Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device for efficiently operating services using automatically generated AI.SOLUTION: An information processing device includes a receiving unit, a determination unit, a generation unit, and an execution unit. The receiving unit receives a sentence in natural language representing an execution instruction input by a user. The determination unit determines whether or not execution information for executing a process corresponding to the execution instruction of the sentence received by the receiving unit is cached. When the determination unit determines that the execution information is not cached, the generation unit generates the execution information using a model that has been trained to generate an answer to a question. The execution unit executes the process using the cached execution information or the execution information generated by the generation unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, automatic response services such as chatbots are becoming more and more popular. For example, a technology has been proposed for such services that extracts questions similar to a question input by a user and their answers from a database, and provides the extracted answers to the user (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2019 / 185578 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional technology did not take into consideration the use of models that generate sentences (so-called automatic generation AI). For example, when using such models, fees are charged according to the amount and number of prompts, so efficient operation is required.

[0005] The present invention has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that enable efficient operation in services using automatically generated AI. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, an information processing device according to the present invention includes a receiving unit, a determining unit, a generating unit, and an executing unit. The receiving unit receives a sentence in a natural language indicating an execution instruction input by a user. The determining unit determines whether execution information for executing a process corresponding to the execution instruction of the sentence received by the receiving unit is cached. If the determining unit determines that the execution information is not cached, the generating unit generates the execution information using a model that has been trained to generate an answer to a question. The executing unit executes the process using the cached execution information or the execution information generated by the generating unit. Effect of the Invention

[0007] According to the present invention, appropriate content can be provided to a user. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a user interface according to the embodiment. [Diagram 3] FIG. 3 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in a prompt dictionary storage unit according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of information stored in an API request storage unit according to the embodiment. [Figure 6] FIG. 6 is an explanatory diagram of a process for generating an extended prompt according to the embodiment. [Figure 7] FIG. 7 is an explanatory diagram of a process for generating an extended prompt according to the embodiment. [Figure 8] FIG. 8 is an explanatory diagram of a process for generating an extended prompt according to the embodiment. [Figure 9] FIG. 9 is an explanatory diagram of a process for generating an extended prompt according to the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of an extended prompt according to the embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of a response to an extended prompt according to the embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of the answer screen according to the embodiment. [Figure 13] FIG. 13 is a flowchart illustrating an example of a providing process according to the embodiment. [Figure 14] FIG. 14 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments.

[0010] [Embodiment] [1. Information Processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that the information processing according to the embodiment is realized by an information processing device 1 shown in Fig. 1.

[0011] 1 is a server device operated by an electronic payment service for electronic money payments for each user. In this embodiment, the information processing device 1 provides an automatic response service that generates answers to questions posed to the user.

[0012] For example, the information processing device 1 can receive questions about the amount of electronic money used, questions about coupons and stores, questions about person-to-person transfer of electronic money, and the like. For example, these questions require executing one of a plurality of APIs (Application Programming Interfaces) to acquire data. In this embodiment, as described later, an API request (a query for executing an API) is generated using a second model M2. Note that the second model M2 is a GPT (Generative Pretrained Transformer) model.

[0013] The user terminal 100 shown in Fig. 1 is an information processing device used by a user. The user terminal 100 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. The user terminal 100 displays information distributed by the information processing device 1 and the server device 200 using a web browser or an application. In the example shown in Fig. 1, the user terminal 100 is a smartphone.

[0014] 1 is an information processing device that provides electronic payment services related to electronic payments using the user terminal 100 and performs various payments. The server device 200 manages accounts of providers (businesses) of transaction objects and users to whom transaction objects are provided, and realizes various payments by transferring electronic money between accounts in response to a payment request from a user.

[0015] Here, prior to the provision process executed by the information processing device 1, an example of payment (electronic payment) using the user terminal 100 will be described. In the following description, an example will be described in which a user makes a payment using the user terminal 100 by using a two-dimensional code (QR code (registered trademark)) placed in store A, which indicates store identification information for identifying store A, but the embodiment is not limited to this. The example of payment described below is also applicable to a case in which an arbitrary user makes a payment at an arbitrary store using an arbitrary user terminal 100. In addition, the store identification information may be not only a QR code, but also a barcode, a predetermined mark, a number, or the like.

[0016] For example, when a user makes a payment for using or purchasing a payment object (transaction object) such as various products or services at store A, the user launches a payment app pre-installed in the user terminal 100. The user then photographs the store identification information installed in store A via the payment app. In such a case, the user terminal 100 displays a screen for inputting the price of the payment object, and accepts input of the payment amount from the user or a clerk at store A. The user terminal 100 then transmits to the server device 200 the user identification information that identifies the user, the store identification information (or information indicated by the store identification information, i.e., information indicating store A (or the operator of store A) (e.g., a store ID), and payment information indicating the payment amount.

[0017] In such a case, the server device 200 transfers electronic money in the amount indicated by the payment amount from the user's account indicated by the user identification information to the account of store A indicated by the store identification information. Then, the server device 200 transmits a notification that the payment has been completed to the user terminal 100. In such a case, the user terminal 100 notifies the user that the payment has been made with electronic money by outputting a screen or a predetermined sound indicating that the payment has been completed.

[0018] A more detailed example will be described. For example, the store identification information installed in the store A is a URL set for each store, and is linked to group identification information indicating a group to which the store A belongs and group store identification information identifying the store A in the group, and is managed so that the server device 200 can refer to it. The URL serving as the store identification information is a URL for accessing the server device 200. When the user terminal 100 photographs the store identification information, it accesses the URL indicated by the photographed store identification information and transmits the user identification information. In such a case, the server device 200 identifies the group identification information corresponding to the accessed URL, and identifies the electronic money account (sometimes displayed as a "wallet") associated with the identified group identification information. Next, the server device 200 causes the user terminal 100 to display an amount input screen and cause the user to input an amount. Then, the server device 200 identifies the group identification information from the wallet associated with the user identification information received from the user terminal 100, and transfers the input amount of electronic money to the wallet associated with the identified group identification information. The server device 200 may transfer the electronic money to a wallet associated with the group identification information and the group store identification information.

[0019] It should be noted that the payment using the user terminal 100 is not limited to the above-mentioned process. For example, the payment using the user terminal 100 may be made using a store terminal installed in store A. For example, the user terminal 100 displays user identification information for identifying the user on a screen. In such a case, the store terminal installed in store A reads the user identification information displayed on the user terminal 100, and transmits payment information indicating the user identification information (or information indicated by the user identification information, i.e., information indicating the user (e.g., user ID), the payment amount, and information identifying store A) to the server device 200. In such a case, the server device 200 may transfer electronic money in an amount indicated by the payment amount from the user's account indicated by the user identification information to the account of store A, and notify the store terminal of store A or the user terminal 100 that the payment has been completed by outputting a screen or a predetermined sound indicating that the payment has been completed.

[0020] More specifically, the user terminal 100 transmits a payment request to the server device 200 together with the user identification information. In such a case, the server device 200 generates a one-time code, links the generated one-time code to the user identification information, and transmits the one-time code to the user terminal 100. The user terminal 100 then displays the one-time code (i.e., information identifying the user) on the screen. In such a case, the store terminal reads the one-time code displayed on the user terminal 100 and transmits the read one-time code, group identification information, group store identification information, and payment amount to the server device 200. The server device 200 then transfers electronic money equivalent to the payment amount from the wallet linked to the user identification information linked to the one-time code to the wallet linked to the group identification information and group store identification information.

[0021] Furthermore, the payment using the user terminal 100 may not only be a process of transferring electronic money from an account to which the user has previously charged electronic money to an account of store A, but may also be a payment using, for example, a credit card registered by the user in advance. In such a case, for example, the user terminal 100 may transfer electronic money of the payment amount to the account of store A, and may also bill the operating company (card company) of the user's credit card for the payment amount.

[0022] In recent years, a model trained to generate answers to questions (so-called auto-generation AI) has been attracting attention. In this embodiment, such a model is utilized to provide an auto-reply service.

[0023] In such an auto-reply service, when it is necessary to execute a process to respond to a question from a user, it is necessary to convert the text entered by the user into a format compatible with the corresponding API.

[0024] In this embodiment, the above format conversion is performed using an auto-generation AI (first and second models, which will be described later).

[0025] 1, the information processing device 1 receives a question from a user via the user terminal 100 (step S1). The question is a sentence in a natural language, and the information processing device 1 can receive the question via a UI, which will be described later with reference to FIG.

[0026] The information processing device 1 generates a prompt to be input to the first model (step S2). The first model is a model such as GPT or BERT (Bidirection Encoder Representation from Transformers). The first model is an example of an internal model.

[0027] In this embodiment, the information processing device 1 performs prompt engineering using the first model to generate an extended prompt from a question by a user. Note that prompt engineering is a process for optimizing the contents of a prompt.

[0028] As will be described later, the information processing device 1 generates an extended prompt by inputting a prompt into the first model. That is, in this embodiment, a desired answer can be obtained from a second model M2, which will be described later, by performing prompt engineering using the first model. The generation of an extended prompt will be described later with reference to Figs. 6 to 10.

[0029] Next, the information processing device 1 inputs the generated extension prompt to a second model M2 outside the information processing device 1 (step S3), and obtains an answer corresponding to the extension prompt from the second model M2 (step S4). The above-mentioned extension prompt includes an instruction sentence that causes the second model M2 to generate an answer in an API format, and the answer obtained from the second model M2 is in, for example, a JSON format.

[0030] In this way, the information processing device 1 can convert the natural language sentence by the user into the JSON format, which is the API format, using the second model M2. That is, the information processing device 1 can obtain the answer of the second model M2 to the extended prompt as an API request.

[0031] Then, the information processing device 1 registers the answer (API request) acquired from the second model M2 in the cache (step S5). For example, the information processing device 1 tags the answer acquired from the second model M2 with the question by the user and registers it in the cache. For example, the information processing device 1 extracts words from the question entered by the user by morphological analysis or the like, and registers these words as tags in the cache, linking them to the answer acquired from the second model M2. Note that the information processing device 1 may omit the process of registering in the cache when an answer corresponding to a past tag corresponding to the current tag has already been registered in the cache.

[0032] After that, the information processing device 1 generates an API request based on the answer acquired from the second model M2 (step S6). The API request is an example of execution information, and includes various parameters for executing the API.

[0033] Next, the information processing device 1 executes the API by providing an API request to the server device 200 (step S7). As a result, the server device 200 outputs content according to the API request to the information processing device 1 (step S8).

[0034] At this time, the information processing device 1 provides the API request to the server device 200 by adding an identifier (for example, a user ID) of the user who is the questioner. In other words, the information processing device 1 generates an API request without passing the user's identification information to the external second model M2. This allows the information processing device 1 to protect the user information.

[0035] Then, the information processing device 1 provides a response to the user terminal 100 based on the content acquired from the server device 200 (step S9). A specific example of the response that the information processing device 1 provides to the user will be described later with reference to FIG.

[0036] In this way, the information processing device 1 according to the embodiment uses the first model to generate an extended prompt from a question sentence by a user, and inputs the generated extended prompt into the second model M2 to obtain an answer to the API request from the second model M2.

[0037] That is, the information processing device 1 can automatically convert a natural language sentence input by a user into an API request by using a model such as GPT or BERT. Then, the information processing device 1 can appropriately execute a process corresponding to the natural language sentence input by the user by executing a process corresponding to the API request.

[0038] Furthermore, when the information processing device 1 receives a new question, it generates a tag indicating the content of the question and searches the cache for a corresponding API request based on the tag. If the API request corresponding to the tag is cached, the information processing device 1 executes processing using the API request, and if the API request corresponding to the tag is not cached, the information processing device 1 generates an API request using the second model M2 based on the first and second prompts as described above, and executes processing.

[0039] In other words, the information processing device 1 can reduce the frequency of use of the second model M2 by linking the API request with a tag and registering it in the cache. This can reduce the usage fee for the second model M2, allowing for efficient operation.

[0040] Next, a user interface for accepting a question from a user will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of a user interface according to an embodiment. The information processing device 1 accepts a question from a user through a payment application provided by the server device 200.

[0041] 2, a QR code and selection buttons for selecting each application are displayed on the home screen HG of the payment app. For example, when the user selects selection button B, the screen transitions from the home screen HG to a chat screen CG.

[0042] As shown in FIG. 2, the talk screen CG displays a tutorial area C that displays a tutorial on functions, a possible question Q where the user can select a question, and an input area A where the user can input a question in text.

[0043] The information processing device 1 accepts a question in natural language from the user by the user selecting an expected question Q or inputting a sentence into the input area A. Then, the information processing device 1 provides an answer to the question in a chat format through a talk screen CG.

[0044] [2. Information Processing Device] Next, a configuration example of the information processing device 1 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in Fig. 3, the information processing device 1 includes a communication unit 2, a storage unit 3, and a control unit 4. Note that the information processing device 1 may also include an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator who uses the information processing device 1, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0045] The communication unit 2 is realized by, for example, a network interface card (NIC) etc. The communication unit 2 is connected to a communication network such as 4G (4th Generation) or 5G (5th Generation) by wire or wirelessly, and transmits and receives information to and from each of the user terminal 100, the server device 200, etc. via the communication network.

[0046] The storage unit 3 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 3 includes a prompt dictionary storage unit 31, an API request storage unit 32, and a first model storage unit 33.

[0047] The prompt dictionary storage unit 31 stores a prompt dictionary. The prompt dictionary is a dictionary related to the first prompt and the second prompt described above. Fig. 4 is a diagram showing an example of information stored in the prompt dictionary storage unit 31 according to the embodiment.

[0048] As shown in Fig. 4, the prompt dictionary storage unit 31 stores information items such as "category question", "category" and "API question" in association with each other. The "category question" is a question used to ask the first model about a category corresponding to a user's question. Specific examples of category questions will be described later with reference to Fig. 6.

[0049] In the example shown in FIG. 4, all API questions are of the same category, “category question #1.” However, the prompt dictionary storage unit 31 may store a plurality of patterns of category questions.

[0050] "Category" indicates the category of the sentence input by the user. Specific examples of categories will be described later with reference to FIG. 6. "API question" is a sentence for asking the first model about the type of API for executing the process corresponding to the user's question or the type of value to be obtained. The API question also includes an answer format corresponding to each API. In the example of FIG. 4, the prompt dictionary storage unit 31 stores one API question in association with one category, but it may also store multiple API questions in association with one category.

[0051] Returning to the explanation of Fig. 3, the API request storage unit 32 will be explained. The API request storage unit 32 stores the API request generated by the second model M2. The API request storage unit 32 corresponds to an example of a cache.

[0052] Fig. 5 is a diagram illustrating an example of information stored in the API request storage unit 32 according to the embodiment. As illustrated in Fig. 5, the API request storage unit 32 stores information items such as "tag" and "API request" in association with each other.

[0053] "Tag" is a tag indicating the content of the question by the user. "API request" is an API request generated by the second model M2. That is, every time a new API request is generated by the second model M2, the new API request is accumulated in the API request storage unit 32.

[0054] Returning to the description of FIG. 3, the first model storage unit 33 will be described. The first model storage unit 33 stores the first model. As described above, the first model is a model trained to generate an answer to a sentence in a natural language, such as GPT or BERT. In this embodiment, the first model is a model used to perform the above-mentioned prompt engineering.

[0055] Next, the control unit 4 will be described. The control unit 4 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM as a working area. The control unit 4 is also, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0056] As shown in Fig. 3, the control unit 4 includes a receiving unit 41, an estimating unit 42, a determining unit 43, a generating unit 44, an executing unit 45, and a providing unit 46, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the control unit 4 is not limited to the configuration shown in Fig. 3, and may be other configurations as long as they perform the information processing described below. Also, the connection relationship between the processing units of the control unit 4 is not limited to the connection relationship shown in Fig. 3, and may be other connection relationships.

[0057] The receiving unit 41 receives a sentence in a natural language indicating an execution instruction input by a user. As described above, the receiving unit 41 receives a question text, which is a sentence related to a question in a natural language, from a user through a payment application provided by the server device 200.

[0058] The receiving unit 41 may receive, from the user, instructions to execute various services provided by the server device 200, such as an instruction to remit electronic money or an instruction to make a payment.

[0059] The estimation unit 42 estimates the content of the sentence received by the reception unit 41. For example, the estimation unit 42 extracts predetermined attribute words from the question sentence input by the user by natural language processing, and estimates the content of the sentence input by the user based on the extracted attribute words.

[0060] For example, assume that the question sentence input by the user is "Please tell me the amount of electronic money used this month." In this case, the estimation unit 42 extracts "electronic money" and "amount used" as attribute words.

[0061] Then, the estimation unit 42 associates the extracted attribute words with the question sentence as tags. Note that the meaning of words indicating a date and time or a period, such as "this month," "this week," and "today," changes depending on the date and time when the user inputs the sentence, whereas words such as "2023," "July 2023," and "July 1, 2023" can uniquely identify a date and time or a period.

[0062] Therefore, the estimation unit 42 may associate "2023", "July 2023", "July 1, 2023", etc. as tags with the question sentence, but may not associate "this month", "this week", "today", etc. as tags with the question sentence. In other words, the estimation unit 42 may not generate tags for words including specific variables.

[0063] The estimation unit 42 may estimate the content of the question sentence and generate tags by using a model that generates tags from a question sentence. For example, such a model can be realized by BERT (Bidirectional Encoder Representation from Transformers) or the like.

[0064] The determination unit 43 determines whether or not execution information (corresponding to an API request) for executing a process corresponding to the execution instruction of the sentence accepted by the acceptance unit 41 is cached. The determination unit 43 determines, based on the content of the question sentence estimated by the estimation unit 42, whether or not an API request corresponding to the content of the question sentence is stored in the API request storage unit 32, which serves as a cache.

[0065] Specifically, the determination unit 43 searches the API request storage unit 32 based on the tag generated by the estimation unit 42, and determines whether or not the API request has been cached. For example, the determination unit 43 searches for an API request associated with the same tag as the tag generated by the estimation unit 42, and determines whether or not the API request has been cached.

[0066] If the determination unit 43 determines that the API request has not been cached, it outputs an instruction to generate a prompt to the generation unit 44, and if it determines that the API request has been cached, it passes the cached API request to the execution unit 45.

[0067] If the determining unit 43 determines that the API request is not cached, the generating unit 44 generates an API request using the second model M2 that has been trained to generate an answer to the question.

[0068] First, prior to generating an API request, the generation unit 44 performs prompt engineering and generates an extended prompt by using the first model stored in the first model storage unit 33. Here, the process of generating an extended prompt will be described with reference to Figs. 6 to 9.

[0069] 6 to 9 are explanatory diagrams of a process of generating an extended prompt according to the embodiment. In the following, a case where the user's question sentence is "Did I Spend more this month?" will be described.

[0070] For example, the prompt to be input to the first model includes the category of the user's question sentence described above, a question sentence inquiring about the type of value (Value as the Key) that will be the key for executing the processing for the question, and an instruction sentence to output the answer in JSON format.

[0071] Then, the generation unit 44 obtains an answer obtained by inputting such a prompt into the first model. For example, as shown in Fig. 7, it is understood from the answer by the first model that the category ID is "0" and the value type is "expense (Spend data)".

[0072] Next, the generation unit 44 determines a prompt to be input to the first model based on the category ID and the type of value included in these answers. For example, the generation unit 44 refers to the prompt dictionary storage unit 31 and selects an API question sentence based on the category ID and the type of value.

[0073] For example, the generation unit 44 selects an API question sentence having a matching category ID from the prompt dictionary storage unit 31. The generation unit 44 generates a prompt to be further input to the first model from the selected API question sentence.

[0074] For example, the generation unit 44 generates the prompt shown in Fig. 8. In the prompt shown in Fig. 8, the question portion by the user (Did you spend more this month?) is replaced with a question of each user.

[0075] As shown in Figure 8, the prompt here includes a sentence inquiring about the type of API to be executed ("normalized metric") and the values ​​to be obtained ("current period statr datetime", "current period end datetime", "previous period statr datetime", "previous period end datetime"), as well as an instruction sentence to output the answer in JSON format.

[0076] The generation unit 44 inputs the prompt shown in Fig. 8 to the first model and obtains an answer from the first model. The first model outputs, for example, an answer shown in Fig. 9 in response to such a prompt.

[0077] As shown in Figure 9, the answers from the first model include answers to the items specified by the prompt: “normalized metric,” “current period statr datetime,” “current period end datetime,” “previous period statr datetime,” and “previous period end datetime.”

[0078] Then, the generation unit 44 generates an extension prompt based on these answers. Fig. 10 is a diagram showing an example of an extension prompt according to the embodiment. The generation unit 44 generates, for example, an extension prompt as shown in Fig. 10. The extension prompt is a prompt that is ultimately input to the second model M2, and is a prompt for generating an API request in the second model M2.

[0079] In the example shown in FIG. 10, the extended prompt includes a request for input of items described in a request body and a description of a user response.

[0080] Then, the generation unit 44 inputs the extension prompt to the second model M2 and obtains a response to the extension prompt from the second model M2. Here, the output result by the second model M2 will be described with reference to Fig. 11. Fig. 11 is a diagram showing an example of a response to the extension prompt according to the embodiment.

[0081] 11, the second model M2 generates a response in JSON format that describes each item of the API type, authentication, request body, and user response. In other words, the second model M2 outputs the API request as a response.

[0082] In this way, the generation unit 44 can generate an extended prompt in which the answer of the second model M2 becomes an API request by executing an engineering prompt using the first model based on the question sentence by the user. Therefore, in this embodiment, an appropriate API request can be generated from the question by the user.

[0083] Returning to the explanation of Fig. 3, the execution unit 45 will be explained. The execution unit 45 executes processing using cached execution information (corresponding to the API request) or execution information generated by the generation unit 44. If an API request corresponding to an execution instruction has been cached, the execution unit 45 extracts the corresponding API request from the API request storage unit 32, associates the API request with a user ID, and transmits the API request to the server device 200.

[0084] Furthermore, if the API request corresponding to the execution instruction has not been cached, the execution unit 45 associates the user ID with the API request generated by the generation unit 44 and transmits the request to the corresponding server device 200.

[0085] This enables the execution unit 45 to obtain the content corresponding to the API request from the server device 200.

[0086] Then, the execution unit 45 associates the tag generated by the estimation unit 42 with the API request newly generated by the generation unit 44, and registers the associated API request in the API request storage unit 32 (corresponding to a cache).

[0087] As a result, when the information processing device 1 receives a new question text, if the content of the text is similar, the information processing device 1 can acquire data by utilizing a past API request registered in the cache.

[0088] Although the case where all API requests are generated by the second model M2 has been described here, the present invention is not limited to this. For example, API requests generated in advance by an administrator or the like may be cached in advance.

[0089] Also, although the case where the information processing device 1 acquires data through an API has been described, the present invention is not limited to this. For example, a sentence or a URL that is a corresponding answer may be cached.

[0090] For example, in response to a question about "resetting a password," the information processing device 1 may return a URL of a page about "resetting a password."

[0091] The providing unit 46 generates an answer to the user's question and provides it to the user who has asked the question. For example, the providing unit 46 generates the answer to the question based on data acquired by the executing unit 45 from the API.

[0092] Then, the providing unit 46 provides the generated answer to the user through the talk screen CG (see FIG. 2). Note that the providing unit 46 may generate and provide an answer by graphing the data acquired from the API.

[0093] Here, an example of the answer screen provided by the providing unit 46 will be described with reference to Fig. 12. Fig. 12 is a diagram showing an example of the answer screen according to the embodiment. In Fig. 12, as described above, a case where the user's question is "Did I spend more this month" will be described.

[0094] In response to such a question, the execution unit 45 transmits an API request to the server device 200 (see FIG. 1) to obtain content from the server device 200. The provision unit 46 generates text and graphs, for example, as shown in FIG. 12, based on the content obtained from the server device 200 and provides them to the user. Note that it is assumed that the graph shown in FIG. 12 is generated by the server device 200 by transmitting a predetermined API request to the server device 200.

[0095] Through such a series of processes, the information processing device 1 provides an answer to the user's question. As a result, for example, the information processing device 1 can generate and provide an appropriate answer to the user's question.

[0096] [3. Processing flow] Next, a process procedure executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 13. Fig. 13 is a flowchart showing an example of a providing process according to the embodiment. Note that the process procedure shown below is repeatedly executed by the information processing device 1 using the receipt of a question sentence by a user as a key.

[0097] 13, the information processing device 1 receives a question sentence in a natural language from a user (step S101).The information processing device 1 then generates a tag indicating the content of the question (step S102).

[0098] Next, the information processing device 1 searches the cache based on the tag (step S103) and determines whether the API request is in the cache (step S104). If the information processing device 1 determines that the API request is not in the cache (step S104; No), it generates a prompt (step S105). Note that the prompt here includes a first prompt and a second prompt.

[0099] Next, the information processing device 1 acquires a response from the model (step S106). That is, the information processing device 1 acquires an API request from the second model M2. Next, the information processing device 1 transmits the API request to the API and acquires data (step S107).

[0100] Then, the information processing device 1 provides an answer to the question by the user (step S108), associates the tag with the API request, and registers it in the cache (step S109), and ends the process. If the information processing device 1 determines in step S104 that the cache exists, it extracts the corresponding API request from the cache and proceeds to the process of step S107.

[0101] 4. Modifications In the above embodiment, the case where the user inputs a sentence as text has been described, but the present invention is not limited to this. The information processing device 1 may receive a sentence in a natural language from the user by voice or the like.

[0102] In the above embodiment, the case where a question about electronic money is received has been described, but the present invention is not limited to this. For example, the present invention may be applied to other services such as shopping sites that obtain user account information through APIs.

[0103] In the above embodiment, the case where a question is received from a user is described, but the present invention is not limited to this. For example, an instruction to execute a remittance or the like may be received from a user.

[0104] For example, if a user writes "Please send 3,000 yen to person A" but "person A" cannot be identified, the user may be asked to confirm person A's account before sending the money.

[0105] 5. Effects The information processing device 1 according to the embodiment includes a reception unit 41 that receives a natural language sentence indicating an execution instruction input by a user, a determination unit 43 that determines whether execution information for executing a process corresponding to the execution instruction of the sentence received by the reception unit 41 is cached, a generation unit 44 that generates execution information using a model that has been trained to generate an answer to a question when the determination unit 43 determines that the execution information is not cached, and an execution unit 45 that executes a process using the cached execution information or the execution information generated by the generation unit 44.

[0106] The information processing device 1 also includes an estimation unit 42 that estimates the content of the text using the receiving unit 41, and a determination unit 43 determines whether or not the execution information is cached based on the content of the text estimated by the estimation unit 42.

[0107] Furthermore, when the execution unit 45 executes a process using the execution information generated by the generation unit 44, the execution unit 45 adds the content of the sentence estimated by the estimation unit 42 to the execution information and registers it in the cache.

[0108] The generation unit 44 also generates execution information by inquiring of the model about the type of application interface for executing the process and the content of the execution information to be executed by the application interface. The generation unit 44 also causes the model to generate the content of the execution information in the format of the application interface.

[0109] By using any one or a combination of the above-mentioned processes, the information processing device of the present application can efficiently operate services using automatically generated AI.

[0110] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 14. Fig. 14 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0111] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0112] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0113] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 14, the output devices and the input devices are collectively referred to as "input / output devices") via an input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0114] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0115] For example, when the computer 1000 functions as an information processing device according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 4. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[0116] [7. Other] Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. The above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0117] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0118] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0119] For example, the above-mentioned information processing device may be realized using multiple server computers, and depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0120] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0121] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0122] 1. Information processing device 2. Communications Department 3 Storage section 4. Control Unit 31 Prompt Dictionary Storage Unit 32 API request storage 41 Reception 42 Estimation part 43 Judgment section 44 Generation part 45 Executive Department 46 Providing Department 100 user terminals 200 Server device

Claims

1. an acceptance unit that accepts a sentence in a natural language indicating an execution instruction input by a user; a determination unit that determines whether execution information for executing a process corresponding to the execution instruction of the sentence accepted by the acceptance unit is cached; a generating unit that generates the execution information using a model that has been trained to generate an answer to a question when the determining unit determines that the execution information is not cached; and an execution unit that executes the process using the cached execution information or the execution information generated by the generation unit; An information processing device comprising:

2. an estimation unit that estimates the content of the text received by the reception unit; Equipped with The determination unit is determining whether the execution information is cached based on the content of the sentence estimated by the estimation unit; 2. The information processing apparatus according to claim 1,

3. The execution unit is When the process is executed using the execution information generated by the generation unit, the execution information is added with the content of the sentence estimated by the estimation unit and registered in the cache.

3. The information processing apparatus according to claim 2,

4. The generation unit is generating the execution information by inquiring of the model regarding a type of an application interface for executing the process and the content of the execution information to be executed by the application interface; 2. The information processing apparatus according to claim 1,

5. The generation unit is generating content of said execution information in a format of said application interface for said model; 5. The information processing apparatus according to claim 4,

6. a storage unit for storing an internal model that is different from the model and that has been trained to generate answers to questions; Equipped with The generation unit is performing prompt engineering using the internal model, and inputting an extended prompt generated by the prompt engineering into the model to generate the execution information; 2. The information processing device according to claim 1,

7. 1. A computer-implemented information processing method, comprising: a receiving step of receiving a sentence in a natural language representing an execution instruction input by a user; a determination step of determining whether execution information for executing a process corresponding to the execution instruction of the sentence accepted by the acceptance step is cached; a generating step of generating the execution information using a model trained to generate an answer to a question when it is determined by the determining step that the execution information is not cached; an execution step of executing the process using the cached execution information or the execution information generated by the generation step; 13. An information processing method comprising:

8. an acceptance step for accepting a natural language sentence indicating an execution instruction input by a user; a determination step for determining whether execution information for executing a process corresponding to the execution instruction of the sentence accepted by the acceptance step is cached; a generating step of generating the execution information using a model trained to generate an answer to a question when it is determined by the determining step that the execution information is not cached; an execution procedure for executing the process using the cached execution information or the execution information generated by the generation procedure; An information processing program characterized by causing a computer to execute the above.

Images