Information processing method, computer program, and information processing device

Abstract

The present invention provides an information processing method, a computer program, and an information processing device for acquiring information desired by a user.　The present invention involves: inputting, into a language generation model, a request for creating related data including a question sentence for subject data related to a specific device or system, a summary of the subject data, or a question sentence for the summary; acquiring the related data output by the language generation model; storing the subject data and the related data into a database in association with each other; acquiring a question related to the device or system; retrieving related data from the database on the basis of the question; extracting subject data associated with the retrieved related data from the database; inputting the question and the extracted subject data into the language generation model; acquiring a response to the question output by the language generation model; and outputting the acquired response.

Description

Information processing method, computer program, and information processing device

[0001] The present disclosure relates to an information processing method, a computer program, and an information processing device.

[0002] When performing some work such as operation or maintenance of some device, such as a machine tool, it may be desirable to refer to information about the device. For example, when cleaning the device, it is desirable to refer to information explaining the cleaning procedure. Similarly, when it comes to a system including multiple devices, it may be desirable to refer to information about the system. Patent Document 1 discloses a technology for displaying information useful for work related to a substrate processing apparatus that performs processes such as etching or film formation on substrates, such as semiconductor wafers or glass substrates.

[0003] JP 2014-164482 A

[0004] Information about a device or system is contained in data containing a large amount of information, such as a manual. Users can search for and use desired information from the data. However, using conventional search methods such as using keywords can sometimes make it difficult for users to find the information they desire.

[0005] The present disclosure provides an information processing method, a computer program, and an information processing device for a user to obtain desired information.

[0006] An information processing method according to one aspect of the present disclosure inputs a request to create related data consisting of a question for target data related to a specific device or system, a summary of the target data, or a question for the summary, into a language generation model, obtains the related data output by the language generation model, associates the target data and the related data with each other and stores them in a database, obtains a question related to the device or system, searches the database for related data based on the question, extracts target data associated with the searched related data from the database, inputs the question and the extracted target data into a language generation model, obtains an answer to the question output by the language generation model, and outputs the obtained answer.

[0007] According to the present disclosure, it is possible to provide an information processing method, a computer program, and an information processing device for a user to obtain desired information.

[0008] FIG. 1 is a conceptual diagram showing an overview of an information processing method according to an embodiment. FIG. 2 is a block diagram showing an example of the internal configuration of an information processing device. FIG. 3 is a flowchart showing an example of a procedure for a process executed by an information processing device to store target data and related data in a database. FIG. 4 is a schematic diagram showing an example of original data and target data. FIG. 5 is a diagram showing another example of target data. FIG. 6 is a schematic diagram showing an example of the contents stored in a database. FIG. 7 is a flowchart showing an example of a procedure for a process executed by an information processing device to output an answer to a question from a user. FIG. 8 is a schematic diagram showing an example of an output answer.

[0009] The present disclosure will be described in detail below with reference to drawings illustrating embodiments thereof. It may be desirable to refer to various information regarding a particular apparatus or system. For example, the apparatus may be a substrate processing apparatus that performs processes such as etching or film formation on substrates, such as semiconductor wafers or glass substrates. For example, the system may include various devices used in connection with the substrate processing apparatus. The system may include devices that manage the substrate processing apparatus, such as devices that store recipes defining the processes performed in the substrate processing apparatus or that input and output data to and from the substrate processing apparatus, and devices that acquire and store log data recording the operation of the substrate processing apparatus. The system may also include a group controller that manages multiple substrate processing apparatuses. For example, when operating a substrate processing apparatus or system or performing maintenance or other work on the substrate processing apparatus or system, a user may want to refer to information regarding the operation or work, such as operating methods, work procedures, or precautions. Because data such as manuals for substrate processing apparatuses or systems contains a large amount of information, conventional search methods, such as using keywords, may not provide the desired information. For example, when information regarding cleaning the piping of a substrate processing apparatus is needed, information regarding cleaning parts other than the piping may be searched for. In this embodiment, an information processing method is used to obtain the desired information.

[0010] FIG. 1 is a conceptual diagram illustrating an overview of an information processing method according to this embodiment. Source data 11 related to a specific device or system exists. For example, the source data 11 may include a device or system manual, log data recording operation details, alarm information recording alarm history, troubleshooting records, or maintenance records. The troubleshooting records may include records of work performed in response to an alarm, such as alarm reception, part replacement, part reassembly, part cleaning, or sensor calibration, which may include details of work performed to restore the device or system in response to an alarm. From the source data 11, multiple target data 12 are generated. The target data 12 are data that users refer to. The target data 12 are generated by dividing the source data 11 or extracting portions of the source data 11. The target data 12 may also be generated by combining multiple elements extracted from the source data 11.

[0011] Target data 12 is input to a language generation model 21, and associated data 13 related to the target data 12 is output from the language generation model 21. The associated data 13 consists of a question sentence for the target data 12, a summary of the target data 12, or a question sentence for the summary. Using the language generation model 21, multiple associated data 13 are generated for one piece of target data 12. The target data 12 and the associated data 13 related to the target data 12 are stored in a database 22 in association with each other.

[0012] With the target data 12 and related data 13 stored in the database 22, a question from a user regarding the substrate processing apparatus or system is acquired. The related data 13 is searched for in the database 22 based on the question, and the target data 12 associated with the searched related data 13 is extracted from the database 22. The question and the extracted target data 12 are input to a language generation model 21, and an answer to the question is output from the language generation model 21. The answer corresponds to information regarding the substrate processing apparatus or system. For example, the answer may be information regarding the operation of the substrate processing apparatus or system, or information regarding work on the substrate processing apparatus or system.

[0013] The information processing method is executed by an information processing device. FIG. 2 is a block diagram showing an example of the internal configuration of the information processing device 3. The information processing device 3 executes the information processing method. The information processing device 3 is configured using a computer such as a personal computer or a server device. The information processing device 3 includes a calculation unit 31, a memory 32, a storage unit 33, a reading unit 34, an input unit 35, and a display unit 36. The calculation unit 31 is, for example, a processor and is configured using a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a multi-core CPU. The calculation unit 31 may also be configured using a quantum computer. The memory 32 stores temporary data generated in conjunction with calculations. The memory 32 is, for example, a RAM (Random Access Memory). The storage unit 33 is non-volatile and is, for example, a hard disk or non-volatile semiconductor memory. The reading unit 34 reads information from a recording medium 30 such as an optical disc or a portable memory.

[0014] The input unit 35 accepts input of data. The input unit 35 includes an operation unit that accepts input of information such as text by accepting operations from the user. The operation unit is, for example, a touch panel, a keyboard, or a pointing device. The input unit 35 may include an input interface that inputs various data from outside the information processing device 3. The display unit 36 ​​displays images. The display unit 36 ​​is, for example, a liquid crystal display or an EL display (Electroluminescent Display).

[0015] The calculation unit 31 causes the reading unit 34 to read the computer program 331 recorded on the recording medium 30, and stores the read computer program 331 in the storage unit 33. The calculation unit 31 executes processing to realize the functions of the information processing device 3 in accordance with the computer program 331. The computer program 331 may be a program product. The computer program 331 may be stored in the storage unit 33 in advance, or may be downloaded from outside the information processing device 3. In this case, the information processing device 3 does not need to be equipped with the reading unit 34.

[0016] The computer program 331 can be deployed to run on a single computer, or on multiple computers located at one site or distributed across multiple sites and interconnected by a communications network. That is, the information processing device 3 may be configured with multiple computers, and the computer program 331 may be executed on multiple computers connected via a communications network. The information processing device 3 may be configured using a cloud server.

[0017] The processing of each step described below for executing the information processing method can be executed by multiple computers. The processing of each step can also be executed by different computers. The processing of each step can also be executed using a virtual machine. The processing of each step may be executed by multiple calculation units. The processing of each step may also be executed by different calculation units.

[0018] The information processing device 3 includes a language generation model 21. The language generation model 21 is a trained model that is trained so that, when a prompt consisting of a command statement requesting some kind of answer and information accompanying the prompt are input, a sentence corresponding to the input prompt and information is output. For example, the language generation model 21 is a large-scale language model. More specifically, the language generation model 21 is BERT, GPT-4, Bard, LLaMA, or the like. The language generation model 21 is trained in advance.

[0019] The language generation model 21 is realized by the calculation unit 31 executing information processing in accordance with the computer program 331. The storage unit 33 stores data for realizing the language generation model 21. The language generation model 21 may be configured with hardware. The language generation model 21 may be realized using a quantum computer. Alternatively, the language generation model 21 may be provided outside the information processing device 3, and the information processing device 3 may execute processing using the external language generation model 21. The language generation model 21 may be realized using multiple computers connected via a communication network, or may be realized using the cloud.

[0020] The information processing device 3 includes a database 22. As described above, the database 22 is for storing the target data 12 and the related data 13. The database 22 is realized by the storage unit 33 storing necessary data. The database 22 may be configured using hardware other than the storage unit 33. The database 22 may be configured using multiple computers. For example, the data stored in the database 22 may be distributed and stored across multiple computers. Alternatively, the database 22 may be provided outside the information processing device 3, and the information processing device 3 may execute processing using the external database 22.

[0021] The information processing device 3 performs a process of storing the target data 12 and the related data 13 in the database 22. Fig. 3 is a flowchart showing an example of the procedure of the process executed by the information processing device 3 to store the target data 12 and the related data 13 in the database 22. Hereinafter, step will be abbreviated as S. The calculation unit 31 executes information processing in accordance with the computer program 331, causing the information processing device 3 to execute the following process.

[0022] The information processing device 3 acquires target data 12 (S11). Original data 11 is input to the information processing device 3 through the input unit 35 and stored in the memory unit 33, or the original data 11 is pre-stored in the memory unit 33, and multiple target data 12 are generated from the original data 11. FIG. 4 is a schematic diagram showing examples of the original data 11 and the target data 12. In the example shown in FIG. 4, the original data 11 is a manual for a substrate processing device and includes text relating to a method for cleaning pipes and a method for cleaning items other than pipes. The original data 11 is divided to generate multiple target data 12. In the example shown in FIG. 4, target data 12 including only text relating to a method for cleaning pipes and target data 12 including only text relating to a method for cleaning items other than pipes are generated from the original data 11.

[0023] 5 is a diagram showing another example of the target data 12. The target data 12 shown in FIG. 5 is data in a table format. For each module such as the piping of the substrate processing apparatus, a task item such as cleaning and a reference time that is a reference value for the task time are recorded. In this way, the target data 12 consisting of text or the target data 12 in a table format is generated from the original data 11. The target data 12 in a graph format may also be generated.

[0024] The calculation unit 31 generates target data 12 consisting of sentences, for example, by dividing the original data 11 by chapter, item, page, or paragraph. The calculation unit 31 generates tabular target data 12 by extracting tables included in the original data 11. The calculation unit 31 may display the contents of the original data 11 on the display unit 36 ​​and generate the target data 12 in accordance with instructions input by a user who has confirmed the contents of the original data 11. For example, the calculation unit 31 receives an instruction specifying positions to divide the original data 11 or portions to be extracted from the original data 11 by the user operating an operation unit included in the input unit 35. The calculation unit 31 generates target data 12 by dividing the original data 11 or extracting portions from the original data 11 in accordance with the received instruction. The calculation unit 31 may receive designation of multiple contents to be extracted from the original data 11, extract the specified multiple contents from the original data 11, and combine the extracted multiple contents to generate target data 12 consisting of sentences or tabular target data 12. In this way, a plurality of target data 12 are generated, each of which contains only a portion of the information contained in the original data 11.

[0025] The information processing device 3 may receive, via the input unit 35, input of a plurality of pieces of target data 12 that have already been generated. The calculation unit 31 stores the generated plurality of pieces of target data 12 or the input plurality of pieces of target data 12 in the storage unit 33. In S11, the calculation unit 31 reads out the target data 12 from the storage unit 33 to acquire the target data 12.

[0026] The information processing device 3 inputs a request to generate associated data 13 related to the target data 12 to the language generation model 21 (S12). The associated data 13 is a question for the target data 12, a summary of the target data 12, or a question for the summary. In S12, the calculation unit 31 generates a prompt including the target data 12 and a request to generate the associated data 13, and inputs the generated prompt to the language generation model 21.

[0027] Examples of prompts that the calculation unit 31 inputs to the language generation model 21 in S12 are shown below: "Please create a question that can be answered using only the target data below. {target data}" "Please create a summary of the target data below using text that is no more than one-tenth the length of the original text. {target data}" "Please create a summary of the target data below using text that is no more than one-tenth the length of the original text, and create a question that can be answered using only the created summary. {target data}" The position of {target data} included in the example prompts includes the target data 12. The calculation unit 31 may input to the language generation model 21 a prompt that includes, instead of the target data 12, information for referencing the target data 12, such as the address where the target data 12 is stored.

[0028] When generating a question regarding the summary of the target data 12 as the related data 13, the calculation unit 31 may use a prompt including a summary of the target data 12 generated using the language generation model 21 instead of the target data 12. An example of the prompt is shown below: "Please create a question that can be answered using only the summary below. {Summary}" The {Summary} included in the example prompt includes the summary of the target data 12 generated using the language generation model 21. The prompt may include information for referencing the summary instead of the summary. If the target data 12 is tabular data, the calculation unit 31 may create text data representing the contents of the tabular target data 12, such as data written down in text form of the contents of the tabular target data 12, explanatory text explaining the contents of the target data 12, or data converted from the target data 12 into Markdown format, and include the text data in the prompt.

[0029] The language generation model 21 performs calculations and outputs sentences in response to the input of a prompt. The prompt input to the language generation model 21 includes a request to generate associated data 13 related to the target data 12, so the language generation model 21 outputs the associated data 13 corresponding to the target data 12. The output associated data 13 is a question regarding the target data 12, a summary of the target data 12, or a question regarding the summary.

[0030] The information processing device 3 acquires associated data 13 related to the target data 12 (S13). In S13, the calculation unit 31 acquires the associated data 13 output by the language generation model 21. The calculation unit 31 repeats the processes of S12 and S13 for one piece of target data 12 to acquire multiple pieces of associated data 13 related to the one piece of target data 12. For example, the calculation unit 31 causes the language generation model 21 to generate multiple pieces of associated data 13 using multiple types of prompts as described above. The calculation unit 31 also repeats the processes of S12 and S13 for each piece of target data 12 to acquire multiple pieces of associated data 13 related to each piece of target data 12. The calculation unit 31 may select, as the associated data 13 to acquire, one of the following types: a question regarding the target data 12, a summary of the target data 12, and a question regarding the summary. For example, the calculation unit 31 may select a type or a combination of multiple types of associated data 13 to acquire, or may acquire all types of associated data 13, in accordance with instructions from a user.

[0031] The information processing device 3 stores the target data 12 and the associated data 13 in the database 22 (S14). In S14, the calculation unit 31 associates the target data 12 with the associated data 13 related to the target data 12 and stores them in the database 22. At this time, the calculation unit 31 associates the multiple associated data 13 acquired for one piece of target data 12 with the one piece of target data 12.

[0032] 6 is a schematic diagram showing an example of the contents stored in the database 22. The database 22 stores a plurality of target data 12, and each target data 12 is associated with a plurality of related data 13. For example, the target data 12 containing information on a method for cleaning pipes is associated with a plurality of related data 13 that are questions about the target data 12, such as "How do you clean pipes?" or "Should you wear gloves when cleaning pipes?" The target data 12 may be associated with a summary of the target data 12 or a question about the summary as the related data 13.

[0033] In S14, the calculation unit 31, for example, vectorizes the target data 12 and the related data 13 and stores them in the database 22. The calculation unit 31 may select, as the related data 13 to be stored in the database 22, a question regarding the target data 12, a summary of the target data 12, or a question regarding the summary. For example, the calculation unit 31 may select, in accordance with an instruction from a user, a type or a combination of multiple types of related data 13 to be stored in the database 22, or may store all types of related data 13 in the database 22. After S14 is completed, the information processing device 3 terminates the process of storing the target data 12 and the related data 13 in the database 22. The processes of S11 to S14 are executed as needed.

[0034] With the target data 12 and related data 13 stored in the database 22, the information processing device 3 performs processing to output an answer to a question from a user based on the database 22. Fig. 7 is a flowchart showing an example of the procedure of processing to output an answer to a question from a user, which is executed by the information processing device 3. The calculation unit 31 executes information processing in accordance with the computer program 331, causing the information processing device 3 to execute the following processing.

[0035] The information processing device 3 acquires a question from the user (S21). In S21, the user operates an operation unit included in the input unit 35 to input a question from the user to the information processing device 3, and the calculation unit 31 acquires the input question. The question may be input by voice input. The question from the user is a question about the substrate processing device or system. In other words, the question from the user is a question about information included in the original data 11. The calculation unit 31 stores the acquired question in the memory unit 33.

[0036] The information processing device 3 searches the database 22 for related data 13 based on the acquired question (S22). In S22, the calculation unit 31 searches for related data 13 that has a high similarity to the acquired question from among the multiple related data 13 stored in the database 22. For example, the calculation unit 31 vectorizes the acquired question, calculates the similarity between the vectorized question and the multiple vectorized related data 13, and searches for the related data 13 with the highest similarity. The calculation unit 31 calculates, for example, cosine similarity or similarity based on Euclidean distance as the similarity. By using the similarity, it is possible to search for related data 13 that is similar to the acquired question. The calculation unit 31 may search for related data 13 using a method other than the method of calculating similarity, such as performing morphological analysis to search for related data 13 that has a meaning closest to the question.

[0037] The calculation unit 31 may select, as the related data 13 to be searched, a type of question for the target data 12, a summary of the target data 12, or a question for the summary. For example, the calculation unit 31 may select a type or a combination of multiple types of related data 13 to be searched for, or may search for all types of related data 13, in accordance with an instruction from the user.

[0038] The information processing device 3 extracts target data 12 associated with the searched associated data 13 from the database 22 (S23). In S23, the calculation unit 31 extracts target data 12 stored in the database 22 in association with the searched associated data 13. That is, the target data 12 is extracted in accordance with the question. For example, a question such as "Do I need to wear gloves when cleaning pipes?" is acquired in S21, and in S22, the associated data 13 such as "Do I wear gloves when cleaning pipes?" included in the example shown in FIG. 6 is searched for. In S23, the target data 12 including information on a pipe cleaning method, included in the example shown in FIG. 6, is extracted.

[0039] In S22 and S23, the calculation unit 31 may search the database 22 for target data 12 based on the question, and extract the searched target data 12 from the database 22. For example, the calculation unit 31 may search the database 22 for target data 12 that has a high similarity to the question. Even when performing this process, the information processing device 3 can acquire appropriate target data 12 as the basis for answering the question from the user.

[0040] The information processing device 3 inputs the question from the user and the extracted target data 12 to the language generation model 21 (S24). In S12, the calculation unit 31 generates a prompt including a request to answer the question based on the extracted target data 12, and inputs the generated prompt to the language generation model 21.

[0041] An example of a prompt that the calculation unit 31 inputs to the language generation model 21 in S24 is shown below: "Please answer the following question based on the following target data: {question} {target data}" In the example prompt, the position of {question} includes the question acquired in S21, and the position of {target data} includes the target data 12 extracted in S23. The calculation unit 31 may input to the language generation model 21 a prompt that includes, instead of the target data 12, information for referencing the target data 12, such as an address in the database 22 where the target data 12 is stored.

[0042] The language generation model 21 performs calculations in response to the input of a prompt and outputs an answer to the question. The prompt input to the language generation model 21 includes a request to answer the question based on the target data 12, so the language generation model 21 outputs an answer based on the target data 12. For example, in response to the question "Do I need to wear gloves when cleaning pipes?", the answer "You need to wear gloves" is output based on the target data 12, which includes information on a pipe cleaning method, as included in the example shown in FIG. 6.

[0043] The information processing device 3 acquires an answer to the question from the user (S25). In S25, the calculation unit 31 acquires the answer output by the language generation model 21. The calculation unit 31 stores the acquired answer in the storage unit 33. The information processing device 3 outputs the acquired answer (S26). In S26, the calculation unit 31 outputs the answer by displaying an image including the acquired answer on the display unit 36.

[0044] The calculation unit 31 may output the related data 13 searched for in S22 in addition to the answer by displaying on the display unit 36 ​​an image including the related data 13 searched for in S22. By outputting the searched related data 13, the user can determine whether the searched related data 13 is data that is far removed from the question. If the searched related data 13 is data that is far removed from the question, there is a high possibility that the answer to the question is incorrect.

[0045] The calculation unit 31 may output the target data 12 extracted in S23 in addition to the answer by displaying an image including the target data 12 extracted in S23 on the display unit 36. By outputting the extracted target data 12, the user can confirm the information on which the answer is based. The calculation unit 31 may output information for referencing the target data 12 extracted in S23, such as a link to the target data 12 stored in the database 22. In this case, the user can also confirm the information on which the answer is based.

[0046] FIG. 8 is a schematic diagram illustrating an example of an output answer. FIG. 8 shows an example of an image including an answer displayed on the display unit 36. The image includes a field for inputting a question, and the question, "Do I need to wear gloves when cleaning pipes?" is input. The image includes the answer to the question, "You need to wear gloves." The image also includes the contents of the searched related data 13 and a link to the extracted target data 12. In this way, the answer, the searched related data 13, and the link to the extracted target data 12 are output. The user can confirm the desired answer to the question by visually checking the image displayed on the display unit 36. The user can also confirm the contents of the searched related data 13 and the contents of the target data 12 using the link to the target data 12.

[0047] In addition to the answer, the calculation unit 31 may output the original data 11 that was the basis for the target data 12 extracted in S23. For example, the memory unit 33 stores the original data 11, and the calculation unit 31 displays an image including the original data 11 that was the basis for the target data 12 on the display unit 36. A portion of the original data 11 that is the basis for the target data 12 may be output. For example, a page corresponding to the content of the target data 12 may be displayed in the original data 11, which is a manual, or the original data 11 may be displayed with the portion corresponding to the content of the target data 12 highlighted. The calculation unit 31 may output information for referencing the original data 11, such as a link to the original data 11 stored in the memory unit 33. In these forms, the user can confirm the source of the information that was the basis for the answer.

[0048] After S26 is completed, the information processing device 3 ends the process of outputting a response to the question from the user. The processes of S21 to S26 are executed as needed. For example, every time the user needs information about the substrate processing device or the system, the user inputs a question into the information processing device 3, and the processes of S21 to S26 are executed. For example, the processes of S21 to S26 are repeated in response to an operation by the user.

[0049] After S26 is completed, the information processing device 3 may perform a process to acquire a response from the user to the output answer. The response is, for example, information indicating that the user is satisfied with the answer. The user operates an operation unit included in the input unit 35 to input the response from the user to the information processing device 3, and the information processing device 3 acquires the response. When the calculation unit 31 outputs an answer to a question and acquires a response indicating that the user is satisfied with the answer, the calculation unit 31 may store the question in the database 22 in association with the target data 12 extracted in S23. Thereafter, the question stored in the database 22 is used as one of the related data 13 related to the target data 12. This process increases the related data 13 related to the target data 12, making it easier to extract appropriate target data 12 according to the question.

[0050] As described above in detail, the information processing device 3 creates associated data 13 related to the target data 12 that is created from the original data 11 and is the target of reference by the user, and stores the target data 12 and the associated data 13 in association with each other in the database 22. The associated data 13 consists of a question sentence for the target data 12, a summary of the target data 12, or a question sentence for the summary, and is generated using the language generation model 21. By using the language generation model 21, the associated data 13 that reflects the content of the target data 12 can be easily generated.

[0051] The information processing device 3 acquires a question from a user, searches the database 22 for related data 13 based on the question, and extracts target data 12 associated with the searched related data 13. The information processing device 3 acquires an answer to the question using a language generation model 21 based on the extracted target data 12. A question sentence for the target data 12 to be referenced in order to answer the user's question, a summary of the target data 12, or a question sentence for the summary may contain content similar to the user's question. Therefore, by extracting from the database 22 the target data 12 associated with related data 13 similar to the question, it is possible to select the target data 12 to be referenced in order to answer the question. Since an answer is obtained using the language generation model 21 based on the target data 12 to be referenced in order to answer the question, an appropriate answer according to the question can be obtained.

[0052] Since appropriate answers are obtained for questions from users, the user can obtain necessary information by inputting questions about the substrate processing apparatus or system and obtaining answers. For example, when information about a pipe cleaning method is to be obtained from the original data 11 shown in FIG. 4 , a conventional search method using keywords may result in information about cleaning methods other than those for pipes. In this embodiment, in response to a question about a pipe cleaning method, target data 12 about the pipe cleaning method is extracted from multiple target data 12, and an answer about the pipe cleaning method is obtained based on the extracted target data 12. In this way, the user can easily obtain desired information about the substrate processing apparatus or system.

[0053] In the present embodiment, an example has been mainly shown in which the original data 11 and the target data 12 are data containing information about a substrate processing apparatus or a system related to the substrate processing apparatus. Alternatively, the original data 11 and the target data 12 may be data containing information about an apparatus other than a substrate processing apparatus, such as a machine tool, or a system related to the apparatus. In the present embodiment, an example has been shown in which the same language generation model 21 is used in the processes of S11 to S14 and S21 to S26, but different language generation models may be used in the processes of S11 to S14 and S21 to S26.

[0054] In the present embodiment, the process of S11 to S14 and the process of S21 to S26 are executed by the same information processing device 3, but the process of S11 to S14 and the process of S21 to S26 may be executed by different information processing devices. For example, one information processing device may execute the process of S11 to S14 to create the database 22, and another information processing device may execute the process of S21 to S26 using the created database 22. For example, an information processing device used by a business providing an information search service may execute the process of S11 to S14 to create the database 22, and an information processing device used by a user of the service may execute the process of S21 to S26 using the database 22.

[0055] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. In other words, embodiments obtained by combining technical means modified appropriately within the scope of the claims are also included in the technical scope of the present invention.

[0056] The matters described in each embodiment can be combined with each other. Furthermore, the independent claims and dependent claims described in the claims can be combined with each other in any and all combinations, regardless of the reference format. Furthermore, the claims do not use a format in which a claim references two or more other claims (multiple claim format), but this is not limited to this. They may be written using a multiple claim format or a format in which multiple claims (multi-multi claim) reference at least one other multiple claim.

[0057] REFERENCE SIGNS LIST 11 Original data 12 Target data 13 Related data 21 Language generation model 22 Database 3 Information processing device 30 Recording medium 31 Calculation unit 33 Storage unit 331 Computer program

Claims

1. An information processing method comprising: inputting a request to create related data consisting of a question for target data related to a specific device or system, a summary of the target data, or a question for the summary, into a language generation model, obtaining the related data output by the language generation model, correlating the target data and the related data with each other and storing them in a database, obtaining a question related to the device or system, searching the database for related data based on the question, extracting target data associated with the searched related data from the database, inputting the question and the extracted target data into a language generation model, obtaining an answer to the question output by the language generation model, and outputting the obtained answer.

2. The information processing method according to claim 1, further comprising the steps of: acquiring a plurality of pieces of related data relating to a plurality of pieces of target data; and storing each piece of target data and each piece of related data relating to the target data in the database in association with each other.

3. The information processing method according to claim 1, further comprising the step of searching for related data having a high similarity to said question when searching for related data.

4. The information processing method according to claim 1, further comprising the steps of: searching for target data from the database based on the question; inputting the question and the searched target data into a language generation model; and obtaining an answer to the question output by the language generation model.

5. The information processing method according to claim 1, further comprising obtaining a response to the output answer, and if a response indicating satisfaction with the answer to the question is obtained, storing the question in the database in association with the extracted target data.

6. The information processing method according to claim 1, further comprising the step of outputting the retrieved related data together with the obtained answer.

7. The information processing method according to claim 1, further comprising the step of outputting the extracted target data, a link to the target data, original data from which the target data was created, or a link to the original data together with the obtained answer.

8. The information processing method according to claim 1, wherein the target data is data created from a manual for the device or the system, or tabular data relating to the device or the system.

9. The information processing method according to claim 1, wherein the apparatus is a substrate processing apparatus and the system is a system including equipment used in connection with the substrate processing apparatus, and information relating to the operation of the apparatus or the system, or information relating to work on the apparatus or the system, is output as a response.

10. A computer program that causes a computer to perform the following processes: inputting a request to create related data consisting of a question for target data related to a specific device or system, a summary of the target data, or a question for the summary, into a language generation model, obtaining the related data output by the language generation model, correlating the target data and the related data with each other and storing them in a database, obtaining a question related to the device or system, searching the database for related data based on the question, extracting target data associated with the searched related data from the database, inputting the question and the extracted target data into a language generation model, obtaining an answer to the question output by the language generation model, and outputting the obtained answer.

11. A computer program that causes a computer to execute the following processes: obtain a question about a specific device or system; search a database in which target data about the device or system is stored in association with related data consisting of a question for the target data, a summary of the target data, or a question for the summary, for related data based on the question; extract from the database target data associated with the searched related data; input the question and the extracted target data into a language generation model, obtain an answer to the question output by the language generation model, and output the obtained answer.

12. An information processing device comprising a calculation unit that: inputs a request to create related data consisting of a question for target data related to a specific device or system, a summary of the target data, or a question for the summary, to a language generation model; obtains the related data output by the language generation model; associates the target data and the related data with each other and stores them in a database; obtains a question related to the device or system; searches the database for related data based on the question; extracts target data associated with the searched related data from the database; inputs the question and the extracted target data to a language generation model; obtains an answer to the question output by the language generation model; and outputs the obtained answer.