel information processing method having excellent convenience, usefulness, or reliability. Also, a novel information processing system can be provided. Also, a novel information processing method can be provided.

[0053] Note that the description of these effects does not preclude the existence of other effects. Note that one embodiment of the present invention does not necessarily have all of these effects. Note that effects other than these will become apparent from the description in the specification, drawings, claims, etc., and it is possible to extract effects other than these from the description in the specification, drawings, claims, etc. [Brief description of the drawings]

[0054] [Figure 1] FIG. 1 is a diagram illustrating a configuration of an information processing system according to an embodiment. [Diagram 2] 2(A) and 2(B) are diagrams illustrating a configuration of an information processing system according to an embodiment. [Diagram 3] 3A to 3C are diagrams illustrating a configuration of an information processing system according to an embodiment. [Figure 4] FIG. 4 is a diagram illustrating a configuration of an information processing system according to an embodiment. [Diagram 5] 5(A) and 5(B) are diagrams illustrating a configuration of an information processing system according to an embodiment. [Figure 6] FIG. 6 is a diagram illustrating a configuration of an information processing system according to an embodiment. [Figure 7]FIG. 7 is a diagram illustrating an information processing method according to an embodiment. [Figure 8] FIG. 8 is a diagram illustrating an information processing method according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0055] An information processing system according to an embodiment of the present invention includes a first component, a second component, and a third component. The first component has a function of receiving a sentence written in a natural language and a query for searching an engineering asset, and transferring the sentence and the query to the third component. The first component also has a function of providing code, and a function of providing the engineering asset by highlighting a portion related to the code. The second component has a function of performing processing using a large-scale language model, and a function of generating intermediate code from the sentence according to a directive, and transferring the intermediate code to the third component. The third component has a function of performing processing using a large-scale language model, and a function of classifying the sentence into a predetermined class. When the sentence is classified into one class, the third component has a function of generating a directive, and transferring the intermediate code to the second component. The instruction includes a sentence and a template sentence, and the third component has a function of performing processing using a first database, and the first database has a first record, and the first record includes an instruction, a syntax associated with the instruction, a template sentence associated with the instruction, and a class associated with the instruction. The template sentence includes a first instruction for analyzing the sentence and extracting predetermined information, a second instruction for converting the extracted information into an intermediate code using a conversion rule, and the conversion rule. The first database has a function of responding to a query specifying a class with the instruction, the syntax, and the template sentence, and the third component has a function of using the intermediate code passed to an argument according to the syntax to generate code from the instruction and pass it to the first component. The third component has a function of performing processing using a second database, and the second database has a function of responding to a query with a design asset, and the third component has a function of passing the design asset to the first component.

[0056] This allows a user to operate the software using a sentence written in a natural language. Furthermore, a user can operate the software even if the user is not familiar with the operation. Furthermore, a user can operate the software without referring to an operation manual. Furthermore, a user can generate code related to the operation using a sentence written in a natural language. Furthermore, a user can use a programming language using a sentence written in a natural language. Furthermore, a circuit design asset can be searched, and parts related to the code can be highlighted and provided to the user. Furthermore, a user can refer to the circuit design asset. Furthermore, even an inexperienced user can use a design tool that is designed for a user with a high level of specialized knowledge. As a result, a novel information processing system that is excellent in convenience, usefulness, and reliability can be provided.

[0057] 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 is easily understood by those skilled in the art that the form 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 is not interpreted as being limited to the description of the embodiments shown below. In the configuration of the invention described below, the same reference numerals are used in common between different drawings for the same parts or parts having similar functions, and repeated explanations are omitted.

[0058] (Embodiment 1) In this embodiment, an information processing system of one embodiment of the present invention will be described with reference to FIGS.

[0059] FIG. 1 is a diagram illustrating a configuration of an information processing system according to an embodiment of the present invention.

[0060] 2(A) and 2(B) are schematic diagrams illustrating the configuration of a database used by the information processing system of one embodiment of the present invention.

[0061] Figure 3(A) is a schematic diagram illustrating the structure of an instruction statement used by an information processing system of one embodiment of the present invention, Figure 3(B) is a schematic diagram illustrating the structure of code generated by an information processing system of one embodiment of the present invention, and Figure 3(C) is a schematic diagram illustrating a state in which an information processing system of one embodiment of the present invention provides design assets.

[0062] FIG. 4 is a schematic diagram illustrating the function of an information processing system according to an embodiment of the present invention.

[0063] FIG. 5(A) is a schematic diagram illustrating the configuration of an instruction statement used by an information processing system of one embodiment of the present invention, and FIG. 5(B) is a schematic diagram illustrating the state in which an information processing system of one embodiment of the present invention provides design assets.

[0064] <Information processing system configuration example 1> The information processing system described in this embodiment includes a component 30, a component 20, and a component 21 (see FIG. 1).

[0065] Component 30 Configuration Example 1 The component 30 has a function of accepting a document TXT written in a natural language and a query statement QUE for searching a design asset DAST, and transferring the document TXT and the query statement QUE to the component 21. For example, a user of the information processing system inputs the document TXT and the query statement QUE to the component 30. Also, the component 30 can transfer the document TXT and the query statement QUE to the component 21 via a network 51 (see FIG. 1).

[0066] The component 30 has a function of providing the code Code_1 and a function of providing the design asset DAST, for example, to a user of an information processing system, with the portion related to the code Code_1 highlighted (see FIG. 3(C)). Specifically, the component 30 has a function of displaying the design asset DAST with the portion related to the code Code_1 underlined or highlighted.

[0067] Component 20 Configuration Example 1 The component 20 has a function of performing processing using a large language model (LLM). For example, the component 20 can perform processing using a BERT (Bidirectional Encoder Representations from Transformers) language model. In addition, the component 20 can perform processing using, for example, GPT-3, GPT-3.5, GPT-4, LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), Llama2, ALBERT, XLNet, etc.

[0068] Specifically, the component 20 has a function of generating an intermediate code IntC_1 from the document TXT in accordance with the directive PT_1, and transferring the intermediate code IntC_1 to the component 21. For example, the intermediate code IntC_1 can be transferred to the component 21 via a network 51 (see FIG. 1).

[0069] The details of the operation will be described later, but the component 21 generates intermediate code IntC_1 “{”power_ring”: [”VDD”, “GND”], ”layers”: [”M1”, ”M2”], ”line_width”: ”5”}” from the text TXT in accordance with the directive PT_1 illustrated in the next paragraph.

[0070] " Analyze the following sentence and convert it according to the rules. The sentence conversion rules are as follows: #Conversion rules Rule 1. The power rings are X1, X2, and X3. => {”power_ring”: [X1, X2, X3]} Rule 2. The layers are X1, X2, and X3. => {”layers”: [X1, X2, X3]} Rule 3. The width of the line is X. => {”line_width”: X} #text Make a power ring for VDD and GND. Use layers M1 and M2. The width of the wiring is 5μm. "

[0071] Component 21 Configuration Example 1 The component 21 has a function of performing processing using a large-scale language model. For example, the component 21 has a function of classifying a given text TXT into a predetermined class.

[0072] For example, a list of dictionaries containing elements that are paired with classes and the definitions of those classes is prepared. Then, the list of dictionaries, an instruction "Analyze the following sentence and select the class with the closest meaning from the list of dictionaries," and the text TXT are given to the component 21. This allows the text TXT to be classified into a predetermined class.

[0073] For example, a dictionary-type list can be used that includes an element paired with class CL_1 and "Place a power ring," an element paired with class CL_2 and "Create a floor plan," and an element paired with class CL_3 and "Create a clock tree."

[0074] In addition, when the above dictionary-type list, the above instruction, and the text TXT "Create a power ring for VDD and GND. Use layers M1 and M2." are given to component 21, component 21 classifies the text TXT into class CL_1.

[0075] For example, by using an instruction such as "Analyze the following sentence and select three classes from a dictionary-type list in order of semantic similarity," it is possible to prioritize multiple classes as candidates.

[0076] When the document TXT is classified into the class CL_1, the component 21 has a function of generating an instruction sentence PT_1 and transferring it to the component 20. For example, the component 21 can transfer the instruction sentence PT_1 to the component 20 via the network 51 (see FIG. 1).

[0077] [Example of directive PT_1] The instruction text PT_1 includes a text TXT and a template text Tmpl_1 (see FIG. 3(A)). The template text Tmpl_1 can be acquired from a database DB1, which will be described later.

[0078] Component 21 Configuration Example 2 The component 21 has a function of performing processing using the database DB1.

[0079] [Database DB1 configuration example 1] The database DB1 includes one or more records. For example, the database DB1 includes record ID1_1 to record ID1_n (see FIG. 2A).

[0080] Record ID1_1 includes a command Cmd_1, a syntax Synt_1 associated with the command Cmd_1, a template Tmpl_1 associated with the command Cmd_1, and a class CL_1 associated with the command Cmd_1. Note that code Code_1 provided by an information processing system according to an embodiment of the present invention is written in a programming language including the command Cmd_1.

[0081] <Command Cmd_1> For example, "createRing" can be used as the command Cmd_1. Note that "createRing" is a command for placing a power ring. The command Cmd_1 is included in the programming language used for the code Code_1 provided by the information processing system of one embodiment of the present invention.

[0082] 〈Synt_1〉 The command Cmd_1 has an associated syntax Synt_1, and the command Cmd_1 is constructed according to the syntax Synt_1.

[0083] For example, the command "createRing" is associated with the syntax "-net ${power_ring} -layers ${layers} -line_width ${line_width}". Note that "-net" is an item that specifies the name of the wiring to be created as a power ring. Also, "-layers" is an item that specifies the name of the layer to be used to create the wiring. "-line_width" is an item that specifies the width of the wiring.

[0084] <Example 1 of template text Tmpl_1> The template text Tmpl_1 includes an instruction Instr_1 for analyzing the text TXT and extracting predetermined information INF_1, an instruction Instr_2 for converting the extracted information INF_1 into intermediate code IntC_1 using a conversion rule CnvR_1, and the conversion rule CnvR_1 (see FIG. 3(A)). Note that ext() in the figure indicates the process of extracting predetermined information, and CnvR_1(INF_1) in the figure indicates the process of converting the information INF_1 into intermediate code IntC_1 using the conversion rule CnvR_1.

[0085] For example, "Analyze the following sentence, convert it according to the rules, and write it out in JSON format. The sentence conversion rules are as follows." can be used for the instruction Instr_1 and the instruction Instr_2.

[0086] Also, for example, " Rule 1. The power rings are X1, X2, and X3. => {”power_ring”: [X1, X2, X3]} Rule 2. The layers are X1, X2, and X3. => {”layers”: [X1, X2, X3]} Rule 3. The width of the line is X. => {”line_width”: X} " can be used for the conversion rule CnvR_1.

[0087] The conversion rule CnvR_1 includes a function to identify and extract information on the wiring name, information on the layer, and information on the wiring width. In other words, the conversion rule CnvR_1 can be used as a means to identify information INF_1 written in the document TXT, extract the information INF_1 from the document TXT, and convert it into intermediate code IntC_1.

[0088] Furthermore, data in which items and values ​​corresponding to those items are stored can be used for the intermediate code IntC_1. Any data format can be used as long as it can store keys and values. For example, data written in JavaScript Object Notation (abbreviated as JSON) format can be used for the intermediate code IntC_1.

[0089] <Class CL_1> A programming language defines various "commands." The function of each "command" can be explained using natural language. Furthermore, the explanation written in natural language can be classified using a large-scale language model. Then, by classifying the explanation into one class, the "command" corresponding to the explanation can be classified into the class. For example, when the explanation written in natural language for the command Cmd_1 is classified into the class CL_1 using the large-scale language model, the command Cmd_1 can be classified into the class CL_1.

[0090] Furthermore, when a text TXT written in a natural language is classified into a predetermined class, the text TXT is highly likely to include a "command" classified into the class. For example, when the text TXT is classified into class CL_1, the received text TXT is highly likely to be a description related to command Cmd_1. In other words, by classifying command Cmd_1 into class CL_1 in advance, the received text TXT can be associated with command Cmd_1 using class CL_1 as a medium.

[0091] The received text TXT can also be directly associated with the command Cmd_1. For example, a dictionary-type list including elements that are paired with commands and their definitions can be prepared, and the dictionary-type list, an instruction "Analyze the following sentence and select the command with the closest meaning from the dictionary-type list," and the text TXT can be provided to the component 21 to associate the text TXT with a specific command. Also, the text TXT can be associated with a specific command by using a semantic search, vector search, or the like.

[0092] [Database DB1 configuration example 2] Furthermore, the database DB1 has the function of responding to a query specifying a class CL_1 with a command Cmd_1, a syntax Synt_1, and a template text Tmpl_1.

[0093] Component 21 Configuration Example 3 The component 21 has a function of using the intermediate code IntC_1 passed thereto as an argument in accordance with the syntax Synt_1 to generate a code Code_1 from a command Cmd_1 and passing the code Code_1 to the component 30.

[0094] For example, the component 21 converts the intermediate code IntC_1 illustrated in the next paragraph into an argument "-net {VDD GND} -layers {M1 M2} -line_width 5" by processing the intermediate code IntC_1 according to the syntax Synt_1.

[0095] “{”power_ring”: [”VDD”, ”GND”], ”layers”: [”M1”, ”M2”], ”line_width”: ”5”}”

[0096] Furthermore, component 21 combines command Cmd_1 and arguments to generate code Code_1 "createRing -net {VDD GND} -layers {M1 M2} -line_width 5." The code Code_1 is a code that creates a power ring using VDD and GND as the wiring names, M1 and M2 as the layers, and a wiring width of 5 μm.

[0097] Component 21 Configuration Example 4 The component 21 has a function of performing processing using the database DB2, and has a function of transferring the design asset DAST to the component 30.

[0098] [Database DB2 configuration example] The database DB2 includes one or more records. For example, a code created by a user of the information processing system according to an embodiment of the present invention can be used as a design asset. Also, a code created by an organization to which a user of the information processing system according to an embodiment of the present invention belongs can be used as a design asset.

[0099] Specifically, a setting file for an Electronic Design Automation (EDA) tool can be used as a design asset, as well as a script file that causes the EDA tool to perform a specific operation.

[0100] The database DB2 includes records ID2_1 to ID2_n (see FIG. 2(B)). For example, record ID2_1 includes design asset DAST and design specification SPEC_1 associated with the design asset DAST. When an EDA tool setting file is used for the record, the record includes, for example, the design specifications of a semiconductor device designed using the EDA tool. Specifically, the design specifications may include the type of semiconductor device, technology node, chip area, operating voltage, operating frequency, and bus width. Note that a central processing unit or a storage device may be used for the type of semiconductor device.

[0101] For example, when a query statement QUE includes a design specification SPEC_1, the database DB2 has a function of responding to the query statement QUE with a design asset DAST. For example, by specifying the type of semiconductor device, technology node, chip area, operating voltage, operating frequency, and bus width and querying the design asset DAST, it is possible to call up code previously created by a user of the information processing system. It is also possible to call up code created by an organization to which the user of the information processing system belongs.

[0102] This allows the user to operate the software using the text TXT written in a natural language. The user can operate the software even if he or she is not familiar with the operation. The user can operate the software without referring to the operation manual. The user can generate the code Code_1 related to the operation using the text TXT written in a natural language. The user can use the programming language using the text TXT written in a natural language. The circuit design asset DAST can be searched, and the part related to the code Code_1 can be highlighted and provided to the user. The user can refer to the circuit design asset DAST. The design tool created for users with advanced expertise can be used even by users with little experience. As a result, a novel information processing system with excellent convenience, usefulness, and reliability can be provided.

[0103] <Configuration example 2 of information processing system> In addition, the information processing system described in this embodiment using Figure 4 etc. has a part of its configuration different from that of the information processing system described using Figure 1 etc. Here, the different parts will be described in detail, and the above description will be used for parts having the same configuration.

[0104] Component 20 Configuration Example 2 The component 20 has a function of generating a message MSG requesting the supplementation of the information INF_1 according to the instruction PT_1 and passing it to the component 21 (see FIG. 4). For example, the component 20 can generate a message MSG requesting the supplementation of missing information.

[0105] Component 21 Configuration Example 5 The component 21 has a function of passing a message MSG to the component 30 when the component 21 receives the message MSG.

[0106] [Database DB1 Configuration Example 3] Furthermore, the component 21 can use a database having a different configuration from the above example of the information processing system for the database DB1. For example, a template text having a different configuration can be used for the template text Tmpl_1.

[0107] <Example 2 of template text Tmpl_1> The template text Tmpl_1 includes an instruction Instr_3 for generating a message MSG requesting supplementation of the information INF_1 when the information INF_1 cannot be sufficiently extracted (see FIG. 5(A)).

[0108] For example, "Analyze the following sentence and convert it according to the rules. The sentence conversion rules are as follows. Also, if any conversion rules were not applied, generate a message requesting the user to supplement the missing information." can be used for instruction Instr_1, instruction Instr_2, and instruction Instr_3.

[0109] Specifically, if the information INF_1 extracted from the text TXT lacks information regarding the width of the wiring, a large-scale language model can be used to cause component 20 to generate a message MSG stating, "The width of the wiring must be specified."

[0110] Component 21 Configuration Example 6 Furthermore, the component 21 has a function of adding the supplemental text SPL_1 to the text TXT, updating the instruction text PT_1, and transferring the instruction text PT_1 to the component 20. For example, the component 21 can transfer the updated instruction text PT_1 to the component 20 via the network 51 (see FIG. 4).

[0111] Component 30 Configuration Example 2 The component 30 has a function of providing the message MSG to a system user when the component 30 receives the message MSG (see FIG. 4). The component 30 also has a function of providing the design asset DAST with emphasis on the portion related to the command Cmd_1 (see FIG. 5(B)). The system user can supplement, for example, the information INF_1 by referring to the portion of the design asset DAST related to the command Cmd_1.

[0112] Furthermore, the component 30 has a function of receiving the supplemental text SPL_1 and transferring the supplemental text SPL_1 to the component 21. For example, the supplemental text SPL_1 can be transferred to the component 21 via a network 51 (see FIG. 4).

[0113] This allows the user to supplement and correct the text TXT using the supplemental text SPL_1 written in natural language. The user can also supplement and correct the operation of the software. The user can also supplement and correct the operation of the software even if the user is not familiar with the operation. The user can also supplement and correct the operation of the software without referring to the operation manual. The user can also supplement and correct the code Code_1 related to the operation using the supplemental text SPL_1 written in natural language. The user can also supplement and correct the description of the programming language using the supplemental text SPL_1 written in natural language. The design asset DAST of the circuit can be searched, and the part related to the command Cmd_1 can be highlighted and provided to the user. The user can also refer to the design asset DAST of the circuit. The design tool created for users with high level of expertise can be used even by users with little experience. As a result, a novel information processing system with excellent convenience, usefulness, or reliability can be provided.

[0114] <Configuration example 3 of information processing system> The information processing system described in this embodiment includes a component 30, a component 21, and a component 20 (see FIGS. 1 and 4).

[0115] For example, an information processing system according to an embodiment of the present invention can be configured with an information processing device that performs the functions of component 30, an information processing device that performs the functions of component 21, and an information processing device that performs the functions of component 20. The number of information processing devices that configure the information processing system according to an embodiment of the present invention is one or more. Also, for example, a plurality of information processing devices can be connected using a network 51 to configure the information processing system according to an embodiment of the present invention.

[0116] When an information processing system according to one embodiment of the present invention is configured using a plurality of information processing devices, the load related to information processing can be distributed.

[0117] "Configuration example 1 of information processing device" The information processing device according to the first exemplary configuration can be used as the component 30. The information processing device according to the first exemplary configuration can be called a client computer. For example, a desktop computer can be used as the component 30.

[0118] The information processing device configuration example 1 can receive data input by a user of the information processing system according to an embodiment of the present invention. Also, the information processing device configuration example 1 can provide the user with data output by the information processing system according to an embodiment of the present invention.

[0119] For example, a dedicated application software or a web browser is operated. A user of the information processing system according to an embodiment of the present invention can access the information processing system via either of them. This allows the user to enjoy services using the information processing system according to an embodiment of the present invention.

[0120] "Configuration example 2 of information processing device" The second configuration example of the information processing device described in this embodiment can be used for the component 21. For example, a workstation, a server computer, a supercomputer, or the like can be used for the component 21.

[0121] Moreover, the information processing device in the configuration example 2 preferably has a function as a parallel computer. By using the information processing device as a parallel computer, for example, it is possible to perform large-scale calculations necessary for learning and inference of artificial intelligence (AI).

[0122] Moreover, the configuration example 2 of the information processing device can perform processing using a natural language processing model using AI.

[0123] For example, it is possible to perform natural language processing using natural language models such as BERT (Bidirectional Encoder Representations from Transformers), T5 (Text-to-Text Transfer Transformer), GPT-3, GPT-3.5, GPT-4, LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), and Llama2.

[0124] "Configuration example 3 of information processing device" For example, the configuration example 3 of the information processing device described in this embodiment can be used for the component 20. Note that the component 20 is larger in scale and has higher calculation capacity than the component 21. For example, a large computer such as a server computer or a supercomputer can be used for the component 20.

[0125] Moreover, it is preferable that the information processing device in configuration example 3 has a function as a parallel computer. By using it as a parallel computer, for example, it is possible to perform large-scale calculations necessary for AI learning and inference.

[0126] Moreover, the configuration example 3 of the information processing device can perform processing using a natural language processing model using AI. In particular, it can execute processing using a general-purpose language processing model that can perform various natural language processing tasks.

[0127] For example, processing (Natural Language Processing) using natural language models such as BERT (Bidirectional Encoder Representations from Transformers), T5 (Text-to-Text Transfer Transformer), GPT-3, GPT-3.5, GPT-4, LaMDA (Language Model for Dialogue Applications), PaLM (Pathways Language Model), and Llama2 can be performed. In particular, it is preferable to be able to perform processing using GPT-4. For example, if processing can be performed using a large-scale language model that is larger than conventional natural language models, more natural sentence generation or dialogue can be realized.

[0128] Note that a person who provides a service using the information processing system according to one embodiment of the present invention does not necessarily need to own the information processing device of configuration example 3. For example, a service provider can use a part of a service provided by another business operator or the like using the information processing device of configuration example 3.

[0129] <Network 51 configuration example> A network 51 that can be used in the information processing system according to one embodiment of the present invention can connect multiple information processing devices. This allows the multiple connected information processing devices to transmit and receive data to and from each other. In addition, the load related to information processing can be distributed.

[0130] When performing wireless communication, communication standards such as the fourth generation mobile communication system (4G), the fifth generation mobile communication system (5G), and the sixth generation mobile communication system (6G), or specifications standardized by IEEE such as Wi-Fi (registered trademark) and Bluetooth (registered trademark), can be used as communication protocols or communication technologies.

[0131] For example, a local network can be used for the network 51. Also, an intranet or an extranet can be used for the network 51. Also, a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a global area network (GAN), or the like can be used for the network 51.

[0132] Also, for example, a global network can be used for the network 51. Specifically, the Internet, which is the basis of the World Wide Web (WWW), can be used.

[0133] Furthermore, a person who provides a service using an information processing system according to an embodiment of the present invention can provide the service using an information processing method according to an embodiment of the present invention via a network 51, for example.

[0134] When the information processing system according to an embodiment of the present invention is constructed within a local network, the possibility of confidential information leaks can be reduced, for example, compared to when the information processing system uses the Internet.

[0135] "Configuration Example 4 of Information Processing Device" An information processing device that can be used in an information processing system according to one embodiment of the present invention includes, for example, an input unit 110, a storage unit 120, a processing unit 130, an output unit 140, and a transmission path 150 (see FIG. 6).

[0136] In the drawings attached to this specification, the components are classified by function and shown as independent blocks in the block diagram, but in reality, it is difficult to completely separate the components by function, and one component may be involved in multiple functions. For example, a part of the processing unit 130 may function as the input unit 110. Also, one function may be involved in multiple components. For example, the processing performed by the processing unit 130 may be executed by different servers depending on the processing.

[0137] [Input section 110] The input unit 110 can receive data from outside the information processing device. For example, the input unit 110 receives data via a network 51.

[0138] The input unit 110 supplies the received data to one or both of the storage unit 120 and the processing unit 130 via a transmission path 150 .

[0139] [Storage section 120] The storage unit 120 has a function of storing a program executed by the processing unit 130. The storage unit 120 may also have a function of storing data generated by the processing unit 130 (e.g., calculation results, analysis results, inference results), data accepted by the input unit 110, and the like.

[0140] The storage unit 120 may have a database. Furthermore, the information processing device may have a database separate from the storage unit 120. The information processing device may have a function of retrieving data from a database that exists outside the storage unit 120, outside the information processing device, or outside the information processing system. Furthermore, the information processing device may have a function of retrieving data from both its own database and an external database.

[0141] Either or both of a storage and a file server can be used for the memory unit 120. Also, a database in which paths of files stored in a file server are recorded can be used for the memory unit 120.

[0142] The storage unit 120 has at least one of a volatile memory and a non-volatile memory. Examples of the volatile memory include a dynamic random access memory (DRAM) and a static random access memory (SRAM). Examples of the non-volatile memory include a resistive random access memory (ReRAM), a phase change random access memory (PRAM), a ferroelectric random access memory (FeRAM), a magnetoresistive random access memory (MRAM), and a flash memory. The storage unit 120 may also have at least one of a NOSRAM (registered trademark) and a DOSRAM (registered trademark). The storage unit 120 may also have a recording media drive. Examples of the recording media drive include a hard disk drive (HDD) and a solid state drive (SSD).

[0143] NOSRAM is an abbreviation of "Nonvolatile Oxide Semiconductor Random Access Memory (RAM)". NOSRAM is a memory in which the memory cell is a two-transistor type (2T) or three-transistor type (3T) gain cell, and the transistor is a transistor (also called OS transistor) that uses a metal oxide in the channel formation region. The current that flows between the source and drain in the off state, that is, the leakage current, is extremely small. NOSRAM can be used as a nonvolatile memory by retaining a charge according to data in the memory cell using the characteristic of extremely small leakage current. In particular, NOSRAM is suitable for arithmetic processing in which only data read operations are repeated in large quantities because it is possible to read the retained data without destroying it (nondestructive read). NOSRAM can increase the data capacity by stacking it, so it can be used as a large-scale cache memory, main memory, or storage memory to improve the performance of semiconductor devices.

[0144] DOSRAM is an abbreviation for "Dynamic Oxide Semiconductor RAM" and refers to RAM with 1T (transistor) 1C (capacitance) type memory cells. DOSRAM is a DRAM formed using OS transistors, and is a memory that temporarily stores information sent from the outside. DOSRAM is a memory that takes advantage of the small off-current of OS transistors.

[0145] In this specification and the like, the term "metal oxide" refers to an oxide of a metal in a broad sense. Metal oxides are classified into oxide insulators, oxide conductors (including transparent oxide conductors), oxide semiconductors (also referred to as oxide semiconductors or simply OS), and the like. For example, when a metal oxide is used for a semiconductor layer of a transistor, the metal oxide may be referred to as an oxide semiconductor.

[0146] The metal oxide in the channel formation region preferably contains indium (In). When the metal oxide in the channel formation region contains indium, the carrier mobility (electron mobility) of the OS transistor is increased. The metal oxide in the channel formation region is preferably an oxide semiconductor containing an element M. The element M is preferably at least one of aluminum (Al), gallium (Ga), and tin (Sn). Other elements applicable to the element M include boron (B), silicon (Si), titanium (Ti), iron (Fe), nickel (Ni), germanium (Ge), yttrium (Y), zirconium (Zr), molybdenum (Mo), lanthanum (La), cerium (Ce), neodymium (Nd), hafnium (Hf), tantalum (Ta), and tungsten (W). However, the element M may be a combination of a plurality of the above elements. The element M is, for example, an element having a high bond energy with oxygen. For example, it is an element that has a higher bond energy with oxygen than indium. In addition, the metal oxide in the channel formation region is preferably a metal oxide containing zinc (Zn). Metal oxides containing zinc may be easily crystallized.

[0147] The metal oxide contained in the channel formation region is not limited to a metal oxide containing indium. The metal oxide contained in the channel formation region may be, for example, a metal oxide containing zinc but not indium, such as zinc tin oxide or gallium tin oxide, a metal oxide containing gallium, or a metal oxide containing tin.

[0148] [Processing section 130] The processing unit 130 has a function of performing processes such as calculation, analysis, and inference using data supplied from one or both of the input unit 110 and the storage unit 120. The processing unit 130 can supply generated data (e.g., calculation results, analysis results, inference results) to one or both of the storage unit 120 and the output unit 140.

[0149] The processing unit 130 has a function of acquiring data from the storage unit 120. The processing unit 130 may also have a function of recording or registering data in the storage unit 120.

[0150] The processing unit 130 may include, for example, an arithmetic circuit. The processing unit 130 may include, for example, a central processing unit (CPU). The processing unit 130 may also include a graphics processing unit (GPU).

[0151] The processing unit 130 may have a microprocessor such as a DSP (Digital Signal Processor). The microprocessor may be realized by a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or an FPAA (Field Programmable Analog Array). The processing unit 130 may also have a quantum processor. The processing unit 130 can perform various data processing and program control by interpreting and executing instructions from various programs using the processor. Programs that can be executed by the processor are stored in at least one of the memory area of ​​the processor and the storage unit 120.

[0152] The processing unit 130 may have a main memory. The main memory may have at least one of a volatile memory such as a random access memory (RAM) and a non-volatile memory such as a read only memory (ROM). The main memory may also have at least one of the above-mentioned NOSRAM and DOSRAM.

[0153] The RAM may be, for example, a DRAM or an SRAM, and a memory space is virtually allocated and used as a working space for the processing unit 130. The operating system, application programs, program modules, program data, lookup tables, and the like stored in the storage unit 120 are loaded into the RAM for execution. These data, programs, and program modules loaded into the RAM are each directly accessed and operated by the processing unit 130.

[0154] ROM can store BIOS (Basic Input / Output System) and firmware that do not require rewriting. Examples of ROM include mask ROM, OTPROM (One Time Programmable Read Only Memory), EPROM (Erasable Programmable Read Only Memory), etc. Examples of EPROM include UV-EPROM (Ultra-Violet Erasable Programmable Read Only Memory), which allows the erasure of stored data by exposure to ultraviolet light, EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory, etc.

[0155] The processing unit 130 can have one or both of an OS transistor and a transistor having silicon in a channel formation region (Si transistor).

[0156] The processing unit 130 preferably includes an OS transistor. Since the off-current of the OS transistor is extremely small, by using the OS transistor as a switch for holding the charge (data) flowing into a capacitive element functioning as a memory element, the data can be held for a long period of time. By using this characteristic in at least one of the register and the cache memory of the processing unit 130, the processing unit 130 can be operated only when necessary, and in other cases, the processing unit 130 can be turned off by saving the information of the immediately preceding processing in the memory element. In other words, normally-off computing is possible, and the power consumption of the information processing system can be reduced.

[0157] It is preferable that the information processing device uses AI for at least part of its processing.

[0158] It is particularly preferable that the information processing device uses an artificial neural network (ANN, hereinafter also simply referred to as a neural network). A neural network is realized by a circuit (hardware) or a program (software).

[0159] In this specification, the term "neural network" refers to a general model that imitates the neural circuit network of a living organism, determines the connection strength between neurons through learning, and has a problem-solving ability. A neural network has an input layer, an intermediate layer (hidden layer), and an output layer.

[0160] In this specification and the like, when discussing neural networks, determining the connection strengths (also called weighting coefficients) between neurons from existing information may be referred to as "learning".

[0161] In this specification and the like, the process of constructing a neural network using connection weights obtained by learning and deriving a new conclusion therefrom may be referred to as "inference."

[0162] [Output section 140] The output unit 140 can output at least one of the calculation result, the analysis result, and the inference result in the processing unit 130 to the outside of the information processing device. For example, the output unit 140 can transmit data via the network 51.

[0163] [Transmission Line 150] The transmission path 150 has a function of transmitting data. Data can be transmitted and received between the input unit 110, the storage unit 120, the processing unit 130, and the output unit 140 via the transmission path 150.

[0164] Note that this embodiment mode can be appropriately combined with other embodiment modes described in this specification.

[0165] (Embodiment 2) In this embodiment, an information processing method according to one embodiment of the present invention will be described with reference to FIGS.

[0166] FIG. 7 is a diagram illustrating an information processing method according to an embodiment of the present invention.

[0167] FIG. 8 is a diagram illustrating an information processing method according to an embodiment of the present invention.

[0168] <Example 1 of information processing method> The information processing method described in this embodiment includes steps S1 to S8 (see FIG. 7).

[0169] [Step S1] In step S 1 , the component 30 accepts a document TXT and a query statement QUE for searching a design asset DAST, and passes the document TXT and the query statement QUE to the component 21 .

[0170] [Step S2] In step S 2 , the component 21 uses the query statement QUE to inquire of the database DB 2 , acquires the design asset DAST, and passes the design asset DAST to the component 30 .

[0171] [Step S3] In step S3, the component 21 classifies the text TXT into a predetermined class using a large-scale language model.

[0172] [Step S4] In step S4, when the document TXT is classified into the class CL_1, the component 21 inquires of the database DB1 by specifying the class CL_1, and obtains the command Cmd_1, the syntax Synt_1, and the template document Tmpl_1.

[0173] The database DB1 includes a record ID1_1, which includes a command Cmd_1, a syntax Synt_1 associated with the command Cmd_1, a template text Tmpl_1 associated with the command Cmd_1, and a class CL_1 associated with the command Cmd_1.

[0174] [Step S5] In step S5, the component 21 generates the instruction statement PT_1 and passes it to the component 20.

[0175] The instruction PT_1 includes a document TXT and a template Tmpl_1. The template Tmpl_1 includes an instruction Instr_1 for analyzing the document TXT and extracting predetermined information INF_1, an instruction Instr_2 for converting the extracted information INF_1 into intermediate code IntC_1 using a conversion rule CnvR_1, and the conversion rule CnvR_1.

[0176] [Step S6] In step S6, the component 20 generates an intermediate code IntC_1 from the text TXT using the large-scale language model in accordance with the directive PT_1, and passes the intermediate code IntC_1 to the component 21.

[0177] [Step S7] In step S7, the component 21 generates the code Code_1 and passes it to the component 30.

[0178] The code Code_1 includes a command Cmd_1 that uses the intermediate code IntC_1 passed to it as an argument in accordance with the syntax Synt_1.

[0179] [Step S8] In step S8, the component 30 provides the code Code_1 and the design asset DAST in which the portion related to the code Code_1 is highlighted.

[0180] This allows the user to operate the software using the text TXT written in a natural language. The user can operate the software even if he or she is not familiar with the operation. The user can operate the software without referring to an operation manual. The user can generate a code Code_1 related to the operation using the text TXT written in a natural language. The user can use a programming language using the text TXT written in a natural language. The circuit design asset DAST can be searched, and the part related to the code Code_1 can be highlighted and provided to the user. The user can refer to the circuit design asset DAST. The design tool created for users with advanced expertise can be used even by users with little experience. As a result, a novel information processing method excellent in convenience, usefulness, and reliability can be provided.

[0181] <Example of information processing method 2> The information processing method described in this embodiment includes steps S1 to S14 (see FIG. 8).

[0182] [Step S1] In step S 1 , the component 30 accepts a document TXT and a query statement QUE for searching a design asset DAST, and passes the document TXT and the query statement QUE to the component 21 .

[0183] [Step S2] In step S 2 , the component 21 uses the query statement QUE to inquire of the database DB 2 , acquires the design asset DAST, and passes the design asset DAST to the component 30 .

[0184] [Step S3] In step S3, the component 21 classifies the text TXT into a predetermined class using a large-scale language model.

[0185] [Step S4] In step S4, when the document TXT is classified into the class CL_1, the component 21 inquires of the database DB1 by specifying the class CL_1, and obtains the command Cmd_1, the syntax Synt_1, and the template document Tmpl_1.

[0186] The database DB1 includes a record ID1_1, which includes a command Cmd_1, a syntax Synt_1 associated with the command Cmd_1, a template text Tmpl_1 associated with the command Cmd_1, and a class CL_1 associated with the command Cmd_1.

[0187] [Step S5] In step S5, the component 21 generates the instruction statement PT_1 and passes it to the component 20.

[0188] The instruction PT_1 includes a document TXT and a template Tmpl_1. The template Tmpl_1 includes an instruction Instr_1 for analyzing the document TXT and extracting predetermined information INF_1, an instruction Instr_2 for converting the extracted information INF_1 into intermediate code IntC_1 using a conversion rule CnvR_1, and an instruction Instr_3 for generating a message MSG requesting supplementation of the information INF_1 and transferring it to the component 21 when the information INF_1 cannot be sufficiently extracted.

[0189] [Step S6] In step S6, the component 20 generates an intermediate code IntC_1 from the text TXT using the large-scale language model in accordance with the directive PT_1, and passes the intermediate code IntC_1 to the component 21.

[0190] [Step S7] In step S7, if the information INF_1 cannot be sufficiently extracted, the process proceeds to step S8, otherwise the process proceeds to step S13.

[0191] [Step S8] In step S8, the component 20 generates a message MSG requesting the supplementation of the information INF_1 in accordance with the directive PT_1, and passes the message to the component 21.

[0192] [Step S9] In step S 9 , component 21 passes message MSG to component 30 .

[0193] [Step S10] In step S10, the component 30 provides a message MSG and a design asset DAST in which a portion related to the command Cmd_1 is highlighted, and waits for input of a supplemental sentence SPL_1.

[0194] [Step S11] In step S11, the component 30 receives the supplemental text SPL_1 and passes the supplemental text SPL_1 to the component 21.

[0195] [Step S12] In step S12, the component 21 adds the supplemental text SPL_1 to the text TXT, updates the instruction text PT_1, and proceeds to step S6.

[0196] [Step S13] In step S13, the component 21 generates the code Code_1 and passes it to the component 30.

[0197] The code Code_1 includes a command Cmd_1 that uses the intermediate code IntC_1 passed to it as an argument in accordance with the syntax Synt_1.

[0198] [Step S14] In step S14, the component 30 provides the code Code_1 and the design asset DAST in which the portion related to the code Code_1 is highlighted.

[0199] This allows the user to supplement and correct the text TXT using the supplemental text SPL_1 written in natural language. The user can also supplement and correct the operation of the software. The user can also supplement and correct the operation of the software even if the user is not familiar with the operation. The user can also supplement and correct the operation of the software without referring to the operation manual. The user can also supplement and correct the code Code_1 related to the operation using the supplemental text SPL_1 written in natural language. The user can also supplement and correct the description of the programming language using the supplemental text SPL_1 written in natural language. The design asset DAST of the circuit can be searched, and the part related to the command Cmd_1 can be highlighted and provided to the user. The user can also refer to the design asset DAST of the circuit. The design tool created for users with high level of expertise can be used even by users with little experience. As a result, a novel information processing method excellent in convenience, usefulness, or reliability can be provided.

[0200] Note that this embodiment mode can be appropriately combined with other embodiment modes described in this specification. [Explanation of symbols]

[0201] CL_1 Class Cmd_1 instruction CnvR_1 Conversion rule Code_1 Code DAST Design Assets ID1_1 record ID2_1 record INF_1 Information Instr_1 Instruction Instr_2 Instructions Instr_3 Instructions IntC_1 intermediate code MSG Message PT_1 Directive text QUE Query statement SPEC_1 Design specifications SPL_1 Supplementary text Synt_1 Syntax Tmpl_1 Template TXT text 20 Components 21 Components 30 Components 51 Network 110 Input section 120 Storage section 130 Processing section 140 Output section 150 Transmission Line

Claims

1. A first component; A second component; and and a third component, the first component has a function of receiving a sentence written in a natural language and a query sentence for searching an intellectual property, and transferring the sentence and the query sentence to the third component; The first component has a function of providing code and a function of providing the design asset by highlighting a portion related to the code; the second component has a function of performing processing using a large-scale language model; the second component has a function of generating an intermediate code from the sentence in accordance with a directive and passing the intermediate code to the third component; the third component has a function of performing processing using a large-scale language model; the third component having a function of classifying the sentence into a predetermined class; when the sentence is classified into one class, the third component has a function of generating the instruction sentence and passing it to the second component; The instruction text includes the text and a template text, the third component has a function of performing processing using a first database; the first database comprises a first record; the first record includes an instruction, a syntax associated with the instruction, the template associated with the instruction, and the class associated with the instruction; The template text includes a first instruction for analyzing the text and extracting predetermined information; a second instruction for converting the extracted information into the intermediate code using a conversion rule; The conversion rule; the first database has a function of responding to a query specifying the class with the command, the syntax, and the template text; the third component has a function of generating the code from the instruction by using the intermediate code passed thereto as an argument in accordance with the syntax, and passing the generated code to the first component; the third component has a function of performing processing using a second database; the second database has a function of responding to the query with the design assets; The third component has a function of transferring the design assets to the first component.

2. the query includes a design specification; the second database comprises a second record; The information processing system according to claim 1 , wherein the second record includes the design asset and the design specification associated with the design asset.

3. the second component has a function of generating a message requesting supplementation of the information according to the instruction text and passing the message to the third component; the third component has a function of transferring the message to the first component when the third component receives the message; the template includes a third instruction for generating the message when the information cannot be sufficiently extracted; 3. The information processing system according to claim 1, wherein the first component has a function of providing the message when the message is received, and a function of providing the design asset by highlighting a portion related to the command.

4. the first component has a function of receiving a supplemental text and transferring the supplemental text to the third component; The information processing system according to claim 3 , wherein the third component has a function of adding the supplemental text to the text, updating the instruction text, and passing the instruction text to the second component.

5. An information processing method having first to eighth steps, In the first step, the first component receives a sentence and a query sentence for searching a design asset, and transfers the sentence and the query sentence to the second component; In the second step, the second component queries a first database using the query statement to obtain the design asset, and transfers the design asset to the first component; In the third step, the second component classifies the sentences into predetermined classes using a large-scale language model; In the fourth step, the second component queries a second database by specifying the class to obtain an instruction, a syntax, and a template; the second database comprises records; the record includes the command, the syntax associated with the command, the template associated with the command, and the class associated with the command; In the fifth step, the second component generates an instruction statement and passes it to a third component; The instruction text includes the sentence and the template text, The template text includes a first instruction for analyzing the text and extracting predetermined information; a second instruction for converting the extracted information into an intermediate code using a conversion rule; The conversion rule; In the sixth step, the third component generates the intermediate code from the sentence using a large-scale language model according to the instruction sentence, and passes the intermediate code to the second component; In the seventh step, the second component generates a code and passes it to the first component; the code includes the instruction using the intermediate code passed thereto as an argument in accordance with the syntax, In the eighth step, the first component provides the code and the design asset in which parts related to the code are highlighted.

6. An information processing method having first to fourteenth steps, In the first step, the first component receives a sentence and a query sentence for searching a design asset, and transfers the sentence and the query sentence to the second component; In the second step, the second component queries a first database using the query statement to obtain the design asset, and transfers the design asset to the first component; In the third step, the second component classifies the sentences into predetermined classes using a large-scale language model; In the fourth step, the second component queries a second database by specifying the class to obtain an instruction, a syntax, and a template; the second database comprises records; the record includes the command, the syntax associated with the command, the template associated with the command, and the class associated with the command; In the fifth step, the second component generates an instruction statement and passes it to a third component; The instruction text includes the sentence and the template text, The template text includes a first instruction for analyzing the text and extracting predetermined information; a second instruction for converting the extracted information into an intermediate code using a conversion rule; The conversion rule; and a third instruction to generate a message requesting supplementation of the information when the information cannot be sufficiently extracted, and to pass the message to the second component; In the sixth step, the third component generates the intermediate code from the sentence using a large-scale language model according to the instruction sentence, and passes the intermediate code to the second component; If the information cannot be sufficiently extracted in the seventh step, proceed to the eighth step, otherwise proceed to the thirteenth step; In the eighth step, the third component generates the message requesting the supplement of the information according to the instruction text and passes the message to the second component; In the ninth step, the second component passes the message to the first component; In the tenth step, the first component provides the message and the design asset in which the portion related to the instruction is highlighted, and waits for input of a supplementary sentence; In the eleventh step, the first component receives the supplemental text and passes the supplemental text to the second component; In the twelfth step, the second component adds the supplemental sentence to the sentence, updates the instruction sentence, and proceeds to the sixth step; In the thirteenth step, the second component generates a code and passes it to the first component; the code includes the instruction using the intermediate code passed thereto as an argument in accordance with the syntax, In a fourteenth step, the first component provides the code and the design asset with portions related to the code highlighted.

Images