Information processing systems, information processing methods

Abstract

To provide a novel information processing system that is superior in convenience, usefulness, or reliability. [Solution] This is an information processing system composed of three components. The first component has the function of receiving information and providing suggestions. The second component has the function of generating evaluation results using a large-scale language model and sending them to the third component. The third component has the function of receiving information, receiving evaluation results and providing suggestions. The third component has subcomponents, the first subcomponent performs processing using a database and management system, the second subcomponent creates queries and generates a set of instruction statements, and the third subcomponent has the function of creating suggestions. This system can process information and conditions related to the synthesis route of a substance by receiving information, generating evaluation results, and providing suggestions.

Description

Technical Field

[0001] One aspect of the present invention relates to an information processing system, an information processing method, or a semiconductor device.

[0002] Note that one aspect of the present invention is not limited to the above technical field. The technical field of one aspect of the invention disclosed in this specification or the like relates to a thing, a method, or a manufacturing method. Or, one aspect 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 aspect of the present invention disclosed in this specification include an information processing device, a semiconductor device, a storage device, a driving method thereof, or a manufacturing method thereof.

Background Art

[0003] In recent years, the development of language models using neural networks has been actively carried out, and in particular, large language models (LLMs) have attracted attention. A large language model is a natural language processing model learned using a large amount of data. By using a large language model, for example, a dialogue model that answers user instructions can be realized. In Non-Patent Document 1, GPT-4 (Generative Pre-trained Transformer 4) (registered trademark) is disclosed as a large language model, and ChatGPT is disclosed as a dialogue model.

[0004] By using a large language model, the capabilities of natural language processing models have been greatly improved. On the other hand, due to the enlargement of language models, it is difficult to build and operate a language model on one's own in terms of equipment and cost. Therefore, using an external service that provides a language model has become one form of using a language model.

[0005] Also, a database constructed from reactions reported in chemical literature since 1779 is known (Non-Patent Document 2).

Prior Art Documents

[0006] [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> [Non-Patent Document 2] Bartosz A. Grzybowski, Angew. Chem. Int. Ed. 2012, 51, 7922 -7927 [Overview of the project] [Problems that the invention aims to solve]

[0007] One aspect of the present invention aims to provide a novel information processing system that is superior in convenience, usefulness, or reliability. Alternatively, it aims to provide a novel information processing method that is superior in convenience, usefulness, or reliability. Alternatively, it aims to provide a novel information processing system, a novel information processing method, or a novel semiconductor device.

[0008] Furthermore, the description of these problems does not preclude the existence of other problems. Moreover, one aspect of the present invention does not need to solve all of these problems. Other problems will naturally become apparent from the description in the specification, drawings, and claims, and it is possible to extract other problems from the description in the specification, drawings, and claims. [Means for solving the problem]

[0009] (1) One aspect of the present invention comprises a first component, a second component, and a third component.

[0010] The first component includes the function of receiving first information and transmitting it to the third component, and the function of receiving and providing proposals. The first information includes information and conditions that identify a substance.

[0011] The second component includes the function of receiving the first instruction and sending the evaluation result to the third component, and the function of performing processing using a large-scale language model. The large-scale language model includes the function of generating the evaluation result according to the first instruction.

[0012] The third component includes the functions of receiving information from the first component and sharing it within the third component, sending instructions from the first component to the second component, and receiving evaluation results and sending suggestions to the first component. The third component also includes a first subcomponent, a second subcomponent, and a third subcomponent.

[0013] The first subcomponent includes the functionality to perform processing using a database and a management system. The management system includes the functionality to create a first list from the database based on a first query, and the first list includes information related to the synthesis route of a substance.

[0014] The second subcomponent has the function of generating a first query and a set of instructions. The first query includes an inquiry statement relating to the synthesis route and synthesis conditions of a substance. The set of instructions includes the first instruction, which includes a first instruction, one synthesis route information selected from a first list, and first information. The first instruction includes an instruction to evaluate the synthesis route information based on the conditions and generate an evaluation result.

[0015] The third subcomponent provides the functionality to generate proposals. These proposals include synthetic route information and evaluation results.

[0016] (2) Another aspect of the present invention is the above-described information processing system in which the database is a graph database.

[0017] A graph database includes a first node, a second node, and edges. Edges connect the first and second nodes, and edges contain conditions for moving from the second node to the first node.

[0018] The synthesis route information includes a first node and an edge list, where the first node is assigned to a substance and the edges are assigned to the productive reactions of the substance. The edge list also includes the edges.

[0019] (3) Another aspect of the present invention is the above-described information processing system in which the synthesized route information includes three or more nodes.

[0020] (4) Another aspect of the present invention is the above-described information processing system in which the database includes an organic chemistry network.

[0021] This allows for the investigation of synthesis routes for substances using a database. Furthermore, it enables the investigation of single or multiple synthesis routes using the database. It also allows for the identification of differences between the conditions and those obtained from the database. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0022] (5) Another aspect of the present invention is the above-described information processing system in which the evaluation result includes an evaluation score. The evaluation score is higher the less difference there is between the conditions and the synthesized route information. The proposal also includes evaluation results in descending order of evaluation score.

[0023] As a result, the synthesis route of a substance can be investigated using a database. Also, one or more synthesis routes can be investigated using a database. Further, the difference between the conditions and the synthesis conditions obtained from the database can be known. Also, the conditions can be arranged in ascending order of the difference from the synthesis conditions obtained from the database, and a proposal can be provided. As a result, a novel information processing system excellent in convenience, usefulness, or reliability can be provided.

[0024] (6) Also, one aspect of the present invention is the above information processing system, in which the first component has a function of receiving synthesis route information and transmitting it to the third component, and a function of receiving a procedure manual and providing it.

[0025] The synthesis route information is selected from the proposals, and the synthesis route information includes an edge list. The edge list includes edges, and the edges include information identifying a document.

[0026] The second component has a function of receiving a second instruction sentence and transmitting a procedure manual to the third component, and a function of performing processing using a large language model. The large language model has a function of generating a procedure manual according to the second instruction sentence.

[0027] The third component has a function of receiving synthesis route information and sharing it within the third component, a function of transmitting a second instruction sentence to the second component, and a function of receiving a procedure manual and transmitting it to the first component.

[0028] The first sub-component has a function of creating a second list from a graph database based on a second query using a management system. The second list stores documents.

[0029] The second subcomponent has the functionality to generate a second query and a second instruction. The second query includes a query statement that collects documents identified in the edge list into the second list. The second instruction includes a second instruction and a second list, and the second instruction includes an instruction to generate a procedure manual from the second list.

[0030] This allows, for example, a user of the information processing system to select composite route information from among the suggestions. Furthermore, one embodiment of the information processing system of the present invention can collect literature related to the selected composite route information from a graph database. Furthermore, one embodiment of the information processing system of the present invention can generate and provide a procedure manual from the literature related to the composite route information. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0031] (7) One aspect of the present invention is an information processing method having a first phase, the first phase comprising a first to tenth step.

[0032] In the first step of the first phase, the first component receives first information and transmits it to the second component. The first information includes information and conditions that identify the substance.

[0033] In the second step of the first phase, the second component receives the information from the first component and shares it within the second component.

[0034] The second component comprises the first subcomponent, the second subcomponent, and the third subcomponent. Furthermore, the first subcomponent includes the functionality to perform processing using a database and management system.

[0035] In the third step of the first phase, the second subcomponent creates and shares the first query within the second component. The first query includes inquiry statements related to the synthesis route and synthesis conditions of the substance.

[0036] In the fourth step of the first phase, the first subcomponent uses a management system to create a first list from the database based on a first query and shares it within the second component. The first list includes information related to the synthesis route of the substance.

[0037] In the fifth step of the first phase, the second subcomponent creates a set of instructions and sends the first instruction to the third component. The set of instructions includes the first instruction, which includes the first instruction, one composite route information selected from the first list, and the first information. The first instruction includes instructions to evaluate the composite route information based on conditions and generate an evaluation result.

[0038] In the sixth step of the first phase, the third component receives the first instruction and generates an evaluation result using a large-scale language model.

[0039] In the seventh step of the first phase, the third component sends the evaluation results to the second component.

[0040] In the eighth step of the first phase, the second component receives the evaluation results and shares them within the second component.

[0041] In the ninth step of the first phase, the third subcomponent creates a proposal and submits it to the first component. The proposal includes synthetic route information and evaluation results.

[0042] In the tenth step of the first phase, the first component receives and provides proposals.

[0043] This allows for the investigation of synthesis routes for substances using a database. Furthermore, it enables the investigation of single or multiple synthesis routes using the database. It also allows for the identification of differences between the conditions and those obtained from the database. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0044] (8) Another aspect of the present invention is an information processing method having a first phase and a second phase.

[0045] The second phase follows the first phase described above, and the second phase comprises steps 1 through 9.

[0046] In the first step of the second phase, the first component receives the composite route information and transmits it to the second component.

[0047] In the second step of the second phase, the second component receives and shares the composite route information within the second component.

[0048] In the third step of the second phase, the second subcomponent creates and shares the second query within the second component.

[0049] The second query includes a query statement that collects the documents identified in the edge list into the second list. The edge list contains edges, each edge contains information that identifies a document, and the second list stores the documents.

[0050] In the fourth step of the second phase, the first subcomponent uses a management system to create a second list from the database based on a second query and shares it within the second component.

[0051] In the fifth step of the second phase, the second subcomponent creates a second instruction and sends it to the third component. The second instruction includes a second instruction and a second list, and the second instruction includes an instruction to generate a procedure manual from the second list.

[0052] In the sixth step of the second phase, the third component receives the second instruction and generates a procedure manual using a large-scale language model.

[0053] In the seventh step of the second phase, the third component sends the procedure manual to the second component.

[0054] In the eighth step of the second phase, the second component receives the procedure manual and sends it to the first component.

[0055] In the ninth step of the second phase, the first component receives and provides the procedure manual.

[0056] This allows, for example, a user of the information processing system to select composite route information from among the suggestions. Furthermore, an information processing system according to one embodiment of the present invention can collect literature related to the selected composite route information from an edge list. In addition, an information processing system according to one embodiment of the present invention can generate and provide a procedure manual from the literature related to the composite route information. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided. [Effects of the Invention]

[0057] One aspect of the present invention can provide a novel information processing system that is superior in convenience, usefulness, or reliability. Alternatively, it can provide a novel information processing method that is superior in convenience, usefulness, or reliability. Alternatively, it can provide a novel information processing system, a novel information processing method, or a novel semiconductor device.

[0058] Furthermore, the description of these effects does not preclude the existence of other effects. Moreover, one aspect of the present invention does not necessarily have to possess all of these effects. Other effects will naturally become apparent from the description in the specification, drawings, and claims, and it is possible to extract other effects from the description in the specification, drawings, and claims. [Brief explanation of the drawing]

[0059] [Figure 1] Figure 1 is a diagram illustrating the configuration of an information processing system according to an embodiment. [Figure 2] Figure 2 is a diagram illustrating the configuration of components used in the information processing system according to the embodiment. [Figure 3] Figures 3(A) and 3(B) illustrate the configuration of information used in the information processing system according to the embodiment. [Figure 4] Figures 4(A) and 4(B) illustrate the configuration of information used in the information processing system according to the embodiment. [Figure 5] Figures 5(A) and 5(B) illustrate the configuration of information used in the information processing system according to the embodiment. [Figure 6] Figures 6(A) and 6(B) illustrate the configuration of information used in the information processing system according to the embodiment. [Figure 7] Figure 7 is a diagram illustrating the configuration of an information processing system according to an embodiment. [Figure 8] Figure 8 is a diagram illustrating the configuration of components used in the information processing system according to the embodiment. [Figure 9] Figures 9(A) and 9(B) illustrate the configuration of information used in the information processing system according to the embodiment. [Figure 10] Figures 10(A) and 10(B) illustrate the configuration of information used in the information processing system according to the embodiment. [Figure 11]Figure 11 is a diagram illustrating the configuration of an information processing device used in an information processing system according to an embodiment. [Figure 12] Figure 12 is a diagram illustrating an information processing method according to an embodiment. [Figure 13] Figure 13 is a diagram illustrating an information processing method according to an embodiment. [Figure 14] Figure 14 is a diagram illustrating an information processing method according to an embodiment. [Figure 15] Figure 15 is a diagram illustrating an information processing method according to an embodiment. [Modes for carrying out the invention]

[0060] An information processing system according to one aspect of the present invention comprises a first component, a second component, and a third component. The first component has the function of receiving information and transmitting it to the third component, and the function of receiving and providing suggestions. The information includes information and conditions that identify a substance. The second component has the function of receiving a first instruction and transmitting the evaluation result to the third component, and the function of performing processing using a large-scale language model. The large-scale language model has the function of generating the evaluation result according to the first instruction.

[0061] The third component has the functions of receiving and sharing information within the third component, sending the first instruction to the second component, and receiving evaluation results and sending the proposal to the first component. The third component also comprises the first subcomponent, the second subcomponent, and the third subcomponent.

[0062] The first subcomponent has the function of performing processing using a database and a management system, and the management system has the function of creating a first list from the database based on a first query. The first list includes information related to the synthesis route information of the substance.

[0063] The second subcomponent has the function of generating a first query and a set of instructions. The first query includes an inquiry statement relating to the synthesis route and synthesis conditions of a substance, and the set of instructions includes the first instruction, a synthesis route information selected from the first list, and other information. The first instruction also includes instructions to evaluate the synthesis route information based on the conditions and generate an evaluation result.

[0064] The third subcomponent has the function of generating proposals, which include synthetic route information and evaluation results.

[0065] This allows for the investigation of synthesis routes for substances using a database. Furthermore, it enables the investigation of single or multiple synthesis routes using the database. It also allows for the identification of differences between the conditions and those obtained from the database. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0066] Embodiments will be described in detail with reference to the drawings. However, it will be readily apparent to those skilled in the art that the present invention is not limited to the following description, and that its form and details can be modified in various ways without departing from the spirit and scope of the present invention. Accordingly, the present invention is not to be interpreted as being limited to the contents of the embodiments shown below. In the configuration of the invention described below, the same reference numerals are used in common across different drawings for the same parts or parts having similar functions, and repeated descriptions are omitted.

[0067] In this specification, ordinal numbers such as "first," "second," etc., are used to avoid confusion of components and do not limit the number of components or the order of components (e.g., process order or layering order). Furthermore, even if a term does not have an ordinal number in this specification, an ordinal number may be added in the claims to avoid confusion of components. Even if a term has an ordinal number in this specification, a different ordinal number may be added in the claims. Even if a term has an ordinal number in this specification, an ordinal number may be omitted in the claims.

[0068] In the drawings attached to this specification, components are classified by function and shown as independent blocks in block diagrams. However, in reality, it is difficult to completely separate components by function, and a single component may be involved in multiple functions.

[0069] (Embodiment 1) In this embodiment, an information processing system according to one aspect of the present invention will be described with reference to Figures 1 to 11.

[0070] Figure 1 is a diagram illustrating the configuration of an information processing system according to one embodiment of the present invention.

[0071] Figure 2 is a diagram illustrating the configuration of components used in an information processing system according to one embodiment of the present invention.

[0072] Figure 3(A) is a diagram illustrating the configuration of information transmitted and received within an information processing system according to one embodiment of the present invention, and Figure 3(B) is a diagram illustrating the proposed configuration.

[0073] Figure 4(A) is a diagram illustrating the structure of a list transmitted and received within an information processing system according to one embodiment of the present invention, and Figure 4(B) is a diagram illustrating the structure of composite route information.

[0074] Figure 5(A) is a diagram illustrating the configuration of a database that can be used in an information processing system according to one embodiment of the present invention, and Figure 5(B) is a diagram illustrating the configuration of an edge list.

[0075] Figure 6(A) is a diagram illustrating the structure of queries sent and received within an information processing system according to one embodiment of the present invention, and Figure 6(B) is a diagram illustrating the structure of a group of instruction statements.

[0076] Figure 7 is a diagram illustrating the configuration of an information processing system according to one embodiment of the present invention.

[0077] Figure 8 is a diagram illustrating the configuration of components used in an information processing system according to one embodiment of the present invention.

[0078] Figure 9(A) is a diagram illustrating the configuration of queries sent and received within an information processing system according to one embodiment of the present invention, and Figure 9(B) is a diagram illustrating the configuration of an edge list.

[0079] Figure 10(A) is a diagram illustrating the structure of instruction statements transmitted and received within an information processing system according to one embodiment of the present invention, and Figure 10(B) is a diagram illustrating the structure of a list.

[0080] Figure 11 is a block diagram illustrating the configuration of an information processing device that can be used in an information processing system according to one embodiment of the present invention.

[0081] <Example of an information processing system configuration 1> The information processing system described in this embodiment includes component 110, component 130, and component 120 (see Figure 1).

[0082] For example, the information processing devices that perform the functions of component 110, component 130, and component 120 each include a computing device and a communication device. Furthermore, these communication devices can be connected to each other, for example, via a network 51, to constitute an information processing system according to one embodiment of the present invention.

[0083] <Example 1 of Component 110> Component 110 has the function of receiving information Inf and transmitting it to component 120, and the function of receiving proposal Rec1 and providing it, for example, to the user 99 of the information processing system. Specifically, it provides it to the user 99 of the information processing system using output devices such as a display device, speaker, printer, and storage device.

[0084] The information Inf includes information that identifies the substance Matl and the conditions Cond (see Figure 3(A)). For example, along with the chemical structure formula of substance Matl, the reaction temperature, reaction time, pressure, etc., desired by the user 99 of the information processing system during the synthesis of substance Matl can be used in the information Inf.

[0085] For example, a user 99 of the information processing system inputs information Inf into component 110. Specifically, the user 99 of the information processing system inputs information into component 110 using input devices such as a keyboard, mouse, eye-tracking device, and microphone.

[0086] <Example 1 of Component 130> Component 130 includes the function of receiving an instruction statement Pt1(x) and sending an evaluation result ER(x) to component 120, and the function of performing processing using a large-scale language model LLM.

[0087] 《Example 1 of a Large-Scale Language Model (LLM)》 The large-scale language model LLM has the function of generating an evaluation result ER(x) according to the instruction Pt1(x).

[0088] <Example 1 of Component 120> Component 120 includes the functions of receiving information Inf and sharing it within component 120, sending instruction statement Pt1(x) to component 130, and receiving evaluation result ER(x) and sending proposal Rec1 to component 110.

[0089] Furthermore, component 120 includes subcomponents 120A, 120B, and 120C (see Figure 2).

[0090] Example 1 of Subcomponent 120A Subcomponent 120A has the functionality to perform processing using a database DB and a management system DBMS.

[0091] The management system (DBMS) has the function of creating list Lst1 from the database (DB) based on query Qu1. Note that list Lst1 includes information related to the synthesis route information SRI(x) of substance Matl (see Figure 4(A)).

[0092] [Synthetic Route Information SRI(x)] The synthesis route information SRI(x) for substance Matl includes the starting material SM and substance Matl (see Figure 4(B)).

[0093] The composite root information SRI(x) can include intermediates Int(x,1), Int(x,2), and Int(x,n-1), where n is an integer greater than 1.

[0094] Furthermore, the synthesis route information SRI(x) may include conditions for synthesizing substance Matl from intermediate Int(x,1), conditions for synthesizing intermediate Int(x,1) from intermediate Int(x,2), and conditions for synthesizing intermediate Int(x,n-1) from starting material SM.

[0095] 《Example 1 of Subcomponent 120B》 Subcomponent 120B has the function of creating query Qu1 and a set of directives Pt1 (see Figure 2).

[0096] [Query Qu1] Query Qu1 contains query statements related to the synthesis route and synthesis conditions for substance Matl (see Figure 6(A)).

[0097] [A group of instructions Pt1] A group of instruction statements Pt1 includes instruction statement Pt1(x) (see Figure 6(B)). Furthermore, when list Lst1 contains multiple composite routes, subcomponent 120B creates instruction statements for each composite route. In other words, a group of instruction statements Pt1 includes instruction statements created for each composite route.

[0098] The instruction Pt1(x) includes instruction g1(), one composite route information SRI(x) selected from list Lst1, and information Inf. Instruction g1() includes an instruction to evaluate the composite route information SRI(x) based on condition Cond and generate the evaluation result ER(x).

[0099] For example, the document in the following paragraph can be used as instruction Pt1(x).

[0100] "Synthetic Route: Synthetic Route Information SRI(x)" Information: Information Inf Evaluate whether the synthesis route meets the conditions presented in Information Inf. For each condition, please answer "Condition met" or "Condition not met." Additionally, if there are other favorable conditions for synthesis, please indicate them as "Favorable conditions present." Conversely, if there are unfavorable conditions for synthesis, please indicate them as "Unfavorable conditions present."

[0101] Subcomponent 120C Subcomponent 120C has the function of generating Proposal Rec1 (see Figure 2). Proposal Rec1 includes the synthesized route information SRI(x) and the evaluation result ER(x).

[0102] [Evaluation result ER(x)] The evaluation result ER(x) includes the evaluation score Sco(x) (see Figure 3(B)). The evaluation score Sco(x) is higher the smaller the difference between the condition Cond and the composite route information SRI(x). Furthermore, proposed Rec1 includes evaluation result ER(x) in descending order of evaluation score Sco(x). For example, subcomponent 120C can use the number of "favorable conditions" and "poor conditions" included in the evaluation result ER(x) to calculate its evaluation score Sco(x).

[0103] This allows for the investigation of synthesis routes for substance Matl using a database (DB). Furthermore, one or more synthesis routes can be investigated using the database. The difference between the given conditions (Cond) and the synthesis conditions obtained from the database (DB) can also be determined. Additionally, the proposed routes (Rec1) can be presented, sorted by the smallest difference between the given conditions (Cond) and the database-obtained synthesis conditions. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0104] Example 2 of Subcomponent 120A Subcomponent 120A has the functionality to perform processing using the graph database GDB. The composite route information SRI(x) is stored in the graph database GDB.

[0105] [Graph Database GDB example] The graph database GDB includes node Nd_0, node Nd(x,1), and edge Edg(x,1) (see Figure 5(A)). The graph database GDB also includes node Nd(x,2), edge Edg(x,2), node Nd(x,n-1), node Nd(x,n), and edge Edg(x,n).

[0106] Furthermore, the graph database GDB can also store synthesis route information different from that of the synthesis route information SRI(x). For example, it can store a synthesis route from the starting material SM2, through intermediate Int21 and intermediate Int22, to material Matl.

[0107] Edge Edg(x,1) connects node Nd_0 and node Nd(x,1), edge Edg(x,2) connects node Nd(x,1) and node Nd(x,2), and edge Edg(x,n) connects node Nd(x,n-1) and node Nd(x,n). Note that edge Edg(x,1) includes a condition for moving from node Nd(x,1) to node Nd_0.

[0108] In particular, the composite route information SRI(x) includes three or more nodes.

[0109] Furthermore, for example, the Network of Organic Chemistry (NOC) can be used as a database.

[0110] [Example of synthetic route information SRI(x)] The synthesis route information SRI(x) includes node Nd_0 and edge list EL(x). Node Nd_0 is assigned to substance Matl, and edge Edg(x,1) is assigned to the synthesis reaction of substance Matl.

[0111] Furthermore, node Nd(x,1) is assigned to the intermediate Int(x,1), edge Edg(x,2) is assigned to the formation reaction of intermediate Int(x,1), and node Nd(x,2) is assigned to the intermediate Int(x,2). Additionally, node Nd(x,n-1) is assigned to the intermediate Int(x,n-1), edge Edg(x,n) is assigned to the formation reaction of intermediate Int(x,n-1), and node Nd(x,n) is assigned to the starting material SM.

[0112] For example, the conditions for synthesizing substance Matl from intermediate Int(x,1) can be stored in edge Edg(x,1), and the conditions for synthesizing intermediate Int(x,1) from intermediate Int(x,2) can be stored in edge Edg(x,2). Furthermore, the conditions for synthesizing intermediate Int(x,n-1) from starting material SM can be stored in edge Edg(x,n).

[0113] [Example of edge list EL(x)] The edge list EL(x) includes edge Edg(x,1) (see Figure 5(B)). The edge list EL(x) also includes edges Edg(x,2) and Edg(x,n).

[0114] This allows for the investigation of synthesis routes for substance Matl using a database (DB). Furthermore, single or multiple synthesis routes can be investigated using the database. Additionally, the difference between the conditions Cond and the synthesis conditions obtained from the database can be identified. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0115] <Example 2 of Component 110> Component 110 has the function of receiving synthesized route information SRI(x) and transmitting it to component 120, and the function of receiving procedure manual PM and providing it, for example, to the user 99 of the information processing system (see Figure 7). Specifically, it provides it to the user 99 of the information processing system using output devices such as display devices, speakers, printers, and storage devices.

[0116] The synthesis route information SRI(x) is selected from proposal Rec1. For example, if proposal Rec1 contains multiple synthesis route information, the user 99 of the information processing system can select the synthesis route that is closest to the desired synthesis conditions (reaction temperature, reaction time, pressure, etc.) from proposal Rec1 and use it for the synthesis route information SRI(x).

[0117] Furthermore, the synthesized root information SRI(x) includes the edge list EL(x), and the edge list EL(x) includes the edge Edg(x,1). Note that the edge Edg(x,1) includes information that identifies the document Doc(x,1) (see Figure 9(B)). The edge list EL(x) can also include edges Edg(x,2) through Edg(x,n). Furthermore, the edge Edg(x,2) includes information that identifies the document Doc(x,2), and the edge Edg(x,n) includes information that identifies the document Doc(x,n).

[0118] For example, a user 99 of the information processing system inputs the synthesized route information SRI(x) into component 110. Specifically, the user 99 of the information processing system inputs the information into component 110 using an input device such as a keyboard, mouse, or eye-tracking device.

[0119] <Example 2 of Component 130> Component 130 includes the function of receiving instruction text Pt2 and sending procedure manual PM to component 120, and the function of performing processing using the large-scale language model LLM.

[0120] 《Example 2 of a Large-Scale Language Model (LLM)》 The large-scale language model LLM has the function of generating procedure manuals PM according to instruction text Pt2.

[0121] <Example 2 of Component 120> Component 120 includes the function of receiving and sharing the synthesized route information SRI(x) within component 120, the function of sending the instruction statement Pt2 to component 130, and the function of receiving the procedure manual PM and sending it to component 110.

[0122] Example 3 of Subcomponent 120A Subcomponent 120A has the function of creating list Lst2 from the graph database GDB based on query Qu2 using the management system DBMS (see Figure 8). List Lst2 stores the reference Doc(x,1).

[0123] Example 2 of Subcomponent 120B Subcomponent 120B has the functionality to create query Qu2 and directive Pt2.

[0124] [Query Qu2] Query Qu2 contains a query statement that collects the literature identified in edge list EL(x) into list Lst2 (see Figures 9(A) and 10(B)). Additionally, list Lst2 stores the literature according to the order specified in the synthetic root information SRI(x), for example.

[0125] [Instructive text Pt2] Instruction Pt2 includes instruction g2() and list Lst2 (see Figure 10(A)). Instruction g2() includes an instruction to generate procedure manual PM from list Lst2.

[0126] For example, the document in the following paragraph can be used as instruction statement Pt2.

[0127] "Synthesis route: List Lst2" References: List Lst2 For each synthesis route, represented in the order they are stored in the list, please create a synthesis procedure manual, referring to the literature.

[0128] This allows, for example, a user of the information processing system to select a composite route information SRI(x) from among the proposed Rec1. Furthermore, an information processing system according to one embodiment of the present invention can collect literature related to the selected composite route information SRI(x) from a graph database GDB. In addition, an information processing system according to one embodiment of the present invention can generate and provide a procedure manual PM from the literature related to the composite route information SRI(x). As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0129] <Example of an information processing system configuration 2> The information processing system described in this embodiment includes component 110, component 120, and component 130 (see Figure 1).

[0130] For example, an information processing system according to one aspect of the present invention can be configured with an information processing device that performs the functions of component 110, an information processing device that performs the functions of component 120, and an information processing device that performs the functions of component 130. The number of information processing devices constituting the information processing system according to one aspect of the present invention is one or more. Furthermore, for example, an information processing system according to one aspect of the present invention can be configured by connecting multiple information processing devices using a network 51.

[0131] By configuring an information processing system according to one aspect of the present invention using multiple information processing devices, the load related to information processing can be distributed.

[0132] <Example of Information Processing Device Configuration 1> The configuration example 1 of the information processing device described in this embodiment can be used as component 110. The configuration example 1 of the information processing device can also be called a client computer or the like. For example, a desktop computer can be used as component 110.

[0133] Configuration Example 1 of the information processing device can receive data input by a user of an information processing system according to one aspect of the present invention. Furthermore, Configuration Example 1 of the information processing device can provide the user with data output by an information processing system according to one aspect of the present invention.

[0134] In component 110, for example, dedicated application software, a web browser, etc., are operated. Users of an information processing system according to one embodiment of the present invention can access the information processing system through either of these. As a result, they can enjoy services using the information processing system according to one embodiment of the present invention.

[0135] <Example of Information Processing Device Configuration 2> The configuration example 2 of the information processing device described in this embodiment can be used for component 120. For example, a workstation, server computer, supercomputer, etc., can be used for component 120.

[0136] Furthermore, it is preferable that the second example of the information processing device configuration has the functionality of a parallel computer. By using it as a parallel computer, it is possible to perform large-scale calculations necessary for, for example, learning and inference of artificial intelligence (AI).

[0137] Furthermore, the second example of the information processing device configuration can perform processing using a natural language model with AI.

[0138] For example, it is preferable to be able to perform processing using natural language models such as GPT-3®, GPT-3.5, GPT-4®, LaMDA, Llama2, and Llama3.

[0139] <Example of Information Processing Device Configuration 3> For example, the configuration example 3 of the information processing device described in this embodiment can be used for component 130. Note that component 130 is larger in scale and has higher computing power than component 120. For example, a large computer such as a server computer or supercomputer can be used for component 130.

[0140] Furthermore, it is preferable that the information processing device configuration example 3 has the functionality of a parallel computer. By using it as a parallel computer, for example, it can perform large-scale calculations necessary for AI training and inference.

[0141] Furthermore, the third example of the information processing device configuration can perform processing using an AI-based natural language model. In particular, it can execute processing using a general-purpose language model capable of performing various natural language processing tasks.

[0142] For example, processing can be performed using natural language models such as GPT-3(registered trademark), GPT-3.5, GPT-4(registered trademark), LaMDA, Llama2, and Llama3. Processing using GPT-4(registered trademark) is particularly preferable. For instance, being able to perform processing using large-scale language models, which are significantly larger than conventional natural language models, can enable more natural document generation or dialogue.

[0143] Furthermore, those who provide services using an information processing system according to one embodiment of the present invention do not necessarily need to own the configuration example 3 of the information processing device themselves. For example, a service provider can utilize a portion of the services provided by other businesses, etc., using the configuration example 3 of the information processing device.

[0144] <Example of Network 51 Configuration> A network 51 that can be used in an information processing system according to one embodiment of the present invention can connect multiple information processing devices. This allows the connected multiple information processing devices to transmit and receive data from each other. Furthermore, it allows for the distribution of the information processing load.

[0145] When performing wireless communication, communication protocols or technologies such as 4th generation mobile communication systems (4G), 5th generation mobile communication systems (5G), 6th generation mobile communication systems (6G), or specifications standardized by IEEE such as Wi-Fi® and Bluetooth® can be used.

[0146] For example, a local network can be used as network 51. An intranet or extranet can also be used as network 51. Furthermore, PAN (Personal Area Network), LAN (Local Area Network), CAN (Campus Area Network), MAN (Metropolitan Area Network), WAN (Wide Area Network), GAN (Global Area Network), etc., can be used as network 51.

[0147] Furthermore, for example, a global network can be used for network 51. Specifically, the internet, which is the foundation of the World Wide Web (WWW), can be used.

[0148] Furthermore, a person who provides services using an information processing system according to one aspect of the present invention can, for example, provide services using an information processing method according to one aspect of the present invention via a network 51.

[0149] Furthermore, if an information processing system according to one embodiment of the present invention is built within a local network, the possibility of confidential information leakage can be reduced compared to using the Internet.

[0150] <Example of Information Processing Device Configuration 4> An information processing device 20 that can be used in an information processing system according to one embodiment of the present invention includes, for example, an input unit 21, a storage unit 22, a processing unit 23, an output unit 24, and a transmission line 25 (see Figure 11).

[0151] In the drawings attached to this specification, the components are classified by function and shown as independent blocks in the block diagram. However, 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 23 may function as the input unit 21. Also, one function may be involved in multiple components. For example, the processing performed by the processing unit 23 may be executed by different information processing devices depending on the processing.

[0152] Input section 21 The input unit 21 can receive data from outside the information processing device. For example, the input unit 21 can receive data via the network 51. Specifically, a device such as a personal computer equipped with a communication port or communication function can be used.

[0153] The input unit 21 supplies the received data to either or both of the storage unit 22 and the processing unit 23 via the transmission line 25.

[0154] 《Storage section 22》 The memory unit 22 has the function of storing the program executed by the processing unit 23. The memory unit 22 may also have the function of storing data generated by the processing unit 23 (for example, calculation results, analysis results, inference results), data received by the input unit 21, etc.

[0155] The storage unit 22 may have a database. The information processing device may also have a database separate from the storage unit 22. The information processing device may have the function to retrieve data from a database located outside the storage unit 22, outside the information processing device itself, or outside the information processing system. Furthermore, the information processing device may have the function to retrieve data from both its own database and an external database.

[0156] Either or both of the storage and / or file server can be used in the storage unit 22. Furthermore, a database recording the paths of files stored on the file server can be used in the storage unit 22.

[0157] The storage unit 22 includes at least one of volatile memory and non-volatile memory. Examples of volatile memory include DRAM (Dynamic Random Access Memory) and SRAM (Static Random Access Memory). Examples of non-volatile memory include ReRAM (Resistive Random Access Memory), PRAM (Phase Change Random Access Memory), FeRAM (Ferroelectric Random Access Memory), MRAM (Magnetoresistive Random Access Memory), and flash memory. The storage unit 22 may also include at least one of NOSRAM (registered trademark) and DOSRAM (registered trademark). The storage unit 22 may also include a recording media drive. Examples of recording media drives include hard disk drives (HDD) and solid state drives (SSD).

[0158] NOSRAM is an abbreviation for "Nonvolatile Oxide Semiconductor Random Access Memory (RAM)". NOSRAM is a type of memory where the memory cell is a 2-transistor (2T) or 3-transistor (3T) gain cell, and the transistors are transistors that use metal oxide in the channel formation region (also called OS transistors). OS transistors have an extremely small current flowing between the source and drain when off, i.e., a leakage current. By utilizing the characteristic of extremely low leakage current, NOSRAM can be used as a non-volatile memory by holding charge corresponding to the data within the memory cell. In particular, NOSRAM can read the stored data without destroying it (non-destructive read), making it suitable for computational processing that involves repeating data read operations a large amount. Because the data capacity of NOSRAM can be increased by stacking it, it can be used as a large-scale cache memory, main memory, or storage memory to improve the performance of semiconductor devices.

[0159] DOSRAM is an abbreviation for "Dynamic Oxide Semiconductor RAM," and refers to RAM with a 1T (transistor) 1C (capacitance) type memory cell. DOSRAM is a type of DRAM formed using OS transistors, and it is a memory that temporarily stores information sent from an external source. DOSRAM is a memory that takes advantage of the low off-current of OS transistors.

[0160] In this specification, "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 called oxide semiconductors or simply OS), etc. For example, when a metal oxide is used in the semiconductor layer of a transistor, that metal oxide may be referred to as an oxide semiconductor.

[0161] The metal oxide in the channel-forming region preferably contains indium (In). When the metal oxide in the channel-forming region contains indium, the carrier mobility (electron mobility) of the OS transistor is increased. For example, indium oxide (InOx) or indium gallium zinc oxide (In-Ga-Zn oxide, also written as "IGZO") can be used in the channel-forming region. Furthermore, the metal oxide in the channel-forming region is preferably an oxide semiconductor containing element M. Element M is preferably at least one of aluminum (Al), gallium (Ga), and tin (Sn). Other elements applicable to 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, in some cases, element M may be a combination of multiple elements as mentioned above. Element M is, for example, an element with a high bond energy with oxygen. For example, an element with a higher bond energy with oxygen than indium. Furthermore, the metal oxide containing the channel-forming region is preferably a metal oxide containing zinc (Zn). Metal oxides containing zinc may be more prone to crystallization.

[0162] The metal oxides present in the channel-forming regions are not limited to indium-containing metal oxides. For example, the metal oxides present in the channel-forming regions may be zinc-tin oxides, gallium-tin oxides, or other metal oxides that do not contain indium but contain zinc, gallium, or tin.

[0163] Processing Unit 23 The processing unit 23 has the function of performing calculations, analyses, and inferences using data supplied from either or both of the input unit 21 and the storage unit 22. The processing unit 23 can supply the generated data (e.g., calculation results, analysis results, inference results) to either or both of the storage unit 22 and the output unit 24.

[0164] The processing unit 23 has the function of acquiring data from the storage unit 22. The processing unit 23 may also have the function of recording or registering data in the storage unit 22.

[0165] The processing unit 23 may, for example, have an arithmetic circuit. The processing unit 23 may, for example, have a central processing unit (CPU). The processing unit 23 may also have a graphics processing unit (GPU). The processing unit 23 may also have a neural processing unit (NPU / neural network processing unit).

[0166] The processing unit 23 may have a microprocessor such as a DSP (Digital Signal Processor). The microprocessor can be implemented using a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or FPAA (Field Programmable Analog Array). The processing unit 23 may also have a quantum processor. The processing unit 23 can perform various data processing and program control by interpreting and executing instructions from various programs via the processor. Programs that can be executed by the processor are stored in at least one of the processor's memory area and the storage unit 22.

[0167] The processing unit 23 may have main memory. The main memory may include at least one of volatile memory such as RAM and non-volatile memory such as ROM (Read Only Memory). Furthermore, the main memory may include at least one of the above-mentioned NOSRAM and DOSRAM.

[0168] For RAM, for example, DRAM or SRAM is used, and a virtual memory space is allocated and used as the workspace for the processing unit 23. The operating system, application programs, program modules, program data, and lookup tables stored in the storage unit 22 are loaded into RAM for execution. These data, programs, and program modules loaded into RAM are each directly accessed and manipulated by the processing unit 23.

[0169] ROM can store BIOS (Basic Input / Output System) and firmware, etc., which do not require rewriting. Examples of ROM include mask ROM, OTPROM (One Time Programmable Read Only Memory), and EPROM (Erasable Programmable Read Only Memory). Examples of EPROM include UV-EPROM (Ultra-Violet Erasable Programmable Read Only Memory), which allows data to be erased by ultraviolet irradiation, EEPROM (Electrically Erasable Programmable Read Only Memory), and flash memory.

[0170] The processing unit 23 may have either or both an OS transistor and a transistor having silicon in its channel formation region (Si transistor).

[0171] The processing unit 23 preferably has an OS transistor. Because the OS transistor has an extremely small off-current, using the OS transistor as a switch to hold the charge (data) that has flowed into a capacitive element that functions as a memory element ensures that the data can be retained for a long period of time. By using this characteristic in at least one of the registers and cache memory of the processing unit, the processing unit can be operated only when necessary, and at other times the information of the previous processing is saved to the memory element, thereby turning off the processing unit. In other words, normally-off computing becomes possible, and the power consumption of the information processing system can be reduced.

[0172] It is preferable for information processing devices to use AI for at least some of their processing.

[0173] Information processing devices preferably utilize artificial neural networks (ANNs, also simply referred to as neural networks). Neural networks are implemented using circuits (hardware) or programs (software).

[0174] In this specification, the term "neural network" refers to any model that mimics the neural network of living organisms, determines the strength of connections between neurons through learning, and possesses problem-solving capabilities. A neural network has an input layer, an intermediate layer (hidden layer), and an output layer.

[0175] In this specification and other documents, when discussing neural networks, the process of determining the connection strength (also called weight coefficient) between neurons from existing information is sometimes referred to as "learning."

[0176] In this specification and other documents, the process of constructing a neural network using connection strengths obtained through learning and deriving new conclusions from it may be referred to as "inference."

[0177] Output section 24 The output unit 24 can output at least one of the calculation results, analysis results, and inference results from the processing unit 23 to the outside of the information processing device. For example, the output unit 24 can transmit data via the network 51. Specifically, a device such as a personal computer equipped with a communication port or communication function can be used. Alternatively, a device equipped with a communication function may be used for both the input unit 21 and the output unit 24.

[0178] Transmission line 25 The transmission line 25 has the function of transmitting data. Data can be transmitted and received between the input unit 21, the storage unit 22, the processing unit 23, and the output unit 24 via the transmission line 25. Specifically, an external bus, LAN, or the internet can be used as the transmission line 25.

[0179] This embodiment can be appropriately combined with other embodiments shown in this specification.

[0180] (Embodiment 2) In this embodiment, an information processing method according to one aspect of the present invention will be described with reference to Figures 12 to 15.

[0181] Figure 12 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0182] Figure 13 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0183] Figure 14 is a sequence diagram illustrating an information processing method according to one embodiment of the present invention.

[0184] Figure 15 is a sequence diagram illustrating an information processing method according to one embodiment of the present invention.

[0185] <Example of information processing method 1> One aspect of the present invention is an information processing method having a phase PH1 (see Figure 12).

[0186] <Example of Phase PH1> Phase PH1 comprises steps S1 to S10.

[0187] Step S1 In step S1 of phase PH1, component 110 receives information Inf and transmits it to component 120. Information Inf includes information that identifies the substance Matl and conditions Cond. For example, a user 99 of the information processing system inputs information Inf. Step S1 corresponds to the arrows extending from (1) and (2) in Figure 14.

[0188] Step S2 In step S2 of phase PH1, component 120 receives information Inf and shares it within component 120.

[0189] Component 120 comprises subcomponents 120A, 120B, and 120C. Subcomponent 120A also includes the functionality to perform processing using a database (DB) and a management system (DBMS).

[0190] Step S3 In step S3 of phase PH1, subcomponent 120B creates query Qu1 and shares it within component 120. Query Qu1 includes a query statement relating to the synthesis route and synthesis conditions of substance Matl. Step S3 corresponds to the arrow extending from (3) in Figure 14.

[0191] Step S4 In step S4 of phase PH1, subcomponent 120A uses the management system DBMS to create list Lst1 from the database DB based on query Qu1 and shares it within component 120. List Lst1 includes information related to the synthesis route information SRI(x) of substance Matl. Step S4 corresponds to the arrow extending from (4) in Figure 14.

[0192] Step S5 In step S5 of phase PH1, subcomponent 120B creates a group of instruction statements Pt1 and sends instruction statement Pt1(x) to component 130. The group of instruction statements Pt1 includes instruction statement Pt1(x).

[0193] The instruction Pt1(x) includes instruction g1(), one composite route information SRI(x) selected from list Lst1, and information Inf. Instruction g1() includes an instruction to evaluate the composite route information SRI(x) based on condition Cond and generate the evaluation result ER(x). Step S5 corresponds to the arrows extending from (5) and (6) in Figure 14.

[0194] Step S6 In step S6 of phase PH1, component 130 receives instruction Pt1(x) and generates evaluation result ER(x) using the large-scale language model LLM.

[0195] Step S7 In step S7 of phase PH1, component 130 transmits the evaluation result ER(x) to component 120. Step S7 corresponds to the arrow extending from (7) in Figure 14.

[0196] Step S8 In step S8 of phase PH1, component 120 receives the evaluation result ER(x) and shares it within component 120.

[0197] Step S9 In step S9 of phase PH1, subcomponent 120C creates proposal Rec1 and sends it to component 110. Proposal Rec1 includes the synthesized route information SRI(x) and the evaluation result ER(x). Step S9 corresponds to the arrow extending from (8) in Figure 14.

[0198] Step S10 In step S10 of phase PH1, component 110 receives proposal Rec1 and provides it, for example, to the user 99 of the information processing system. Step S10 corresponds to the arrows extending from (9) and (10) in Figure 14.

[0199] This allows for the investigation of synthesis routes for substance Matl using a database (DB). Furthermore, single or multiple synthesis routes can be investigated using the database. Additionally, the difference between the conditions Cond and the synthesis conditions obtained from the database can be identified. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0200] <Example of information processing method 2> One aspect of the present invention is an information processing method having phase PH1 and phase PH2 (see Figure 13).

[0201] <Example of Phase PH2> Phase PH2 follows Phase PH1, and Phase PH2 comprises steps S1 to S9.

[0202] Step S1 In step S1 of phase PH2, component 110 receives the composite route information SRI(x) and transmits it to component 120. For example, a user 99 of the information processing system inputs the composite route information SRI(x). Step S1 corresponds to the arrows extending from (1) and (2) in Figure 15.

[0203] Step S2 In step S2 of phase PH2, component 120 receives the synthetic route information SRI(x) and shares it within component 120.

[0204] Step S3 In step S3 of phase PH2, subcomponent 120B creates query Qu2 and shares it within component 120.

[0205] Query Qu2 includes a query statement that collects the documents identified in edge list EL(x) into list Lst2. Edge list EL(x) includes edge Edg(x,1), and edge Edg(x,1) includes information that identifies document Doc(x,1). List Lst2 stores document Doc(x,1). Step S3 corresponds to the arrow extending from (3) in Figure 15.

[0206] Step S4 In step S4 of phase PH2, subcomponent 120A uses the management system DBMS to create list Lst2 from database DB based on query Qu2 and shares it within component 120. Step S4 corresponds to the arrow extending from (4) in Figure 15.

[0207] Step S5 In step S5 of phase PH2, subcomponent 120B creates instruction statement Pt2 and sends instruction statement Pt2 to component 130. Instruction statement Pt2 includes instruction g2() and list Lst2, where instruction g2() includes an instruction to generate procedure manual PM from list Lst2. Step S5 corresponds to the arrows extending from (5) and (6) in Figure 15.

[0208] Step S6 In step S6 of phase PH2, component 130 receives instruction Pt2 and generates procedure PM using the large-scale language model LLM.

[0209] Step S7 In step S7 of phase PH2, component 130 sends the procedure manual PM to component 120. Step S7 corresponds to the arrow extending from (7) in Figure 15.

[0210] Step S8 In step S8 of phase PH2, component 120 receives the procedure manual PM and transmits it to component 110. Step S8 corresponds to the arrow extending from (8) in Figure 15.

[0211] Step S9 In step S9 of phase PH2, component 110 receives the procedure manual PM and provides it, for example, to the user 99 of the information processing system. Step S9 corresponds to the arrow extending from (9) in Figure 15.

[0212] This allows, for example, a user of the information processing system to select a composite route information SRI(x) from among the proposed Rec1. Furthermore, an information processing system according to one embodiment of the present invention can collect literature related to the selected composite route information SRI(x) from the edge list EL(x). In addition, an information processing system according to one embodiment of the present invention can generate and provide a procedure manual PM from the literature related to the composite route information SRI(x). As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0213] This embodiment can be appropriately combined with other embodiments shown in this specification. [Explanation of Symbols]

[0214] Cond condition DB Database DBMS Management System Edg Edge ER(x) evaluation results GDB Graph Database Inf information Int21 Intermediate Int22 Intermediate Large-Scale Language Model (LLM) Matl substance Nd node Nd_0 node PM Procedure Manual Sco(x) Evaluation Score SM starting material SRI(x) Synthetic Route Information 20 Information Processing Devices 21 Input section 22 Memory section 23 Processing Unit 24 Output section 25 Transmission lines 51 Network 99 User 110 components 120 components 120A Subcomponent 120B Subcomponent 120C Subcomponents 130 components

Claims

1. The first component and The second component, It has a third component, The first component includes a function for receiving first information and transmitting the first information to the third component, and a function for receiving a proposal and providing the proposal. The first information includes information and conditions that identify the substance, The second component includes a function to receive a first instruction and send the evaluation result to the third component, and a function to perform processing using a large-scale language model. The large-scale language model has a function to generate the evaluation result according to the first instruction, The third component includes a function to receive the first information and share the first information within the third component, a function to transmit the first instruction to the second component, and a function to receive the evaluation result and transmit the proposal to the first component. The third component comprises a first subcomponent, a second subcomponent, and a third subcomponent. The first subcomponent is equipped with a function to perform processing using a database and a management system, The management system includes a function to create a first list from the database based on a first query. The first list includes information relating to the synthesis route information of the substance, The second subcomponent has the function of creating the first query and a set of directives, The first query includes a query statement relating to the synthesis route and synthesis conditions of the substance, The group of instructions includes the first instruction, The first instruction statement includes the first instruction, one of the composite route information selected from the first list, and the first information. The first instruction includes an instruction to evaluate the composite route information based on the conditions and generate the evaluation result, The third subcomponent has the function of creating the proposal, The proposed system is an information processing system that includes the synthesized route information and the evaluation results.

2. The aforementioned database is a graph database, The graph database includes a first node, a second node, and an edge, The edge connects the first node and the second node, The edge includes a condition for moving from the second node to the first node, The composite route information includes the first node and edge list, The first node is assigned to the substance, The edge is assigned to the reaction for the formation of the substance, The information processing system according to claim 1, wherein the edge list includes the edges.

3. The information processing system according to claim 2, wherein the synthesized route information includes three or more nodes.

4. The information processing system according to claim 1, wherein the database includes an organic chemistry network.

5. The aforementioned evaluation results include an evaluation score, The evaluation score is higher the less difference there is between the conditions and the composite route information. The proposed information processing system is according to any one of claims 1 to 3, which includes the evaluation results in descending order of the evaluation scores.

6. The first component has the function of receiving the composite route information and transmitting the composite route information to the third component, The system includes a function for receiving and providing a procedure manual, The aforementioned synthesis route information is selected from the above proposals. The composite route information includes the edge list, The aforementioned edge list includes the aforementioned edges, The aforementioned edge includes information that identifies the literature, The second component has the function of receiving a second instruction and transmitting the procedure to the third component. The large-scale language model has a function to generate the procedure document according to the second instruction, The third component includes a function to receive the composite route information and share it within the third component, a function to transmit the second instruction statement to the second component, and a function to receive the procedure document and transmit the procedure document to the first component. The first subcomponent has the function of creating a second list from the graph database based on a second query using the management system, The second list contains the aforementioned documents, The second subcomponent has the function of creating the second query and the second directive, The second query includes a query statement that collects the documents identified in the edge list into the second list, The second instruction statement includes the second instruction and the second list, The information processing system according to claim 2 or 3, wherein the second instruction includes an instruction to generate the procedure manual from the second list.

7. An information processing method having a first phase, The first phase comprises a first to a tenth step, In the first step of the first phase, the first component receives the first information and transmits the first information to the second component. The first information includes information and conditions that identify the substance, In the second step of the first phase, the second component receives the first information and shares the first information within the second component. The second component comprises a first subcomponent, a second subcomponent, and a third subcomponent. The first subcomponent is equipped with a function to perform processing using a database and a management system, In the third step of the first phase, the second subcomponent creates a first query and shares the first query within the second component. The first query includes a query statement relating to the synthesis route and synthesis conditions of the substance, In the fourth step of the first phase, the first subcomponent uses the management system to create a first list from the database based on a first query, and shares the first list within the second component. The first list includes information relating to the synthesis route information of the substance, In the fifth step of the first phase, the second subcomponent creates a set of instructions and sends the first instructions to the third component. The group of instructions includes the first instruction, The first instruction statement includes the first instruction, one of the composite route information selected from the first list, and the first information. The first instruction includes an instruction to evaluate the composite route information based on the conditions and generate an evaluation result, In the sixth step of the first phase, the third component receives the first instruction and generates the evaluation result using a large-scale language model. In the seventh step of the first phase, the third component transmits the evaluation result to the second component. In the eighth step of the first phase, the second component receives the evaluation result and shares the evaluation result within the second component. In the ninth step of the first phase, the third subcomponent prepares a proposal and sends the proposal to the first component. The above proposal includes the synthesis route information and the evaluation results, In the tenth step of the first phase, the first component is an information processing method that receives and provides the proposal.

8. An information processing method having the first phase and the second phase, The second phase follows the first phase, The second phase comprises the first to ninth steps, In the first step of the second phase, the first component receives the composite route information and transmits the composite route information to the second component. In the second step of the second phase, the second component receives the composite route information and shares the composite route information within the second component. In the third step of the second phase, the second subcomponent creates a second query and shares the second query within the second component. The second query includes a query statement that collects the documents identified in the edge list into a second list, The aforementioned edge list includes edges, The aforementioned edge includes information that identifies the literature, The second list contains the aforementioned documents, In the fourth step of the second phase, the first subcomponent uses the management system to create the second list from the database based on the second query, and shares the second list within the second component. In the fifth step of the second phase, the second subcomponent creates a second instruction and transmits the second instruction to the third component. The second instruction statement includes the second instruction and the second list, The second instruction includes an instruction to generate a procedure manual from the second list, In the sixth step of the second phase, the third component receives the second instruction and generates the procedure using the large-scale language model. In the seventh step of the second phase, the third component transmits the procedure to the second component. In the eighth step of the second phase, the second component receives the procedure and transmits it to the first component. The information processing method according to claim 7, wherein in the ninth step of the second phase, the first component receives and provides the procedure manual.

Images