Data processing apparatus, data processing method, and program

Abstract

To provide a data processing apparatus, a data processing method, and a program with which an appropriate response can be obtained for a user input.SOLUTION: A data processing apparatus includes: a receiving unit which receives a precondition to be set on a data generation model which generates a text according to input data; a setting unit which inputs a prompt including the precondition to the data generation model; a processing unit which inputs a prompt including a user input to the data generation model to obtain a response to the user input using an output of the data generation model; and an output unit which outputs the obtained response.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The technology disclosed herein relates to a data processing device, a data processing method, and a program. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the prior art leaves room for improvement in obtaining appropriate responses to user input. [Means for solving the problem]

[0005] A first aspect of the technology disclosed herein is a data processing device comprising: a receiving unit that receives prerequisites to be set for a data generation model that generates sentences according to input data; a setting unit that inputs a prompt including the prerequisites to the data generation model; a processing unit that inputs a prompt including a user input to the data generation model and obtains a response to the user input using an output of the data generation model; and an output unit that outputs the obtained response.

[0006] A second aspect of the technology disclosed herein is a data processing method including: a receiving unit receiving preconditions to be set for a data generation model that generates sentences according to input data; a setting unit inputting a prompt including the preconditions to the data generation model; a processing unit inputting a prompt including a user input to the data generation model and obtaining a response to the user input using an output of the data generation model; and an output unit outputting the obtained response.

[0007] A third aspect of the technology disclosed herein is a program for causing a computer to execute a process including accepting preconditions to be set for a data generation model that generates sentences based on input data, inputting a prompt including the preconditions to the data generation model, inputting a prompt including user input to the data generation model, obtaining a response to the user input using output of the data generation model, and outputting the obtained response. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a data processing system. [Diagram 2] FIG. 2 is a conceptual diagram showing an example of main functions of a data processing device and a smart device. [Figure 3A] The outline of the specific process is shown below. [Figure 3B] The outline of the specific process is shown below. [Figure 3C] The outline of the specific process is shown below. [Figure 3D] The outline of the specific process is shown below. [Figure 3E] The outline of the specific process is shown below. [Figure 3F] The outline of the specific process is shown below. [Figure 4] 2 shows a schematic functional configuration of a specific processing unit of the data processing device. [Diagram 5] 13 illustrates an example of an operational flow of a specific process performed by a data processing device. [Figure 6A]1 shows an emotion map onto which multiple emotions are mapped. [Figure 6B] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment.

[0017] As shown in Fig. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. An example of the smart device 14 is a smartphone. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the person 20 by outputting the data in a form of expression that the person 20 can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 60. The data generation model 58 and the emotion identification model 60 are used by the identification processing unit 290.

[0026] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 62. The reception output program 62 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 62 from the storage 50, and executes the read reception output program 62 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48.

[0027] Next, the processing of the specification processing unit 290 when the data processing device 12 performs specification processing for setting preconditions for a data generation model will be described.

[0028] The identification process in this embodiment assists in setting preconditions for deriving optimal answers from data generation models such as ChatGPT.

[0029] Specifically, the identification process provides a function for deriving an accurate and appropriate answer that the user desires when the user uses the data generation model. For example, as shown in FIG. 3A, an "assistant" function that assists in setting prerequisites is provided as an agent function for interacting with the user in the smart device 14. FIG. 3A shows an example in which an "assistant" function, a "chat" function, a "consultation" function, a "news" function, an "order" function, a "schedule" function, a "translation" function, and a "settings" function are provided as agent functions for interacting with the user.

[0030] The background is that in order to use ChatGPT, you need to enter a prompt to set the appropriate prerequisites. However, for those who are using ChatGPT for the first time or who are not good at using it, entering the prompt to set the appropriate prerequisites can be difficult.

[0031] In the specific process, a specific function is to set preconditions in a chat format before use (the "chat" function in FIG. 3B). For example, roles such as doctor, lawyer, and newscaster can be defined as preconditions. Also, preconditions regarding the format of answers can be set. For example, it is possible to set answers of about 100 characters, or answers in five bullet points. At this time, an input box for setting the preconditions is displayed on the smart device 14, and the necessary conditions can be input into the input box.

[0032] Furthermore, previously used preconditions are recorded and can be recalled and used at any time.

[0033] Thanks to the specific processing functions mentioned above, even first-time users or those who are not good at using ChatGPT will be able to use it more effectively and get accurate and appropriate answers.

[0034] As shown in FIG. 3B, in addition to the "Chat" function, there are provided a "File UL" function for uploading data representing the preconditions to be set, a "Character Select" function for selecting a character with preconditions set in advance, and a "My Character" function for selecting a My Character with preconditions set according to the user's preferences.

[0035] In the "chat" function, the preconditions for the prompt are set in a dialogue with the user. Specifically, in the smart device 14, an application corresponding to a specific process asks the user questions necessary for the preconditions in the form of questions, and the user can set the preconditions by answering the questions.

[0036] In the "File UL" function, prerequisites are set by uploading a file containing the prerequisites to the application side in the smart device 14. This makes it possible to set prerequisites more quickly than in an interactive format.

[0037] The "Character Select" function allows the user to set prerequisites by selecting a character that best suits the situation desired from a selection of pre-prepared characters.

[0038] For example, the prerequisite for the character "Lawyer" is that he or she will respond logically and using technical terms in a few lines.

[0039] For the character "Sportsman," preconditions are set such that responses are based on familiar examples, such as "it's like this," rather than logical answers.

[0040] The character "Elementary School Student" has knowledge at the university professor level, but the prerequisite is that he responds in easy-to-understand words appropriate for his age.

[0041] In the "My Character" function, the user can create preconditions of their choice and select a My Character with the preconditions set. For example, each time a conversation is held, the preconditions desired by the user are learned, and preconditions are created that are suited to the user and that give the user more in-depth and penetrating answers that the user desires.

[0042] For individual users, it is aimed at those who are using ChatGPT for the first time, those who are not good at using it, and those who are not able to get the answers they want. It is also aimed at those who are not good at setting up prompts to get the answers they want. It is also aimed at almost all users who use smartphones, the Internet, and GPT. In particular, it is aimed at elderly people who do not have high computer literacy.

[0043] In addition, for business users, it can be provided as a function to support those in charge of promoting business transformation (DX) at companies.

[0044] For example, if the user company is an airline, it provides an "elder" function, a "mechanic" function, a "flight attendant" function, and a "personnel" function, as shown in FIG. 3C.

[0045] The "Elder" function sets up a premise where a senior employee who is well versed in the structure of the company and the organizational structure will answer questions from new employees, mid-career employees, and transferred employees, explaining things they don't understand, using company terminology in an easy-to-understand way.

[0046] The "Mechanic" function sets preconditions so that the mechanic, as a professional in the maintenance business, can give appropriate advice on parts and maintenance methods that he or she does not understand. This allows the mechanic to explain things in an easy-to-understand manner to departments other than the mechanic, using examples of the work of those departments.

[0047] The "Cabin Attendant" function sets preconditions so that cabin attendants, as cabin crew professionals, can give appropriate advice on the operation of each aircraft and the structure of in-flight services. This allows them to provide easy-to-understand explanations to departments other than cabin attendants, using examples of their department's work.

[0048] The "Human Resources" function allows you to set prerequisites so that an in-house human resources professional can answer questions about salary allowances, how to apply for special leave, employee benefits and how to apply for them.

[0049] In this way, for corporate users, prerequisites are set that are specific to the customer's business operations, and support the user's business operations.

[0050] As shown in FIG. 4, the specific processing unit 290 includes a receiving unit 291, a setting unit 292, a processing unit 294, and an output unit 296.

[0051] The receiving unit 291 receives preconditions to be set for the data generation model 58 that generates sentences according to input data.

[0052] Specifically, when the "chat" function is selected, the accepting unit 291 accepts preconditions by accepting user input to questions related to preconditions prepared in advance.

[0053] For example, the control unit 46A of the smart device 14 outputs voice or displays questions related to preconditions prepared in advance, accepts voice input or text input from the user for the questions, and obtains the voice input or text input from the user accepted by the smart device 14. Then, the accepting unit 291 accepts the preconditions including a combination of the questions and the user's input for the questions.

[0054] Furthermore, when the "file UL" function is selected, the receiving unit 291 receives an input of data representing information on each item related to the prerequisites.

[0055] For example, when the control unit 46A of the smart device 14 receives text representing the precondition as a user input, the text representing the precondition is transmitted to the data processing device 12, and the receiving unit 291 receives the text representing the precondition.

[0056] Furthermore, when the "character" function is selected, the reception unit 291 receives a selection of one of a plurality of types of preconditions prepared in advance.

[0057] For example, the control unit 46A of the smart device 14 outputs voice or displays a plurality of characters prepared in advance and accepts the selection of the character. Then, the accepting unit 291 accepts a precondition determined in advance for the selected character.

[0058] The setting unit 292 sets the preconditions by inputting a prompt including the preconditions received by the receiving unit 291 into the data generation model.

[0059] For example, a prompt such as "You are a lawyer. Please answer in 100 characters or less" is generated and input into the data generation model 58.

[0060] The setting unit 292 may estimate the user's emotion using the emotion identification model 60 and include the user's emotion in the precondition.

[0061] The processor 294 inputs a prompt including a user input to the data generation model 58 and uses the output of the data generation model 58 to obtain a response to the user input.

[0062] Specifically, when the control unit 46A of the smart device 14 receives a voice input or a text input representing a question as a user input, the received voice or text is transmitted to the data processing device 12, and the processing unit 294 receives the voice or text representing the question. The processing unit 294 inputs a prompt including the voice representing the question or the text representing the question to the data generation model 58, and obtains an answer to the user's question using the output of the data generation model 58.

[0063] The processing unit 294 may estimate the user's emotion using the emotion identification model 60, and may obtain a response to the user input using the user's emotion and the data generation model 58.

[0064] The output unit 296 transmits a response to the user input to the smart device 14. In the smart device 14, the control unit 46A causes the display 40A or the speaker 40B of the output device 40 to output the response to the user input. The microphone 38B further acquires a voice indicating the user input in response to the response to the user input. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0065] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search PT), which generates sentences based on input data.<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0066] Next, the operation of the data processing system 10 will be described with reference to FIG.

[0067] First, an example of the flow of the specific processing of the data processing device 12 will be described with reference to Fig. 5. When an "assistant" function that assists in setting prerequisites is selected as one of the agent functions for interacting with the user shown in Fig. 3A in the smart device 14, the specific processing of the data processing device 12 is executed. The flow of the specific processing shown in Fig. 5 is an example of a "data processing method" according to the technology of the present disclosure. Also, the case where the "chat" function is selected will be described as an example.

[0068] In the identification process shown in FIG. 5, first, in step S100, the reception unit 291 causes the smart device 14 to output voice or display questions related to prerequisites that have been prepared in advance. For example, as shown in FIG. 3D, the reception unit 291 outputs voice or displays questions such as "What kind of job would you like?" and "How would you like to be answered?". At this time, the control unit 46A of the smart device 14 receives voice input or text input from the user for the questions. For example, as shown in FIG. 3D, the reception unit 291 receives voice input or text input such as "Lawyer please" and "Please answer concisely in 100 characters or less."

[0069] In step S102, the reception unit 291 acquires a voice input or a text input received by the smart device 14 from the user.

[0070] In step S104, the receiving unit 291 judges whether or not the processes of steps S100 and S102 have been executed for all question items related to the preconditions prepared in advance. If there is a question item for which the processes of steps S100 and S102 have not been executed, the process returns to step S100, and the processes of steps S100 and S102 are executed for that question item. On the other hand, if the processes of steps S100 and S102 have been executed for all question items related to the preconditions prepared in advance, the process proceeds to step S106. At this time, the receiving unit 291 receives preconditions including combinations of question items and user inputs therefor.

[0071] In step S106, the setting unit 292 sets the precondition by inputting a prompt including the precondition received by the reception unit 291 to the data generation model 58. In the example of FIG. 3D above, a prompt saying "You are a lawyer. Please answer briefly in 100 characters or less" is generated and input to the data generation model 58.

[0072] In step S108, the processing unit 294 accepts a voice or text representing a question. Specifically, when the control unit 46A of the smart device 14 accepts a voice input or text input representing a question as a user input, the accepted voice or text is transmitted to the data processing device 12, and the processing unit 294 accepts the voice or text representing the question. For example, as shown in FIG. 3D, the voice or text "Please tell me about my parent's inheritance. The land of my parent's house..." is accepted.

[0073] In step S110, the processing unit 294 inputs a prompt including a user input to the data generation model 58, and obtains a response to the user input using the output of the data generation model 58. In the example of Fig. 3D above, a prompt including a voice or text "Please tell me about my parent's inheritance. The land of my family home..." is generated and input to the data generation model 58.

[0074] In step S112, the output unit 296 transmits a response to the user input to the smart device 14. At this time, in the smart device 14, the control unit 46A causes the output device 40 to output the response to the user input. In the example of FIG. 3D above, the response "I will answer. XXXXXX..." is output.

[0075] In step S114, it is determined whether or not to end the specific process. If an instruction to end the specific process is input by the user, the specific process is ended, whereas if an instruction to end the specific process is not input by the user, the process returns to step S108 and accepts user input.

[0076] In the above, an example was explained in which the "Chat" function was selected. However, when the "File UL" function was selected, the control unit 46A of the smart device 14 receives, as user input, for example, text representing the preconditions, such as "Occupation = Lawyer, Answer method = 100 characters or less, 〇〇 = ···, 〇〇 = ···," as shown in FIG. 3E, the text representing the preconditions is transmitted to the data processing device 12, and the receiving unit 291 receives the text representing the preconditions.

[0077] In the case of business users, as shown in FIG. 3F, the data generation model 58 may search for responses corresponding to user inputs from a company-specific database and provide answers. For example, ChatGPT Plugins (Internet search<URL: https: / / openai.com / blog / chatgpt-plugins> ) to search for and answer questions from a company-specific database. The company-specific database may contain, for example, pairs of questions and answers related to the company's business operations.

[0078] As described above, the data processing device 12 receives preconditions to be set for a data generation model that generates sentences according to input data, inputs a prompt including the preconditions to the data generation model, inputs a prompt including a user input to the data generation model, obtains a response to the user input using the output of the data generation model, and outputs the obtained response. This makes it possible to easily obtain an appropriate response to the user input.

[0079] In addition, in order to utilize a data generation model such as ChatGPT, it is necessary to set an appropriate prompt. However, for those who are using ChatGPT for the first time or those who are not good at using it, it may be difficult to set an appropriate prompt. Even if there is an excellent data generation model that can return useful output, it is necessary to set a prompt including the correct preconditions that can maximize its effect. In this embodiment, the specific process of setting the preconditions can help anyone maximize the output of the data generation model.

[0080] Although the smart device 14 is described as a smartphone, the present invention is not limited thereto. Smart glasses may be used as the smart device 14. In this case, the above-mentioned specific process may provide an "assistant" function for assisting in setting prerequisites as an agent function for interacting with the user in the smart glasses.

[0081] Furthermore, the emotion identification model 60 may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 60 may determine the emotion of the user according to an emotion map (see FIG. 6A), which is a specific mapping.

[0082] FIG. 6A is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0083] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0084] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0085] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0086] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0087] The emotion identification model 60 inputs user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. In addition, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 6B. FIG. 6B shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0088] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0089] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0090] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0091] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0092] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing the specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0093] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0094] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0095] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0096] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above description and illustrations, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require explanation in order to enable the implementation of the technology of the present disclosure.

[0097] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0098] 10 Data Processing System 12 Data Processing Device 14 Smart Devices 56 Specific Processing Program 58 Data Generation Model 290 Specific Processing Department 291 Reception 292 Setting section 294 Processing section 296 Output section

Claims

1. a reception unit that receives a precondition to be set for a data generation model that generates sentences according to input data; a configuration unit that inputs a prompt including the precondition into the data generation model; a processor for inputting a prompt including a user input to the data generation model and obtaining a response to the user input using an output of the data generation model; an output unit that outputs the acquired response; 2. A data processing device comprising:

2. 2 . The data processing apparatus according to claim 1 , wherein the accepting unit accepts the preconditions by accepting user input for each of a plurality of questions relating to the preconditions prepared in advance.

3. The data processing apparatus according to claim 1 , wherein the reception unit receives input of data representing information on each item related to the prerequisites.

4. The data processing apparatus according to claim 1 , wherein the reception unit receives a selection of one of a plurality of types of preconditions prepared in advance.

5. The reception unit receives a precondition to be set for a data generation model that generates sentences according to input data; The setting unit inputs a prompt including the precondition into the data generation model; a processor for inputting a prompt including a user input to the data generation model and obtaining a response to the user input using an output of the data generation model; The output unit outputs the acquired response. (c) Processing the data.

6. Accept preconditions to be set for a data generation model that generates sentences based on input data; inputting a prompt including the precondition into the data generation model; inputting a prompt including a user input into the data generation model and obtaining a response to the user input using an output of the data generation model; Output the acquired response A program for causing a computer to execute a process including the above.

Images