Data processing device, data processing method, and data processing program

Abstract

To provide a data processor, a method and a program for facilitating the order reception / placement of non-verbal work in a site for mediating the order reception / placement of work through the Internet.SOLUTION: A data processing apparatus that communicates with a user terminal on an orderer side, the data processing apparatus including an input unit that receives, from the user terminal, a text representing a content of a task desired to be ordered; The information processing apparatus includes a determination unit configured to acquire a determination result of non-linguisticity from an AI of the generation output model, a registering unit configured to, in a case of a work having a non-linguisticity, translate a text representing content of the work into a plurality of languages and register the text in a site that mediates placing and receiving orders for the work, and an outputting unit configured to, in a case where placing and receiving orders for the work are established, translate a message between an ordering party and an order receiving party into a language predetermined for the order receiving party and display the message on user terminals, and translate the message into a language predetermined for an ordering party and display the message on the user terminals.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a data processing device, a data processing method, and a data processing 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 an instruction sentence related to a description of 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] There are websites that mediate job orders via the Internet, but there is room for improvement in the way that conventional websites mediate job orders involving non-verbal communication. [Means for solving the problem]

[0005] A first aspect of the technology disclosed herein is a data processing device that includes an input unit that receives information representing the content of work that a client wishes to order from a terminal on the client's side; a judgment unit that inputs instruction information that includes the information representing the content of the work and instructs a judgment of the content of the work that the client wishes to order to determine whether the work is non-verbal and independent of language into a generative AI model and obtains the judgment result of the non-verbal nature from the output of the generative AI model; and a registration unit that, if the content of the work that the client wishes to order is work that has the non-verbal nature, translates the information representing the content of the work into a language different from the received information and registers it on a site that mediates the ordering and purchase of the work.

[0006] A second aspect of the technology disclosed herein is a data processing method in which a computer receives information representing the content of work to be ordered from a client's terminal, inputs instruction information including the information representing the content of the work and instructing a language-independent determination of the content of the work to be ordered into a generative AI model, obtains the non-verbal determination result from the output of the generative AI model, and, if the content of the work to be ordered is work that has the non-verbal nature, translates the information representing the content of the work into a language different from the received information and registers it on a site that mediates the ordering and purchase of the work.

[0007] A third aspect of the technology disclosed herein is a data processing program that causes a computer to receive information representing the content of work to be ordered from a client's terminal, input instruction information including the information representing the content of the work and instructing a determination of the content of the work to be ordered as being non-verbal and independent of language into a generative AI model, obtain the determination result of the non-verbal nature from the output of the generative AI model, and, if the content of the work to be ordered is work that has the non-verbal nature, translate the information representing the content of the work into a language different from the received information and register it on a site that mediates the ordering and purchase of the work. [Brief explanation of the drawings]

[0008] [Figure 1]1 illustrates an example of the configuration of a data processing system. [Figure 2] 1 shows an example of main functions of a data processing device and a user terminal. [Figure 3] 2 shows a schematic functional configuration of a specific processing unit of the data processing device. [Figure 4] An example of a screen for inputting text representing the content of the work to be ordered is shown below. [Figure 5] This shows how to translate a job description text written in English into a language other than English. [Figure 6] Here is an example of a site that displays a list of jobs registered in Japanese with the details of the work you want to order. [Figure 7] An example of a screen displaying a translated message is shown below. [Figure 8] 10 is a diagram illustrating an example of an operational flow of a registration process performed by a data processing device. [Figure 9] 10 shows an example of an operational flow of assistance processing by a data processing device. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, exemplary embodiments of a data processing device, a data processing method, and a data processing program according to the techniques 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 coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single 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), or an APU (Accelerated Processing Unit).

[0012] In the following embodiments, a coded 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 symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "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 user terminals 14A and 14B. An example of the data processing device 12 is a server. Examples of the user terminals 14A and 14B are a personal computer, a tablet, or a smartphone. The multiple user terminals 14A are used by multiple freelancers who wish to accept work on the crowdsourcing site, one by one. The user terminal 14B is used by an orderer who wishes to place an order for work on the crowdsourcing site. 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The user terminals 14A and 14B each include a computer 36, a reception device 38, an output device 40, 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 and the output device 40 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a keyboard, a mouse, etc., and receives user input. The reception device 38 may also receive user input by touch of an indicator (for example, a pen or a finger) by detecting contact with the touch panel, or may receive user input by voice by detecting the user's voice by a microphone. The control unit 46A transmits data indicating the received user input 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 a person by outputting the data in a form of expression that can be perceived by the person (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the user terminals 14A and 14B.

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

[0025] The storage 32 stores a generative AI model 58. The generative AI model 58 is used by the specific processing unit 290.

[0026] The generative AI model 58 is a so-called generative AI (Artificial Intelligence). An example of the generative AI model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generative AI models. The generative AI model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the generative AI model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The generative AI model 58 performs inference on the input inference data in accordance with 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.

[0027] In the user terminals 14A and 14B, the processor 46 performs the reception output process. The storage 50 stores a reception output program 62. The reception output program 62 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads 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.

[0028] Next, the processing of the specific processing unit 290 when the data processing device 12 performs specific processing for operating a crowdsourcing site that mediates job orders and placement will be described.

[0029] In the identification process of this embodiment, information representing the content of a job to be ordered is received from user terminal 14B on the orderer side, and using generative AI model 58, the content of the job to be ordered is determined to be non-verbal, independent of language. If the content of the job to be ordered is non-verbal, the information representing the content of the job is translated into a language different from the received information and registered on the crowdsourcing site. Furthermore, when a job order is placed or accepted on the crowdsourcing site, in messages exchanged between the orderer and the contractor, the message is translated into a language predetermined for the contractor and displayed on user terminal 14A on the contractor side, and the message is also translated into a language predetermined for the orderer and displayed on user terminal 14B on the orderer side.

[0030] As shown in FIG. 3, the specific processing unit 290 includes an input unit 291, a determination unit 292, a registration unit 293, an output unit 294, a support unit 295, and an evaluation acquisition unit 296.

[0031] The input unit 291 receives information (text or voice) indicating the content of the work to be ordered from the user terminal 14B on the orderer side.

[0032] For example, on the user terminal 14B on the orderer side, the orderer operates a crowdsourcing site screen as shown in Fig. 4 to input text representing the content of the work they wish to order. Fig. 4 shows an example in which the price to be paid as compensation for the work they wish to order, the type of work (Type of your offer), the title of the work (Title of the offer), and a detailed description of the work (Details about the offer) are input on the crowdsourcing site screen, and the submit button (SUBMIT) is pressed.

[0033] The judgment unit 292 inputs instruction information, which includes information representing the content of the accepted work and instructs the generation AI model 58 to judge whether the work content to be ordered is non-verbal, meaning that the work is not dependent on language, into the generation AI model 58, and obtains the non-verbal judgment result from the output of the generation AI model 58.

[0034] As an example, the instruction information "The text to be input is the content of the job you would like to order on a crowdsourcing site. Please determine whether this job is non-verbal and independent of language" and the text representing the content of the job are input into the generative AI model 58.

[0035] Here, the generative AI model 58 is configured to determine the non-verbal nature of the content of the job to be ordered by using a database that stores a plurality of pairs of text representing the content of the job and the non-verbal nature determination results, which are prepared in advance. For example, the generative AI model 58 is configured to determine the non-verbal nature of the content of the job to be ordered by using Retrieval-Augmented Generation (RAG).

[0036] The generative AI model 58 may be trained using a plurality of pairs of pre-prepared texts representing the work content and non-verbal character determination results as training data. Fine tuning, for example, can be used as the training data.

[0037] If the content of the work to be ordered is non-verbal, the registration unit 293 translates the text representing the content of the work into at least one language different from the received information and registers it on the crowdsourcing site. For example, as shown in FIG. 5, if the content of the work to be ordered is non-verbal, the registration unit 293 translates the text representing the content of the work written in English into multiple languages ​​other than English and registers it on the crowdsourcing site as shown in FIG. 6. FIG. 5 shows an example of translating the text representing the content of the work written in English into Japanese. Also, FIG. 6 shows an example of a site that displays a list of jobs whose content of the work to be ordered is registered in Japanese.

[0038] At this time, the registration unit 293 may use the generative AI model 58 to translate the text representing the content of the work into multiple languages.

[0039] As an example, the instruction information "The text to be entered is the content of the work you would like to order on a crowdsourcing site. Please translate this into Japanese, Chinese, and Korean," along with the text representing the content of the work, is input into the generative AI model 58.

[0040] When a job order is placed on a crowdsourcing site, the output unit 294 translates the message exchanged between the orderer and the contractor into a language predetermined for the contractor and displays it on the contractor's user terminal 14A, and also translates the message into a language predetermined for the orderer and displays it on the orderer's user terminal 14B.

[0041] Specifically, in the exchange of messages between the orderer and the contractor, the output unit 294 uses the generation AI model 58 to translate the message into a language predetermined for the contractor and displays it on the contractor's user terminal 14B, and also uses the generation AI model 58 to translate the message into a language predetermined for the orderer and displays it on the orderer's user terminal 14B (Figure 7).

[0042] As an example, instruction information such as "Please translate the input text into Japanese" and an English message input from the user terminal 14B on the ordering party side are input to the generative AI model 58.

[0043] Figure 7 shows an example of a screen on a crowdsourcing site that displays an exchange between a Japanese translation of an English message entered from the client's user terminal 14B and a Japanese message entered from the client's user terminal 14A.

[0044] The support unit 295 inputs instruction information into the generating AI model 58 that indicates the role of the AI ​​manager in supporting the exchange of messages between the client and the contractor, and obtains the AI ​​manager's message from the output of the generating AI model 58.

[0045] At this time, the output unit 294 further translates the AI ​​manager's message in the message exchange between the orderer and the contractor into a language predetermined for the contractor and displays it on the contractor's user terminal 14A, and also translates the AI ​​manager's message into a language predetermined for the orderer and displays it on the orderer's user terminal 14B (Figure 7).

[0046] Figure 7 shows an example in which, in a message exchange between a client and a contractor, the message from the AI ​​manager is translated into a language (Japanese) predetermined for the contractor and displayed on the contractor's user terminal 14A.

[0047] As an example, the instruction information "You are an AI manager who supports the exchange of messages between clients and contractors on a crowdsourcing site. As the AI ​​manager, please generate appropriate messages and translate them into Japanese and English" and data showing the exchange of messages between clients and contractors are input into generative AI model 58.

[0048] When a job is completed, the evaluation acquisition unit 296 receives, from the client, an evaluation of the job completion result or the contractor.

[0049] At this time, the role of the AI ​​manager in the generative AI model 58 is additionally learned using pairs of messages from the AI ​​manager displayed in the message exchange between the client and the contractor for the job and the received evaluation.

[0050] Next, the operation of the data processing system 10 will be described.

[0051] An example of the flow of a registration process included in the identification process by the data processing device 12 will be described with reference to Fig. 8. The flow of the registration process shown in Fig. 8 is an example of a "data processing method" according to the technology of the present disclosure.

[0052] When the client operates the user terminal 14B on the client's side to input text representing the content of the work they wish to order into the screen of the crowdsourcing site as shown in Figure 4 above, the data processing device 12 executes the registration process shown in Figure 8.

[0053] In step S100, the input unit 291 receives text indicating the content of the work to be ordered from the user terminal 14B on the orderer side.

[0054] In step S102, the determination unit 292 generates instruction information that includes text representing the content of the accepted job and instructs determination of the non-linguistic nature of the job content that is not dependent on language, for the job content to be ordered.

[0055] In step S104, the determination unit 292 inputs the created instruction information to the generative AI model 58, and obtains the non-verbal determination result from the output of the generative AI model 58.

[0056] In step S106, the determination unit 292 determines whether the content of the work to be ordered is a non-verbal work based on the acquired non-verbal determination result. If it is determined to be a non-verbal work, the process proceeds to step S110, and if it is determined not to be a non-verbal work, the process proceeds to step S108.

[0057] In step S108, since the content of the work to be ordered is not non-verbal, the registration unit 293 registers the text representing the content of the work as is on the crowdsourcing site without translating it into another language, and ends the registration process.

[0058] In step S110, since the content of the work to be ordered is a non-verbal work, the registration unit 293 uses the generative AI model 58 to translate the text representing the content of the work into multiple languages.

[0059] In step S112, the translation results obtained by translating the text expressing the content of the work into a plurality of languages ​​are registered on the crowdsourcing site, and the registration process is terminated.

[0060] An example of the flow of the support process included in the specific processing by the data processing device 12 will be described with reference to FIG. 9. The flow of the support process shown in FIG. 9 is an example of a "data processing method" according to the technology of the present disclosure. When the contractor or the orderer inputs text representing a message to be sent to the other party on the screen of the crowdsourcing site at the user terminal 14A on the contractor's side or the user terminal 14B on the orderer's side, the data processing device 12 executes the support process shown in FIG. 9. It is assumed that a job order has been placed between the orderer and the contractor on the crowdsourcing site. It is also assumed that the support unit 295 has previously input, into the generative AI model 58, instruction information that instructs the role of the AI ​​manager to support the exchange of messages between the orderer and the orderer.

[0061] In step S120, the output unit 294 receives text representing a message to be sent to the other party from the user terminal 14A on the order recipient side or the user terminal 14B on the order recipient side.

[0062] In step S122, the output unit 294 uses the generative AI model 58 to translate the received message into a predetermined language for the contractor and also into a predetermined language for the orderer, thereby performing mutual translation.

[0063] In step S124, the output unit 294 displays a message translated into a predetermined language for the contractor on the contractor's user terminal 14B, and also displays a message translated into a predetermined language for the orderer on the orderer's user terminal 14B.

[0064] In step S126, the support unit 295 inputs the message exchange between the orderer and the order recipient into the generative AI model 58, and obtains the message of the AI ​​manager from the output of the generative AI model 58.

[0065] In step S128, the output unit 294 determines whether or not a message from the AI ​​manager was acquired in step S126. If it is determined that a message from the AI ​​manager was acquired, the process proceeds to step S130; on the other hand, if it is determined that a message from the AI ​​manager was not acquired, the support process ends.

[0066] In step S130, the output unit 294 uses the generative AI model 58 to perform mutual translation, translating the AI ​​manager's message into a predetermined language for the contractor and into a predetermined language for the orderer.

[0067] In step S132, the output unit 294 displays the AI ​​manager's message translated into a predetermined language for the contractor on the contractor's user terminal 14B, and also displays the AI ​​manager's message translated into a predetermined language for the orderer on the orderer's user terminal 14B, thereby completing the support process.

[0068] As explained above, according to the data processing system of this embodiment, when the content of the job to be ordered is non-verbal, the information expressing the content of the job is translated into a language different from the received information and registered on a site that mediates job orders, and when the job order is placed on the site, the messages exchanged between the orderer and the contractor are mutually translated and displayed on the contractor's terminal and the orderer's terminal. This makes it easier to place and receive orders for non-verbal jobs on a site that mediates job orders via the Internet.

[0069] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[0070] In the above embodiment, the case where orders for and from work are mediated on a crowdsourcing site has been described as an example, but the present invention is not limited to this. The present invention may also be applied to cases where orders for and from work are mediated on sites other than crowdsourcing sites (for example, a temporary staffing site).

[0071] 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.

[0072] 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 USB (Universal Serial Bus) 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 specific processing in accordance with the specific processing program 56. The present invention may also be applied to a program product.

[0073] Alternatively, 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 in response to a request from the data processing device 12.

[0074] 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.

[0075] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0076] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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 processing may be a single processor.

[0077] As an example of a system configured with a single 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 system that uses a processor that realizes the functions of an 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.

[0078] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0079] The above-described description and illustrations are a detailed explanation 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, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects 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-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0080] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0081] 10 Data Processing System 12 Data Processing Device 14A, 14B User terminal 22, 36 Computer 28, 46 processors 32, 50 storage 38 Reception device 40 Output Devices 46A Control Unit 56 Specific Processing Program 58 Generative AI Models 62 Reception output program 290 Special Processing Department 291 Input section 292 Judgment section 293 Registration Department 294 Output Section 295 Support Department 296 Evaluation Acquisition Department< / url:>

Claims

1. an input unit that receives information indicating the content of the work to be ordered from a terminal on the ordering party's side; a determination unit that inputs instruction information, including information representing the content of the work, that instructs the content of the work to be ordered to determine whether the work is non-linguistic and does not depend on language, into a generative AI model and obtains a determination result of the non-linguistic nature from the output of the generative AI model; If the content of the work to be ordered is work having non-verbal characteristics, information expressing the content of the work is translated into a language different from the received information, and the translated information is registered on a site that mediates the ordering and purchase of the work; a registration unit that, if the content of the work to be ordered is not a work having non-linguistic characteristics, registers information representing the content of the work on a site that mediates the ordering and receiving of the work without translating the information into a language different from that of the received information; 2. A data processing device comprising:

2. an output unit that translates the message into a predetermined language for the orderer and displays it on a terminal of the orderer when an order for the job is placed on the site and messages are exchanged between the orderer and the order recipient in a predetermined language for the order recipient and displays it on a terminal of the order recipient; 2. The data processing apparatus of claim 1, further comprising:

3. 2. The data processing device of claim 1, wherein the generative AI model is configured to determine the non-verbal nature of the content of the job to be ordered using a database that stores a plurality of pairs of text representing the content of the job and non-verbal nature determination results that have been prepared in advance.

4. The data processing device according to claim 1, wherein the generative AI model is additionally trained using as training data a plurality of pairs of text representing the content of the work and non-verbal judgment results that have been prepared in advance.

5. Further includes a support unit that inputs instruction information instructing the role of a manager who supports the exchange of messages between the orderer and the contractor into the generation AI model and acquires the message of the manager from the output of the generation AI model, 3. The data processing device according to claim 2, wherein the output unit further translates the manager's message in a message exchange between the orderer and the contractor into a language predetermined for the contractor and displays it on the contractor's terminal, and translates the manager's message into a language predetermined for the orderer and displays it on the orderer's terminal.

6. Further, an evaluation acquisition unit is configured to receive, from the client, an evaluation of the completion result of the work or the contractor when the work is completed, 6. A data processing device according to claim 5, wherein the role of the manager in the generative AI model is additionally learned using a pair of the manager's message displayed in the message exchange between the client and contractor for the job and the received evaluation.

7. 3. The data processing device according to claim 2, wherein the output unit, in a message exchange between the orderer and the contractor, uses the generation AI model to translate the message into a language predetermined for the contractor and displays it on a terminal on the contractor's side, and also uses the generation AI model to translate the message into a language predetermined for the orderer and displays it on a terminal on the orderer's side.

8. The data processing device according to claim 1 , wherein the site is a crowdsourcing site for requesting work via the Internet.

9. The computer The client receives information from their terminal that describes the work they want to order, Inputting instruction information into a generative AI model, the instruction information including information representing the content of the work and instructing a determination that the content of the work to be ordered is non-verbal and independent of language, and obtaining a determination result of the non-verbal nature from the output of the generative AI model; If the content of the work to be ordered is work having non-verbal characteristics, information expressing the content of the work is translated into a language different from the received information, and the translated information is registered on a site that mediates the ordering and purchase of the work; If the content of the work to be ordered is not a non-linguistic work, information representing the content of the work is registered on a site that mediates the ordering and receiving of the work without being translated into a language different from the received information. The data processing method that performs the processing.

10. On the computer, The client receives information from their terminal that describes the work they want to order, Inputting instruction information into a generative AI model, the instruction information including information representing the content of the work and instructing a determination that the content of the work to be ordered is non-verbal and independent of language, and obtaining a determination result of the non-verbal nature from the output of the generative AI model; If the content of the work to be ordered is work having non-verbal characteristics, information expressing the content of the work is translated into a language different from the received information, and the translated information is registered on a site that mediates the ordering and purchase of the work; If the content of the work to be ordered is not a non-linguistic work, information representing the content of the work is registered on a site that mediates the ordering and receiving of the work without being translated into a language different from the received information. A data processing program for executing processing.

Images