JP2024114549A - Assist Server - Google Patents

Abstract

To provide an AI server assist system, a mediation server and a server mediation system which reduce man-hours for inputting data to be submitted to an AI, and process items of untrained matters.SOLUTION: An assist server includes: a trained model which is trained to receive data to be processed, which has been received from a mediation server connected via a public communication network 4, process the data to be processed and output processed data to be transmitted to the mediation server; and a control unit which acquires, when the trained model outputs a response indicating the input data to be processed has not been learned yet, a content of an external site by accessing a URL described in a search result which has been output by a search server having a search engine that searches with a keyword regarding matters not leaned by the trained model, trains the trained model with the acquired content, submits again the data to be processed, after the learning, to the trained model for processing, acquires processed data processed again by the trained model, and transmits the processed data to the mediation server.SELECTED DRAWING: Figure 13

Description

The present invention relates to an assist server.

Recently, the technology known as AI (Artificial Intelligence) has been developing rapidly. AI, specifically, server systems equipped with trained models and communication functions (hereinafter, these server systems will be referred to as "AI servers") have been made public, and developers and others are providing environments that can be used freely.

One type of AI that has been attracting attention recently is so-called chat-type AI, in which natural language data is input and a trained model outputs a dialogue in natural language that is valid for the input data (for example, Non-Patent Document 1).

This chat-type AI learns from conversation data from various chat services on the Internet and other platforms, which have been used in the past, and users can obtain the desired output through conversation with the chat-type AI.

Therefore, to get the desired output from a chat-based AI, it is necessary to input information requesting the type of output desired, in addition to the underlying circumstances, situation, or conditions.

For example, if you want to use a chat-based AI to obtain sample questions and model answers for the final exam in marketing theory at the graduate school where you are studying to obtain an MBA (Master of Business Administration), you will need to interactively input into your computer or other device background information such as the fact that you are aiming to obtain an MBA, that you are taking a marketing theory course at graduate school, and the scope of the final exam, as well as a request to be "taught" the sample questions and model answers for the final exam.

However, this input requires a considerable amount of effort. Furthermore, even if you take the trouble to input the dialogue, the current situation is that for matters that the chat AI's trained model has not yet learned, the chat AI cannot produce the desired output, and simply outputs that the matter has not yet been learned.

This kind of input effort and the need to deal with processing unlearned items also arises with AI other than chat-based AI.

Therefore, there is a demand for a server intermediation system, intermediation server, assist system, and assist server that can reduce the amount of work required to input data into AI and process items that have not yet been learned.

ChatGPT published at https://openai.com/

The problem that this invention aims to solve is to provide a server intermediation system, an intermediation server, and an AI server assist system that can reduce the amount of work required to input data into AI and process items that have not yet been learned.

The contents of the above "Background Art" and "Problem to be Solved by the Invention" indicate the opportunity (trigger) that led to the invention, and do not limit the technical scope of the invention, nor do they permit a limited interpretation of the technical scope of the invention (see Heisei 17 (Gyo-Ke) No. 10042 and the Japan Patent Office Examination Guidelines as of the filing date, Part II, Chapter 2, Section 2, 3.2.1).

The present invention provides an assist server including a trained model that is trained to input data to be processed received from an external server connected via a communication line, process the data to be processed, and output processed data to be transmitted to the external server; and a control unit that, when the trained model outputs a response indicating that the input data to be processed has not yet been learned, transmits keywords related to matters that the trained model has not yet learned to a search server having a search engine to cause the search to be performed, accesses the URL of an external site listed in the search results output by the search, acquires the content of the external site, trains the acquired content into the trained model, and, after training, re-inputs the data to be processed into the trained model for processing, acquires the processed data reprocessed by the trained model, and transmits the processed data to the external server.

The present invention can provide a server intermediation system, an intermediation server, a trained model assist system, and an assist server that can reduce the amount of work required to input data into AI and process unlearned items.

FIG. 2 is a diagram illustrating the configuration of an intermediation server and an assist server according to the first embodiment. FIG. 4 is a diagram illustrating an example of a data configuration of a user database. FIG. 2 is a diagram showing a data structure of a question database. FIG. 13 is a diagram showing the data structure of an additional information database. FIG. 2 is a diagram showing a data structure of a format database. FIG. 4 is a diagram showing a data structure of an account database. FIG. 4 is a diagram showing the data structure of a session record database. FIG. 13 is a diagram showing the configuration of information stored as an AI group. 2 is a flowchart showing the operation of the server intermediation system, the intermediation server, and the AI server assist system of the first embodiment. FIG. 13 is a diagram showing an example of a reply/request input screen displayed on a user terminal. A diagram showing the configuration of a mediation server that realizes the server mediation system of the second embodiment, a user terminal that communicates with the mediation server, and an assist server. FIG. 4 is a diagram showing a data structure of a site database. A flowchart showing the operation of the server intermediation system, the intermediation server, and the AI server assist system of the second embodiment. FIG. 13 is a diagram showing configurations of an intermediation server, a user terminal, an assist server, and a portfolio server according to the third embodiment. FIG. 2 is a diagram illustrating an example of a data configuration of a portfolio database.

The following provides a detailed explanation of the server intermediation system, intermediation server, and AI server assist system according to one embodiment of the present invention.

First Embodiment
In the first embodiment, the intermediary server 1 generates pre-transmission data by adding additional data necessary to obtain the desired output from the trained model held by the assist server 2 to the initial data received from the user terminal 3, further prepares data to be processed from the pre-transmission data in accordance with an input format specific to the trained model, instructs the assist server 2 to input the data to be processed into the trained model and transmits it, receives processed data from the assist server 2 that the trained model has processed and output from the trained model, prepares output data to be output to the user terminal 3 based on the output format specific to the processed data output by the trained model, and transmits the output data to the user terminal.

The intermediary server 1 mediates data exchange between the user terminal 3 and the assist server 2, and the assist server 2 assists the operation of the trained model.

Figure 1 shows the configuration of the intermediation server 1 that realizes the server intermediation system of this embodiment, as well as the user terminal 3 and assist server 2 that communicate with the intermediation server 1.

As shown in FIG. 1, the intermediary server 1 includes an intermediary server control unit 11, an intermediary server storage unit 12, and an intermediary server input/output unit and communication unit 13.

The intermediary server control unit 11 includes a processor such as a central processing unit (CPU). The intermediary server control unit 11 sequentially reads and executes the software stored in the intermediary server storage unit 12.

The intermediary server storage unit 12 includes storage devices such as memory, SSD (Solid State Drive), and HDD (Hard Disk Drive).

The intermediary server storage unit 12 stores the software executed by the intermediary server control unit 11, as well as a user DB 121 (hereinafter, database is referred to as DB), an additional information DB 122, and a format DB 123.

The user DB 121 stores user information for each user, which is information about the user's attributes, etc., and round information that indicates the history of a series of information exchanges with the assist server 2.

The additional information DB 122 stores additional information, such as prerequisites necessary to obtain a desired output from the trained model held by the assist server 2 and request content indicating what type of output is desired, which the intermediary server control unit 11 adds to the initial data, which is data received from the user terminal 3, and additional example sentences, which are example sentences set for each additional information.

For each assist server 2, the format DB 123 stores an input format, which is a format required for data to be input to a learned model specific to the learned model stored in the assist server 2, and an output format specific to the processed data output by the learned model.

The intermediary server input/output unit/communication unit 13 includes input/output devices such as a keyboard, mouse, microphone, and display, and a communication device that communicates with external devices via a network.

The assist server 2 includes an assist server control unit 21, an assist server memory unit 22, and an assist server input/output unit/communication unit 23.

The assist server control unit 21 has a calculation device such as a CPU. The assist server control unit 21 sequentially reads and executes the software stored in the assist server memory unit 22.

The assistant server storage unit 22 includes storage devices such as memory, SSD, and HDD.

The assist server memory unit 22 stores the software executed by the assist server control unit 21, as well as an account DB 221, a session record DB 222, and an AI group 223.

The account DB221 stores accounts, which are identifiers uniquely assigned to each user of the assist server 2, and various information related to each account.

The session record DB222 stores session information indicating the history of a series of information exchanges with the intermediary server 1, and chat information such as the content of chats exchanged within each session.

The AI group 223 stores, for each trained model, information about each trained model and the trained model. The AI group 223 can also include a plurality of trained models and an AI operation unit that is software that determines how to select and use the plurality of trained models and sequentially combines and operates the selected trained models.

The assist server input/output unit/communication unit 23 includes input/output devices such as a keyboard, mouse, microphone, and display, as well as a communication device that communicates with external devices via a network.

The user terminal 3 and the intermediation server 1, and the intermediation server 1 and the assist server 2 are connected via a public communication line network 4 such as the Internet, and communicate with each other.

Figure 2 is a diagram showing an example of the data configuration of user DB 121. As shown in Figure 2, user DB 121 stores a user ID, which is an identifier uniquely assigned to each user, user information, which is information about the user such as name and contact information, a round ID, which is an identifier uniquely assigned to each round, round information, such as the access date and time, a question ID identifying the question posed to the user, the user's response to the question, an assist server ID identifying the assist server 2 on which the round occurred, and a session ID identifying the session on which the round occurred.

Now, we will explain rounds and sessions. A session refers to a series of information exchanges that begin when a user uses the user terminal 3 to start exchanging information with the assist server 2 via the intermediary server 1, and ends when the user finishes exchanging information with the assist server 2. Usually, a session occurs regarding a single topic, but the topic may change during the session.

A round refers to one exchange of information between the user terminal 3 and the assist server 2 via the intermediary server 1 that occurs during one session. One round begins with the flow of information in the sending direction, sent from the user terminal 3 to the assist server 2 via the intermediary server 1, and ends with the flow of information in the receiving direction, received from the assist server 2 via the intermediary server 1. Thus, one session may include multiple rounds.

Figure 3 shows the data structure of the question DB. The intermediation server storage unit 12 of the intermediation server 1 is an arbitrary database that may or may not store the question DB. Therefore, it is not shown in Figure 1.

The question DB stores a question ID, which is an identifier uniquely assigned to each question; question attribute information, which is information about the attributes of questions such as non-cognitive skill measurement types that ask the user to speak and act in a hypothetical situation that would normally not occur to the user, and response ability measurement types that ask the user to respond in an unexpected situation; and the question text.

Figure 4 is a diagram showing the data structure of the additional information DB 122. As shown in Figure 4, the additional information DB 122 stores additional example sentence IDs, which are identifiers uniquely assigned to each example sentence that the intermediation server 1 adds to the initial data, additional information, and additional example sentences.

Figure 5 is a diagram showing the data structure of the format DB 123. As shown in Figure 5, the format DB 123 stores an assist server ID, which is an identifier assigned to each assist server 2, an input format, and an output format.

Figure 6 is a diagram showing the data configuration of the account DB 221. As shown in Figure 6, the account DB 221 stores an account, which is an identifier uniquely assigned to each user of the assist server 2, identification information that identifies the user, and account attribute information that indicates the attributes of the account, such as educational use by a school or the like, or commercial use by a company or the like.

Figure 7 is a diagram showing the data configuration of the session record DB 222. As shown in Figure 7, the session record DB 222 stores a session ID, which is an identifier uniquely assigned to each session, the account that performed the session, the session start date and time, the session end date and time, a chat ID, which is an identifier uniquely assigned to each chat (comment) that occurred within the session, the chat content for each chat, and a read flag that is turned ON when the chat has been read by the other party (meaning that it has been displayed on the user terminal 3 and that it has been input into the trained model on the assist server 2).

FIG. 8 is a diagram showing the configuration of information stored as the AI group 223. As shown in FIG. 8, the AI group 223 stores, as a collection of indexed data such as a database, a trained model ID, which is an identifier uniquely assigned to each trained model, input format information regarding the input format such as the data type (e.g., plain text, XML, binary data, etc.) and data length that the data input to the trained model must have, output format information regarding the output format such as the data type and data length of the data output by the trained model, trained model information indicating the attributes of the trained model such as image judgment, character judgment, natural language analysis/interpretation, translation, and dialogue, a specific functional description of the trained model, and the main body of the trained model. The AI group 223 may also include an AI operation unit.

Figure 9 is a flowchart showing the operation of the server intermediation system, intermediation server 1, and AI server assist system of this embodiment. The server intermediation system is realized by the cooperation of the hardware and software equipped in the intermediation server 1. The AI server assist system is realized by the cooperation of the hardware and software equipped in the assist server 2, and cooperation with the server intermediation system enables advanced use of the trained model equipped in the assist server 2.

As shown in FIG. 9, in step 901, the control unit of the user terminal 3 exchanges various information to start a session with the intermediary server 1, and then sends an instruction to the intermediary server 1 to request a question.

In step 902, the intermediary server control unit 11 transmits a question read randomly from the question DB or selected from questions that have not yet been administered to the user.

In step 903, the control unit of the user terminal 3 transmits the answer entered by the user and, if necessary, a request to the intermediary server 1.

Here, steps 901 to 903 can be replaced with an operation in which the intermediary server 1 simply receives data entered from the user terminal 3 to start a dialogue, rather than requesting and sending a question.

In step 904, the intermediary server control unit 11 selects an assist server 2 having a trained model to be used from one or more assist servers 2 based on the answer (or data for starting a dialogue; hereinafter, these are referred to as initial data) received from the user terminal 3 and the request optionally received. This selection may be made by the intermediary server control unit 11 searching a database that stores information about the assist server 2 that the intermediary server 1 stores separately in the intermediary server storage unit 12.

In step 905, the intermediary server control unit 11 searches the user DB based on the user ID received from the user terminal 3, and reads out the assist server ID, session ID, and round information if they are stored. The intermediary server control unit 11 uses the assist server ID, session ID, and round information to identify which assist server 2, which session, and which round the user wishes to continue. In this case, the intermediary server control unit 11 selects the identified assist server 2 instead of the assist server 2 selected in step 904.

In step 906, the intermediation server control unit 11 adds the read session ID to the initial data.

In step 907, the intermediary server control unit 11 generates pre-conversion data by adding additional data such as a request statement to the initial data. This request statement may be a statement created by the user and sent from the user terminal 3, or it may be an additional example statement that the intermediary server control unit 11 retrieves from the additional information DB based on additional information selected by the user via the user terminal 3.

A specific example is given below (see FIG. 10).
(1) Questions given to users Q1. Katsu Kaishu is on the Kanrin Maru, sailing to America. You are a passenger on the ship. What would you suggest to Katsu Kaishu that he should do when he gets to America?
(2) User responses (initial data)
A1. I would suggest to Katsu Kaishu that he invite the President of the United States to dinner. Even though the President likes hamburgers, he should have dinner. To show that they are on equal footing.
(3) A request selected by the user (request 3): Please evaluate from an objective point of view. In this case, the intermediation server control unit 11 generates pre-conversion data as shown below based on the above (1) to (3).
(Data before conversion: The underlined part is additional data added to the initial data by the intermediation server control unit 11.)
I was asked the following questions:
Q1. Katsu Kaishu is on the Kanrin Maru, sailing to America. You are a passenger on the ship. What would you suggest to Katsu Kaishu that he should do when he gets to America?
To this question, I answered as follows:
A1. I would suggest to Katsu Kaishu that he invite the President of the United States to dinner. Even though the President likes hamburgers, he should have dinner. To show that they are on equal footing.
Please evaluate my answer to Q1, A1, from an objective point of view.

In step 908, the intermediary server control unit 11 searches the format DB 123 based on the assist server ID of the assist server 2 selected in steps 904 and 905, and reads out the input format. The intermediary server control unit 11 converts the pre-conversion data based on the read input format, and generates the data to be processed.

In step 909, the intermediary server control unit 11 sends the data to be processed to the selected assist server 2.

In step 910, the assist server control unit 21 inputs the received data to be processed into the learned model and causes the learned model to process the data to be processed.

In step 911, the assist server control unit 21 transmits the processed data output by the learned model after processing the data to be processed to the intermediation server 1.

In step 912, the intermediary server control unit 11 searches the format DB 123 based on the assist server ID and reads out the output format. The intermediary server control unit 11 converts the processed data based on the read out output format and generates response data to be displayed on the user terminal 3.

In step 913, the intermediation server control unit 11 sends the response data to the user terminal 3.

In step 914, the control unit of the user terminal 3 displays the received response data on the display of the user terminal 3.

Of the above actions, steps 901 to 908 are called the round start actions, and steps 912 to 914 are called the round end actions.

Figure 10 is a diagram showing an example of the answer/request input screen 100 displayed on the user terminal 3. When sending a question in step 902 of Figure 9, the intermediary server control unit 11 generates data for the answer/request input screen 100, sends it to the user terminal 3, and displays it.

As shown in FIG. 10, the answer/request input screen 100 includes a question display field 1001 that displays a question, an answer input field 1002 where the user inputs an answer, a request selection field 1003 which is a pull-down menu for selecting a request, a request details field 1004 that is displayed by clicking on the request selection field 1003, and a send button 1005 that instructs the input/selected information to be sent to the intermediary server 1.

As described above, in the server intermediation system, intermediation server, and AI server assist system of this embodiment, the intermediation server 1 stores additional information, which is data to be added to the initial data transmitted by the user from the user terminal 3 by the user, in order to obtain a desired output from the trained model possessed by the assist server 2, in the additional information DB 122, and for each assist server 2, a format DB 123 stores an input format, which is a format required for data to be input to the trained model specific to the trained model, and an output format specific to the processed data output by the trained model, and reads out additional information selected from the additional information DB 122 and adds the additional information to the initial data as additional data. and an intermediary server control unit 11 that adds the input format to the selected assist server 2 to generate pre-conversion data, reads an input format from the format DB 123 based on the selected assist server 2, converts the pre-conversion data based on the input format to generate data to be processed, transmits the data to be processed to the assist server 2 and inputs it to the trained model for processing, receives processed data from the assist server 2 that is output by the trained model after processing the data to be processed, reads an output format from the format DB 123 based on the assist server 2, converts the processed data based on the output format to generate response data to be displayed on the user terminal 3, and transmits the response data to the user terminal 3.

Therefore, according to this embodiment, it is possible to provide a server intermediation system, an intermediation server, and an AI server assist system that can reduce the amount of work required to input data into AI.

Second Embodiment
In the second embodiment, the configuration and operation of the intermediation server 1 are similar to those of the intermediation server 1 in the first embodiment.

In contrast, the assist server 2 of the second embodiment further stores a site DB 224 in the assist server memory unit 22.

The configuration and operation of the assist server 2 in the first embodiment differs from that of the assist server 2 in the first embodiment in that, when the assist server control unit 21 in the second embodiment outputs a response indicating that the learned model has not yet learned the input data to be processed, it reads the site URL (Uniform Resource Locator) of the search server 5 from the site DB 224, sends a keyword related to the matter that has not been learned to the read site URL to perform a search, accesses the URL of the external site 6 listed in the search results output by the search to obtain the content of that site, trains the obtained content into the learned model, and after training, inputs the data to be processed again and processes it, thereby obtaining the processed data.

Figure 11 shows the configuration of the intermediation server 1 that realizes the server intermediation system of this embodiment, as well as the user terminal 3 and assist server 2 that communicate with the intermediation server 1.

The assist server 2 of this embodiment further stores a site DB 224 in the assist server storage unit 22. The assist server 2 is further connected to a search server 5 and an external site 6 via a public communication line network 4 such as the Internet, and communicates with each other.

The search server 5 has a search engine that, when a keyword is input, outputs a list of external sites 6 related to the keyword and their URLs. When the URL is accessed, the external site 6 transmits content to the access source.

Figure 12 is a diagram showing the data structure of site DB 224. As shown in Figure 12, site DB 224 stores a site ID, which is an identifier uniquely assigned to a site, site attribute information such as a search engine's specialty in cases where the search engine has a unique field, and a site URL indicating the URL of the site.

Figure 13 is a flowchart showing the operation of the server intermediation system, intermediation server 1, and AI server assist system of this embodiment. The server intermediation system is realized by the cooperation of the hardware and software equipped in the intermediation server 1. The AI server assist system is realized by the cooperation of the hardware and software equipped in the assist server 2, and by working with the server intermediation system, even more advanced use of the trained model equipped in the assist server 2 becomes possible.

Specifically, in the prior art, trained models had difficulty responding to matters that had not yet been trained, but in this embodiment, the assist server 2 uses a search server 5 having a search engine to find the URL of an external site 6 that describes an item that has not yet been trained in the trained model, accesses the external site 6 to obtain content related to that item, and has the trained model learn the obtained content, thereby assisting further learning of the trained model and realizing more advanced use of the trained model.

In this embodiment, it is possible to use the content of all sites around the world that can be accessed via a public communication line network 4 such as the Internet as the background for learning the trained model, making it possible to further improve the performance of the trained model. It is also expected to eliminate the time-consuming and laborious tasks of conventionally inputting keywords and checking search results.

As shown in FIG. 13, in step 1301, the control unit of the user terminal 3 and the intermediary server control unit 11 execute a round start operation.

In step 1302, the intermediary server control unit 11 transmits the data to be processed to the assist server 2.

In step 1303, the assist server control unit 21 inputs the data to be processed received from the intermediary server 1 into the learned model.

In step 1304, the assist server control unit 21 acquires the processed data that the learned model outputs after processing the data to be processed.

In step 1305, the assist server control unit 21 determines whether the processed data includes content indicating that the data has not been learned. If the assist server control unit 21 determines that the processed data does not include content indicating that the data has not been learned (N in step 1305), the process proceeds to step 1313; if the assist server control unit 21 determines that the processed data includes content indicating that the data has not been learned (Y in step 1305), the process proceeds to step 1306.

In step 1306, the assist server control unit 21 extracts items that have not been learned from the processed data, particularly nouns, as keywords, and retrieves from the site DB 224 the URL of a search server 5 that has a search engine that specializes in the field of the keyword, or a search engine that can search for general items if no such search engines are found. The assist server control unit 21 then accesses the retrieved search server 5 and sends and inputs the keywords to the search engine as search information.

In step 1307, the search server 5 transmits the search results, which include the URLs of the external sites 6 that contain information related to the keywords, to the assist server control unit 21.

In step 1308, the assist server control unit 21 reads the URL of the external site 6 from the search results and accesses the external site 6.

In step 1309, the control unit of the external site 6 transmits the content to the assist server 2.

In step 1310, the assist server control unit 21 generates training data with the data to be processed as explanatory variables and the content as the objective variable, and trains the trained model with the generated training data.

In step 1311, the assist server control unit 21 re-inputs the data to be processed into the trained model.

In step 1312, the assist server control unit 21 reacquires the processed data that the learned model has output after processing the data to be processed, and transmits it to the intermediary server 1.

In step 1313, the control unit of the user terminal 3 and the intermediary server control unit 11 execute the round end operation.

As described above, in the server intermediation system, intermediation server, and AI server assist system of this embodiment, the assist server 2 further stores the site DB 224 in the assist server memory unit 22, and when the assist server control unit 21 outputs a response indicating that the learned model has not yet learned the input data to be processed, it reads out the site URL of the search server 5 from the site DB 224, sends keywords related to matters that have not been learned to the read site URL to perform a search, accesses the URL of the external site 6 listed in the search results output by the search, acquires the content of the external site 6, trains the acquired content into the learned model, and after learning, inputs the data to be processed again and processes it, thereby acquiring the processed data.

Therefore, the assist server 2 can use the search server 5 having a search engine to find the URL of an external site 6 that describes an item that has not yet been learned by the trained model, access the external site 6 to obtain content related to that item, have the trained model learn the obtained content, and after learning, input the data to be processed again and have it processed, thereby obtaining the processed data.

Third Embodiment
In the third embodiment, the configuration and operation of the assist server 2 are similar to those of the assist server 2 in the second embodiment.

In contrast, the intermediation server 1 of the third embodiment is different from the operation of the intermediation server 1 of the first and second embodiments in that it connects to the portfolio server 8 via the public communication line network 4, the intermediation server control unit 11 acquires from the portfolio server 8 the portfolio that the user has stored in advance in the portfolio DB 821 of the portfolio server 8, and adds the acquired portfolio together with the additional data to the initial data when generating pre-conversion data.

Below, we will first explain the configuration of the portfolio server 8, and then explain the operation of the intermediation server control unit 11 to obtain a portfolio from the portfolio DB 821 of the portfolio server 8.

Figure 14 is a diagram showing the configuration of the intermediation server 1 that realizes the server intermediation system of this embodiment, as well as the user terminal 3, assist server 2, and portfolio server 8 that communicate with the intermediation server 1.

The configuration of the intermediary server 1 and the assist server 2 has already been explained, so here we will explain the configuration of the portfolio server 8.

As shown in FIG. 14, the portfolio server 8 includes a portfolio server control unit 81, a portfolio server memory unit 82, and a portfolio server input/output unit/communication unit 83.

The portfolio server control unit 81 includes a calculation device such as a CPU. The portfolio server control unit 81 sequentially reads and executes the software stored in the portfolio server storage unit 82.

The portfolio server storage unit 82 includes storage devices such as memory, SSD, and HDD.

The portfolio server storage unit 82 stores the software executed by the portfolio server control unit 81 as well as the portfolio DB 821.

The portfolio server input/output unit/communication unit 83 includes input/output devices such as a keyboard, mouse, microphone, and display, and a communication device that communicates with external devices via a network.

Figure 15 is a diagram showing an example of the data structure of the portfolio DB 821. As shown in Figure 15, the portfolio DB 821 stores, for each user ID, a portfolio ID, which is an identifier uniquely assigned to the portfolio, and portfolio data, which is the main body of the portfolio.

Next, we will explain the operation of the intermediation server control unit 11 to acquire a portfolio from the portfolio DB 821 of the portfolio server 8, focusing only on the parts that differ from the operation of the intermediation server control unit 11 in the first embodiment.

The operation of step 906 in the first embodiment is changed as follows.
"In step 906, the intermediation server control unit 11 transmits an instruction to the portfolio server 8 to read out the portfolio data from the portfolio DB 821 based on the user ID received from the user terminal 3 and transmit the read portfolio data to the intermediation server 1. The intermediation server control unit 11 adds the session ID and the portfolio data received from the portfolio server 8 to the initial data."

As described above, in the server intermediation system, intermediation server, and AI server assist system of this embodiment, the intermediation server 1 connects to the portfolio server 8 via the public communication line network 4, and the intermediation server control unit 11 acquires from the portfolio server 8 the portfolio that the user has stored in advance in the portfolio DB 821 of the portfolio server 8, and adds the acquired portfolio together with the additional data to the initial data when generating pre-conversion data.

Now, let me explain what a portfolio is. In recent years, when taking entrance exams such as university entrance exams, or when conducting personnel evaluations or selection at companies, there have been attempts to include not only academic tests, but also portfolios that compile information about activities such as participation in volunteer activities, awards received in sports, and overseas travel experiences, in addition to the various activities that students engaged in at school, in order to include the portfolio in the evaluation.

A spreadsheet or word processing software can be used to create a portfolio, but recently, the applicant and several other companies have started to offer cloud-based portfolio creation systems that not only reduce labor costs but also allow users to contact each other and inspire each other.

This portfolio then reflects the user's values, interests, and even a part of their personality.

Therefore, according to this embodiment, the intermediary server 1 adds the user's portfolio data to the initial data to generate pre-conversion data, converts the format of this pre-conversion data to generate data to be processed, and inputs this data to be processed into the trained model, resulting in the effect that processed data that is more suited to the user's individuality is output compared to when the portfolio data is not added.

REFERENCE SIGNS LIST 1 Mediation server 2 Assist server 3 User terminal 4 Public communication line network 5 Search server 6 External site 8 Portfolio server 11 Mediation server control unit 12 Mediation server memory unit 13 Mediation server input/output unit/communication unit 21 Assist server control unit 22 Assist server memory unit 23 Assist server input/output unit/communication unit 81 Portfolio server control unit 82 Portfolio server memory unit 83 Portfolio server input/output unit/communication unit 100 Answer/request input screen 223 AI group 1001 Question display field 1002 Answer input field 1003 Request selection field 1004 Request details field 1005 Send button

The present invention provides an assist server comprising: a trained model trained to input data to be processed received from an external server connected via a communication line, process the data to be processed, and output processed data to be transmitted to the external server; and a control unit that, when the trained model outputs a response indicating that it has not yet learned about the input data to be processed, sends keywords related to matters that the trained model has not yet learned to a search server having a search engine to perform a search, accesses a URL of an external site listed in the search results output by the search, acquires content of the external site, trains the acquired content into the trained model, and after learning, re-inputs the data to be processed into the trained model for processing, acquires the processed data reprocessed by the trained model, and transmits it to the external server.

Claims (4)

A trained model that is trained to input processing target data received from an external server connected via a communication line, process the processing target data, and output processed data to be transmitted to the external server;
a control unit that, when the trained model outputs a response indicating that the trained model has not yet learned the input data to be processed, sends a keyword related to an item that the trained model has not yet learned to a search server having a search engine to perform a search, accesses a URL of an external site listed in the search results output by the search to obtain the content of the external site, trains the obtained content into the trained model, inputs the data to be processed again into the trained model after learning, obtains the processed data that has been processed again by the trained model, and transmits the processed data to the external server;
An assist server comprising: A plurality of the trained models are provided,
The control unit is
The assist server according to claim 1, further comprising an AI operation unit that determines how to select and use the plurality of trained models, and sequentially combines and operates the selected trained models. The trained model is
The assist server according to claim 1 or claim 2, wherein the trained model is trained to input the data to be processed, process the data to be processed, and output the processed data such that a dialogue can be established for the data to be processed. The external server is
An additional information database that stores additional information that is data to be added to initial data transmitted by a user from a user terminal in order to obtain a desired output from the trained model possessed by the assist server;
A format database that stores, for each assistant server, an input format that is a format required for data to be input to the trained model that is specific to the trained model, and an output format that is specific to the processed data output by the trained model;
an intermediary server control unit that reads the selected additional information from the additional information database, generates pre-conversion data by adding the additional information to the initial data as additional data, reads the input format from the format database based on the selected assist server, converts the pre-conversion data based on the input format to generate the data to be processed, transmits the data to be processed to the assist server and inputs it to the trained model for processing, receives from the assist server the processed data that the trained model has processed and output from the trained model, reads the output format from the format database based on the assist server, converts the processed data based on the output format to generate response data to be displayed on the user terminal, and transmits the response data to the user terminal;
The assist server according to claim 3, which is an intermediary server comprising:

Images