system

Abstract

The system according to this embodiment aims to efficiently suggest the relevant documents necessary for preparing an application form. [Solution] The system according to the embodiment comprises a reception unit, a proposal unit, an evaluation unit, and a learning unit. The reception unit receives user input. The proposal unit proposes relevant materials based on the information received by the reception unit. The evaluation unit collects evaluations of the materials proposed by the proposal unit. The learning unit allows the AI ​​to learn based on the evaluations collected by the evaluation unit.

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [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] Conventional technology has made it difficult and time-consuming to efficiently search for the relevant documents needed to complete an application form.

[0005] The system according to this embodiment aims to efficiently suggest the relevant documents necessary for preparing an application form. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a proposal unit, an evaluation unit, and a learning unit. The reception unit accepts user input. The proposal unit proposes related materials based on the information accepted by the reception unit. The evaluation unit collects evaluations of the materials proposed by the proposal unit. The learning unit allows the AI ​​to learn based on the evaluations collected by the evaluation unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently suggest related materials required for application preparation. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor 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), and Bluetooth (registered trademark).

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

[0017] 1, a 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 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 (for example, 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 (see FIG. 2) acquires the data indicating the user input.

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

[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 smart device 14.

[0024] 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 "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 data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The related document suggestion system according to an embodiment of the present invention is a system that efficiently finds related documents necessary when creating an application form. When a user selects an application form, the AI ​​recommendation engine analyzes related documents purchased simultaneously by other users based on past data and suggests the most suitable related documents. For example, if a user selects application form A, the system suggests creation manuals and service documents previously purchased together with application form A. This suggests that users can easily find the necessary documents, significantly reducing the time spent searching. Furthermore, the AI ​​recommendation engine can also suggest the most suitable related documents for each individual user based on their past purchase and search history. This allows users to easily find the documents best suited to them, reducing the risk of selecting the wrong documents. This system not only significantly improves the efficiency of application form creation but also enhances user satisfaction. For example, when a user creates an application form, they can quickly find the necessary documents, leading to smoother work and reduced stress. Additionally, the reduced risk of selecting the wrong documents allows for the creation of accurate application forms. Thus, the related document suggestion system using the AI ​​recommendation engine contributes to improved efficiency and accuracy in application form creation. This allows the related document suggestion system to efficiently find and suggest the relevant documents that users need when creating an application form.

[0029] The related materials suggestion system according to this embodiment comprises a reception unit, a suggestion unit, an evaluation unit, and a learning unit. The reception unit receives user input. User input includes, but is not limited to, text input, voice input, and image input. For example, the reception unit receives text input when the user selects an application form. The reception unit can also receive user instructions using voice input. For example, if the user gives a voice command, "Select application form A," the reception unit receives that instruction. The reception unit can also receive user instructions using image input. For example, if the user uploads an image of an application form, the reception unit receives that image. The suggestion unit suggests related materials based on the information received by the reception unit. The suggestion unit suggests related materials based on past purchase history and search history, for example, using an AI recommendation engine. For example, if the user selects application form A, the suggestion unit suggests creation manuals and service materials that were previously purchased together with application form A. The suggestion unit can also suggest related materials considering the user's job duties and position. For example, the proposal unit suggests materials related to sales activities if the user is in sales. The evaluation unit collects evaluations of the materials suggested by the proposal unit. The evaluation unit collects feedback from users and evaluates whether the suggested materials were useful. The evaluation unit collects evaluations using methods such as questionnaires, comments, and evaluation scores. The learning unit uses the evaluations collected by the evaluation unit to train the AI. The learning unit improves the accuracy of suggestions using methods such as machine learning algorithms and deep learning. The learning unit can optimize the suggestion algorithm based on the collected evaluations. As a result, the related material suggestion system according to this embodiment can improve the accuracy of suggestions by suggesting related materials based on user input and learning from the collected evaluations.

[0030] The suggestion unit can suggest relevant materials based on past purchase and search history. For example, the suggestion unit can suggest relevant materials based on past purchase history. Past purchase history includes, but is not limited to, purchase date and time, purchased items, and purchase amount. For example, the suggestion unit can suggest creation manuals and service materials that were purchased together with application form A that the user previously purchased. The suggestion unit can also suggest relevant materials based on search history. Search history includes, but is not limited to, search keywords, search date and time, and search results. For example, the suggestion unit can suggest materials related to application form A that the user previously searched for. In this way, by suggesting relevant materials based on past history, the system can provide the user with the most suitable materials. Some or all of the above processing in the suggestion unit may be performed using, for example, AI, or not using AI. For example, the suggestion unit can suggest relevant materials using an AI model that takes past purchase and search history as input and outputs relevant materials.

[0031] The proposal department can suggest relevant materials considering the user's job duties and position. For example, the proposal department can suggest relevant materials considering the user's job duties. Job duties include, but are not limited to, sales, marketing, and development. For example, if the user is in sales, the proposal department will suggest materials related to sales activities. The proposal department can also suggest relevant materials considering the user's position. Positions include, but are not limited to, manager, engineer, and assistant. For example, if the user is in a management position, the proposal department will suggest materials related to management tasks. This allows for the provision of more appropriate materials by suggesting materials tailored to the user's job duties and position. Some or all of the above processing in the proposal department may be performed using, for example, AI, or not using AI. For example, the proposal department can suggest relevant materials using an AI model that takes the user's job duties and position as input and outputs relevant materials.

[0032] The evaluation unit can collect feedback from users and evaluate whether the proposed materials were useful. The evaluation unit, for example, collects feedback from users. Feedback includes, but is not limited to, questionnaires, comments, evaluation scores, etc. The evaluation unit can collect feedback, for example, by users answering questionnaires about the proposed materials. The evaluation unit can also collect feedback by users leaving comments about the proposed materials. Furthermore, the evaluation unit can collect feedback by users assigning evaluation scores to the proposed materials. In this way, collecting user feedback can improve the accuracy of suggestions. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that receives user feedback as input and outputs evaluation results.

[0033] The learning unit allows the AI ​​to learn based on the collected evaluations and improve the accuracy of the suggestions. The learning unit, for example, allows the AI ​​to learn based on the collected evaluations. Methods for AI learning include, but are not limited to, machine learning algorithms and deep learning. The learning unit, for example, uses a machine learning algorithm to optimize the proposal algorithm based on the collected evaluations. The learning unit can also use deep learning to optimize the proposal algorithm based on the collected evaluations. As a result, the AI ​​learns and the accuracy of the suggestions improves. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can perform learning using an AI model that uses the collected evaluations as input and outputs an optimized proposal algorithm.

[0034] The proposal department can periodically check for updates to the proposed materials to ensure that the proposed materials are up-to-date. For example, the proposal department can periodically check for updates to the materials. This includes, but is not limited to, the date and time of updates, the content of the updates, and the frequency of updates. For example, the proposal department can check the date and time of updates and propose the latest materials. The proposal department can also check the content of the updates and propose materials that contain the latest information. Furthermore, the proposal department can check the frequency of updates and prioritize proposing materials that are frequently updated. This ensures that the latest materials are provided, thereby providing users with useful information. Some or all of the above processing in the proposal department may be performed using, for example, AI, or not using AI. For example, the proposal department can check for updates to the materials using an AI model that takes the update information as input and outputs the latest materials.

[0035] The proposal unit can provide an explanation showing how the proposed materials are incorporated into the business workflow. For example, the proposal unit can provide an explanation showing how the proposed materials are incorporated into the business workflow. The business workflow includes, but is not limited to, business procedures, process diagrams, and flowcharts. For example, the proposal unit can provide an explanation showing business procedures. The proposal unit can also provide an explanation showing the business workflow using process diagrams. Furthermore, the proposal unit can provide an explanation showing the business workflow using flowcharts. This allows users to effectively utilize the materials by showing how to use them. Some or all of the above processing in the proposal unit may be performed using, for example, AI, or not using AI. For example, the proposal unit can provide an explanation using an AI model that takes information about the business workflow as input and outputs an explanation showing the business workflow.

[0036] The proposal department can quantitatively demonstrate how much work time will be reduced by using the proposed materials. For example, the proposal department can quantitatively demonstrate how much work time will be reduced by using the proposed materials. Methods for demonstrating the work time reduction effect include, but are not limited to, time measurement methods and comparison criteria. For example, the proposal department can quantitatively demonstrate the work time reduction effect by measuring the work time before and after using the proposed materials and showing the difference. The proposal department can also show, on average, how much work time will be reduced by using the proposed materials, based on past data. Furthermore, the proposal department can demonstrate the work time reduction effect according to the user's job content and position. For example, the proposal department can show a sales user how much the time spent on sales activities will be reduced by using the proposed materials. This can improve convenience for the user by demonstrating the work time reduction effect. Some or all of the above processing in the proposal department may be performed using, for example, AI, or not using AI. For example, the proposal unit can quantitatively demonstrate the effect of reducing work time by using an AI model that takes measurement data of work time as input and outputs the effect of reducing work time.

[0037] The reception desk can analyze the user's past input history and suggest the optimal input method. For example, the reception desk analyzes the user's past input history. Past input history includes, but is not limited to, input date and time, input content, and input frequency. For example, the reception desk can automatically display as a candidate the type of application form the user has frequently entered in the past. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest the type of application form to be used during a specific time period based on the user's past input history. This improves the user's input efficiency by suggesting the optimal input method based on past input history. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not. For example, the reception desk can suggest an input method using an AI model that takes past input history as input and outputs the optimal input method.

[0038] The reception desk can customize input fields based on the user's job duties and position. For example, the reception desk can customize input fields based on the user's job duties. Job duties include, but are not limited to, sales, marketing, and development. For example, if the user is in sales, the reception desk will customize the input fields of application forms related to sales activities. The reception desk can also customize input fields based on the user's position. Positions include, but are not limited to, manager, engineer, and assistant. For example, if the user is in a management position, the reception desk will prioritize displaying input fields of application forms related to management tasks. This improves the user's input efficiency by providing input fields that are appropriate to their job duties and position. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can customize input fields using an AI model that takes the user's job duties and position as input and customizes the input fields.

[0039] The reception unit can prioritize displaying relevant input fields by taking into account the user's geographical location information. The reception unit, for example, displays input fields by taking into account the user's geographical location information. Geographical location information includes, but is not limited to, GPS data, IP address, location information services, etc. For example, when the user is in a specific area, the reception unit can prioritize displaying input fields on the application form related to that area. Furthermore, when the user is on a business trip, the reception unit can prioritize displaying input fields on the application form related to the business trip destination. Furthermore, when the user is at home, the reception unit can prioritize displaying input fields on the application form related to the user's home. This can improve the user's input efficiency by providing input fields based on the geographical location information. Some or all of the above-described processing by the reception unit can be performed, for example, using AI, or can be performed without using AI. For example, the reception unit can display input fields using an AI model that inputs the user's geographical location information and outputs relevant input fields.

[0040] The reception desk can analyze a user's social media activity and suggest relevant input fields. For example, the reception desk can analyze a user's social media activity. Social media activity includes, but is not limited to, posts, likes, and follower counts. For example, if a user indicates on social media that they will be participating in a particular event, the reception desk can suggest input fields for an application form related to that event. The reception desk can also suggest input fields for an application form related to a particular project if a user indicates on social media that they are involved in that project. Furthermore, if a user shares information about a particular job on social media, the reception desk can suggest input fields for an application form related to that job. This improves the efficiency of user input by providing input fields based on social media activity. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can suggest input fields using an AI model that takes a user's social media activity as input and outputs relevant input fields.

[0041] The proposal function can adjust the level of detail of a proposal based on the importance of the document. For example, the proposal function can adjust the level of detail of a proposal based on the importance of the document. Criteria for evaluating the importance of a document include, but are not limited to, frequency of use, user ratings, and relevance. For example, the proposal function can provide a detailed explanation along with the proposal for important documents. For less important documents, it can provide a concise explanation along with the proposal. Furthermore, for documents of moderate importance, it can provide a proposal with an appropriate level of detail. This improves user convenience by providing a level of detail of proposals that matches the importance of the document. Some or all of the above processing in the proposal function may be performed using, for example, AI, or not using AI. For example, the proposal function can adjust the level of detail of a proposal using an AI model that takes the importance of the document as input and outputs the level of detail of the proposal.

[0042] The proposal unit can apply different proposal algorithms depending on the category of the document. For example, the proposal unit can apply different proposal algorithms depending on the category of the document. Document categories include, but are not limited to, technical documents, marketing documents, and educational documents. For example, in the case of technical documents, the proposal unit can apply a proposal algorithm that emphasizes technical details. In the case of marketing documents, it can also apply a proposal algorithm that emphasizes visual elements. Furthermore, in the case of legal documents, it can also apply a proposal algorithm that emphasizes legal requirements. This improves user convenience by providing proposal algorithms tailored to the category of the document. Some or all of the above processing in the proposal unit may be performed using, for example, AI, or not using AI. For example, the proposal unit can apply a proposal algorithm using an AI model that takes the category of the document as input and outputs a proposal algorithm.

[0043] The proposal department can determine the priority of proposals based on the submission timing of the materials. For example, the proposal department can determine the priority of proposals based on the submission timing of the materials. The submission timing of materials includes, but is not limited to, submission date and time, submission deadline, and submission frequency. For example, the proposal department may prioritize proposals with approaching deadlines. It may also postpone proposals with later submission dates. Furthermore, it may assign appropriate priority to proposals with medium submission dates. This improves user convenience by providing a priority of proposals according to the submission timing. Some or all of the above processing in the proposal department may be performed using, for example, AI, or not using AI. For example, the proposal department can determine the priority of proposals using an AI model that takes the submission timing of materials as input and outputs the priority of proposals.

[0044] The suggestion unit can adjust the order of suggestions based on the relevance of the materials. The suggestion unit, for example, adjusts the order of suggestions based on the relevance of the materials. Criteria for evaluating the relevance of materials include, but are not limited to, content similarity, common keywords, and related topics. For example, the suggestion unit can suggest the most relevant material first. Alternatively, the suggestion unit can suggest materials with a moderate relevance next. Furthermore, the suggestion unit can suggest materials with little relevance last. This improves user convenience by providing a suggestion order based on relevance. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can adjust the order of suggestions using an AI model that inputs the relevance of materials and outputs the order of suggestions.

[0045] The evaluation unit can select the optimal evaluation method by referring to the user's past evaluation history. The evaluation unit, for example, refers to the user's past evaluation history. The past evaluation history includes, for example, evaluation date and time, evaluation content, evaluation score, etc., but is not limited to these examples. The evaluation unit, for example, preferentially suggests evaluation methods used by the user in the past. The evaluation unit can also select the most appropriate evaluation method from the user's past evaluation history. Furthermore, the evaluation unit can analyze the user's past evaluation history and customize the evaluation method. This can improve user convenience by providing the optimal evaluation method based on the past evaluation history. Some or all of the above-mentioned processing in the evaluation unit can be performed, for example, using AI or without AI. For example, the evaluation unit can select the evaluation method using an AI model that inputs the past evaluation history and outputs the optimal evaluation method.

[0046] The evaluation unit can customize evaluation items based on the user's job duties and position. For example, the evaluation unit can customize evaluation items based on the user's job duties. Job duties include, but are not limited to, sales, marketing, and development. For example, if the user is in sales, the evaluation unit will customize evaluation items related to sales activities. The evaluation unit can also customize evaluation items based on the user's position. Positions include, but are not limited to, manager, engineer, and assistant. For example, if the user is in a management position, the evaluation unit will prioritize displaying evaluation items related to management tasks. This improves user convenience by providing evaluation items tailored to job duties and position. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can customize evaluation items using an AI model that takes the user's job duties and position as input and customizes the evaluation items.

[0047] The evaluation unit can prioritize the collection of relevant evaluation items by taking into account the user's geographical location information. For example, the evaluation unit collects evaluation items by taking into account the user's geographical location information. Geographical location information includes, but is not limited to, GPS data, IP addresses, and location services. For example, if the user is in a specific region, the evaluation unit will prioritize displaying evaluation items related to that region. The evaluation unit can also prioritize displaying evaluation items related to the user's business trip destination if the user is on a business trip. Furthermore, if the evaluation unit is at home, it can prioritize displaying evaluation items related to home. This improves user convenience by providing evaluation items based on geographical location information. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can collect evaluation items using an AI model that takes the user's geographical location information as input and outputs relevant evaluation items.

[0048] The evaluation unit can analyze the user's social media activity and collect related evaluation items. The evaluation unit can analyze, for example, the user's social media activity. Social media activity includes, but is not limited to, the content of posts, the number of likes, and the number of followers. For example, if the user indicates on social media that they will participate in a specific event, the evaluation unit can collect evaluation items related to the event. Furthermore, if the user indicates on social media that they are involved in a specific project, the evaluation unit can also collect evaluation items related to the project. Furthermore, if the user shares information about a specific business on social media, the evaluation unit can also collect evaluation items related to the business. This can improve user convenience by providing evaluation items based on social media activity. Some or all of the above-described processing by the evaluation unit can be performed using, for example, AI, or without AI. For example, the evaluation unit can collect evaluation items using an AI model that inputs the user's social media activity and outputs related evaluation items.

[0049] The learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, refers to past learning data. Past learning data includes, for example, learning date and time, learning content, learning results, etc., but is not limited to these examples. The learning unit, for example, selects an optimal learning algorithm based on the past learning data. The learning unit can also select an algorithm that improves learning efficiency from the past learning data. Furthermore, the learning unit can analyze the past learning data and customize the learning algorithm. This can improve learning efficiency by providing an optimal learning algorithm based on the past learning data. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or without AI. For example, the learning unit can optimize the learning algorithm using an AI model that uses past learning data as input and optimizes the learning algorithm.

[0050] The learning unit can customize training data based on the user's job duties and position. For example, the learning unit can customize training data based on the user's job duties. Job duties include, but are not limited to, sales, marketing, and development. For example, if the user is in sales, the learning unit will customize training data related to sales activities. The learning unit can also customize training data based on the user's position. Positions include, but are not limited to, manager, engineer, and assistant. For example, if the user is in a management position, the learning unit will prioritize providing training data related to management tasks. This improves the efficiency of learning by providing training data tailored to job duties and position. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can customize training data using an AI model that takes the user's job duties and position as input and customizes the training data.

[0051] The learning unit can weight the training data based on the submission timing of the evaluation data. For example, the learning unit weights the training data based on the submission timing of the evaluation data. The submission timing of the evaluation data includes, but is not limited to, the submission date and time, submission deadline, and submission frequency. For example, the learning unit weights the training data by giving more weight to recent evaluation data. The learning unit can also weight the training data by downplaying older evaluation data. Furthermore, the learning unit can weight moderately evaluation data. By providing training data weighting according to submission timing, the efficiency of learning can be improved. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can weight the training data using an AI model that takes the submission timing of the evaluation data as input and outputs the training data weights.

[0052] The learning unit can analyze a user's social media activity and collect relevant learning data. For example, the learning unit can analyze a user's social media activity. Social media activity includes, but is not limited to, posts, the number of likes, and the number of followers. For example, if a user indicates on social media that they are participating in a particular event, the learning unit can collect learning data related to that event. The learning unit can also collect learning data related to a particular project if a user indicates on social media that they are involved in that project. Furthermore, if a user shares information about a particular job on social media, the learning unit can collect learning data related to that job. This improves the efficiency of learning by providing learning data based on social media activity. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can collect learning data using an AI model that takes a user's social media activity as input and outputs relevant learning data.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The related materials suggestion system can also collect real-time user behavior data and incorporate it into its suggestions. For example, if a user frequently visits a particular website, it can suggest materials related to that website. Similarly, if a user uses a specific application, it can suggest materials related to that application. Furthermore, if a user participates in a specific event, it can suggest materials related to that event. This allows for more appropriate material suggestions based on the user's real-time behavior data.

[0055] The suggestion department can analyze a user's past purchase and search history, as well as their social media activity, to suggest relevant materials. For example, if a user frequently posts about a particular topic on social media, it can suggest materials related to that topic. Similarly, if a user belongs to a specific group, it can suggest materials related to that group. Furthermore, if a user participates in a specific event, it can suggest materials related to that event. This allows for more appropriate material suggestions based on the user's social media activity.

[0056] The proposal team can suggest relevant materials by considering the user's job responsibilities, position, and skill set. For example, if a user is proficient in a particular programming language, materials related to that language can be suggested. Similarly, if a user possesses specific job skills, materials related to those skills can be suggested. Furthermore, if a user holds a specific certification, materials related to that certification can be suggested. This allows for the suggestion of more appropriate materials based on the user's skill set.

[0057] The evaluation unit can analyze user behavior data in addition to user feedback to assess how useful the suggested materials were. For example, it can analyze how much the user viewed the suggested materials. It can also analyze how much the user utilized the suggested materials. Furthermore, it can analyze whether the user shared the suggested materials with other users. This allows the usefulness of the suggested materials to be evaluated based on user behavior data.

[0058] The learning unit can improve the accuracy of its suggestions by having the AI ​​learn from user behavior data in addition to collected evaluations. For example, it can learn from how much the user viewed the suggested materials. It can also learn from how much the user used the suggested materials. Furthermore, it can learn from whether the user shared the suggested materials with other users. This allows the accuracy of suggestions to be improved based on user behavior data.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The reception desk receives user input. User input includes text input, voice input, and image input. For example, it accepts text input when the user selects an application form, receives user instructions using voice input, and receives instructions by uploading an image of the application form using image input. Step 2: The proposal department suggests relevant materials based on the information received by the reception department. The proposal department uses an AI recommendation engine to suggest relevant materials based on past purchase and search history. For example, if the user selects application form A, it will suggest the creation manual and service materials that were previously purchased together with application form A. It can also suggest relevant materials considering the user's job duties and position. Step 3: The evaluation department collects evaluations of the materials proposed by the proposal department. The evaluation department collects feedback from users and evaluates whether the proposed materials were useful. For example, evaluations are collected using questionnaires, comments, and evaluation scores. Step 4: The learning unit uses the evaluations collected by the evaluation unit to train the AI. The learning unit uses machine learning algorithms and deep learning to improve the accuracy of the proposals. Based on the collected evaluations, the proposed algorithm can be optimized.

[0061] (Example 2) The related document suggestion system according to an embodiment of the present invention is a system that efficiently finds related documents necessary when creating an application form. When a user selects an application form, the AI ​​recommendation engine analyzes related documents purchased simultaneously by other users based on past data and suggests the most suitable related documents. For example, if a user selects application form A, the system suggests creation manuals and service documents previously purchased together with application form A. This suggests that users can easily find the necessary documents, significantly reducing the time spent searching. Furthermore, the AI ​​recommendation engine can also suggest the most suitable related documents for each individual user based on their past purchase and search history. This allows users to easily find the documents best suited to them, reducing the risk of selecting the wrong documents. This system not only significantly improves the efficiency of application form creation but also enhances user satisfaction. For example, when a user creates an application form, they can quickly find the necessary documents, leading to smoother work and reduced stress. Additionally, the reduced risk of selecting the wrong documents allows for the creation of accurate application forms. Thus, the related document suggestion system using the AI ​​recommendation engine contributes to improved efficiency and accuracy in application form creation. This allows the related document suggestion system to efficiently find and suggest the relevant documents that users need when creating an application form.

[0062] The related materials suggestion system according to this embodiment comprises a reception unit, a suggestion unit, an evaluation unit, and a learning unit. The reception unit receives user input. User input includes, but is not limited to, text input, voice input, and image input. For example, the reception unit receives text input when the user selects an application form. The reception unit can also receive user instructions using voice input. For example, if the user gives a voice command, "Select application form A," the reception unit receives that instruction. The reception unit can also receive user instructions using image input. For example, if the user uploads an image of an application form, the reception unit receives that image. The suggestion unit suggests related materials based on the information received by the reception unit. The suggestion unit suggests related materials based on past purchase history and search history, for example, using an AI recommendation engine. For example, if the user selects application form A, the suggestion unit suggests creation manuals and service materials that were previously purchased together with application form A. The suggestion unit can also suggest related materials considering the user's job duties and position. For example, the proposal unit suggests materials related to sales activities if the user is in sales. The evaluation unit collects evaluations of the materials suggested by the proposal unit. The evaluation unit collects feedback from users and evaluates whether the suggested materials were useful. The evaluation unit collects evaluations using methods such as questionnaires, comments, and evaluation scores. The learning unit uses the evaluations collected by the evaluation unit to train the AI. The learning unit improves the accuracy of suggestions using methods such as machine learning algorithms and deep learning. The learning unit can optimize the suggestion algorithm based on the collected evaluations. As a result, the related material suggestion system according to this embodiment can improve the accuracy of suggestions by suggesting related materials based on user input and learning from the collected evaluations.

[0063] The suggestion unit can suggest relevant materials based on past purchase and search history. For example, the suggestion unit can suggest relevant materials based on past purchase history. Past purchase history includes, but is not limited to, purchase date and time, purchased items, and purchase amount. For example, the suggestion unit can suggest creation manuals and service materials that were purchased together with application form A that the user previously purchased. The suggestion unit can also suggest relevant materials based on search history. Search history includes, but is not limited to, search keywords, search date and time, and search results. For example, the suggestion unit can suggest materials related to application form A that the user previously searched for. In this way, by suggesting relevant materials based on past history, the system can provide the user with the most suitable materials. Some or all of the above processing in the suggestion unit may be performed using, for example, AI, or not using AI. For example, the suggestion unit can suggest relevant materials using an AI model that takes past purchase and search history as input and outputs relevant materials.

[0064] The proposal department can suggest relevant materials considering the user's job duties and position. For example, the proposal department can suggest relevant materials considering the user's job duties. Job duties include, but are not limited to, sales, marketing, and development. For example, if the user is in sales, the proposal department will suggest materials related to sales activities. The proposal department can also suggest relevant materials considering the user's position. Positions include, but are not limited to, manager, engineer, and assistant. For example, if the user is in a management position, the proposal department will suggest materials related to management tasks. This allows for the provision of more appropriate materials by suggesting materials tailored to the user's job duties and position. Some or all of the above processing in the proposal department may be performed using, for example, AI, or not using AI. For example, the proposal department can suggest relevant materials using an AI model that takes the user's job duties and position as input and outputs relevant materials.

[0065] The evaluation unit can collect feedback from users and evaluate whether the proposed materials were useful. The evaluation unit, for example, collects feedback from users. Feedback includes, but is not limited to, questionnaires, comments, evaluation scores, etc. The evaluation unit can collect feedback, for example, by users answering questionnaires about the proposed materials. The evaluation unit can also collect feedback by users leaving comments about the proposed materials. Furthermore, the evaluation unit can collect feedback by users assigning evaluation scores to the proposed materials. In this way, collecting user feedback can improve the accuracy of suggestions. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can perform evaluation using an AI model that receives user feedback as input and outputs evaluation results.

[0066] The learning unit allows the AI ​​to learn based on the collected evaluations and improve the accuracy of the suggestions. The learning unit, for example, allows the AI ​​to learn based on the collected evaluations. Methods for AI learning include, but are not limited to, machine learning algorithms and deep learning. The learning unit, for example, uses a machine learning algorithm to optimize the proposal algorithm based on the collected evaluations. The learning unit can also use deep learning to optimize the proposal algorithm based on the collected evaluations. As a result, the AI ​​learns and the accuracy of the suggestions improves. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can perform learning using an AI model that uses the collected evaluations as input and outputs an optimized proposal algorithm.

[0067] The proposal department can periodically check for updates to the proposed materials to ensure that the proposed materials are up-to-date. For example, the proposal department can periodically check for updates to the materials. This includes, but is not limited to, the date and time of updates, the content of the updates, and the frequency of updates. For example, the proposal department can check the date and time of updates and propose the latest materials. The proposal department can also check the content of the updates and propose materials that contain the latest information. Furthermore, the proposal department can check the frequency of updates and prioritize proposing materials that are frequently updated. This ensures that the latest materials are provided, thereby providing users with useful information. Some or all of the above processing in the proposal department may be performed using, for example, AI, or not using AI. For example, the proposal department can check for updates to the materials using an AI model that takes the update information as input and outputs the latest materials.

[0068] The proposal unit can provide an explanation showing how the proposed materials are incorporated into the business workflow. For example, the proposal unit can provide an explanation showing how the proposed materials are incorporated into the business workflow. The business workflow includes, but is not limited to, business procedures, process diagrams, and flowcharts. For example, the proposal unit can provide an explanation showing business procedures. The proposal unit can also provide an explanation showing the business workflow using process diagrams. Furthermore, the proposal unit can provide an explanation showing the business workflow using flowcharts. This allows users to effectively utilize the materials by showing how to use them. Some or all of the above processing in the proposal unit may be performed using, for example, AI, or not using AI. For example, the proposal unit can provide an explanation using an AI model that takes information about the business workflow as input and outputs an explanation showing the business workflow.

[0069] The proposal department can quantitatively demonstrate how much work time will be reduced by using the proposed materials. For example, the proposal department can quantitatively demonstrate how much work time will be reduced by using the proposed materials. Methods for demonstrating the work time reduction effect include, but are not limited to, time measurement methods and comparison criteria. For example, the proposal department can quantitatively demonstrate the work time reduction effect by measuring the work time before and after using the proposed materials and showing the difference. The proposal department can also show, on average, how much work time will be reduced by using the proposed materials, based on past data. Furthermore, the proposal department can demonstrate the work time reduction effect according to the user's job content and position. For example, the proposal department can show a sales user how much the time spent on sales activities will be reduced by using the proposed materials. This can improve convenience for the user by demonstrating the work time reduction effect. Some or all of the above processing in the proposal department may be performed using, for example, AI, or not using AI. For example, the proposal unit can quantitatively demonstrate the effect of reducing work time by using an AI model that takes measurement data of work time as input and outputs the effect of reducing work time.

[0070] The reception unit can estimate the user's emotion and adjust the display method of the input interface based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion. Methods for estimating the user's emotion include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the reception unit can recognize the user's facial expression using a camera and estimate the emotion. The reception unit can also analyze the user's voice using a microphone to estimate the emotion. Furthermore, the reception unit can analyze the user's input text to estimate the emotion. The reception unit adjusts the display method of the input interface based on the estimated user's emotion. For example, if the user is stressed, the reception unit can provide a simple interface and minimize input steps. Alternatively, if the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input to allow the user to quickly enter necessary information. This improves user convenience by providing an interface that corresponds to the user's emotion. Some or all of the above-described processing in the reception unit may be performed using, for example, AI or without AI. For example, the reception desk can use an AI model that takes user emotion data as input and outputs how the interface should be displayed to adjust how the interface is displayed.

[0071] The reception desk can analyze the user's past input history and suggest the optimal input method. For example, the reception desk analyzes the user's past input history. Past input history includes, but is not limited to, input date and time, input content, and input frequency. For example, the reception desk can automatically display as a candidate the type of application form the user has frequently entered in the past. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest the type of application form to be used during a specific time period based on the user's past input history. This improves the user's input efficiency by suggesting the optimal input method based on past input history. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not. For example, the reception desk can suggest an input method using an AI model that takes past input history as input and outputs the optimal input method.

[0072] The reception desk can customize input fields based on the user's job duties and position. For example, the reception desk can customize input fields based on the user's job duties. Job duties include, but are not limited to, sales, marketing, and development. For example, if the user is in sales, the reception desk will customize the input fields of application forms related to sales activities. The reception desk can also customize input fields based on the user's position. Positions include, but are not limited to, manager, engineer, and assistant. For example, if the user is in a management position, the reception desk will prioritize displaying input fields of application forms related to management tasks. This improves the user's input efficiency by providing input fields that are appropriate to their job duties and position. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can customize input fields using an AI model that takes the user's job duties and position as input and customizes the input fields.

[0073] The reception desk can estimate the user's emotions and determine input priorities based on those estimated emotions. For example, the reception desk can estimate the user's emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, voice analysis, and text analysis. For example, the reception desk can use a camera to recognize the user's facial expressions and estimate their emotions. It can also use a microphone to analyze the user's voice and estimate their emotions. Furthermore, it can analyze the user's input text and estimate their emotions. Based on the estimated user emotions, the reception desk determines input priorities. For example, if the user is stressed, the reception desk will prioritize displaying important input items and postpone others. If the user is relaxed, the reception desk can display all input items equally. Furthermore, if the user is in a hurry, the reception desk can display only the most important input items to allow for quick completion. This improves user input efficiency by providing input priorities that correspond to the user's emotions. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may determine the priority of inputs using an AI model that receives user emotion data as input and outputs the priority of inputs.

[0074] The reception unit can prioritize displaying relevant input fields by taking into account the user's geographical location information. The reception unit, for example, displays input fields by taking into account the user's geographical location information. Geographical location information includes, but is not limited to, GPS data, IP address, location information services, etc. For example, when the user is in a specific area, the reception unit can prioritize displaying input fields on the application form related to that area. Furthermore, when the user is on a business trip, the reception unit can prioritize displaying input fields on the application form related to the business trip destination. Furthermore, when the user is at home, the reception unit can prioritize displaying input fields on the application form related to the user's home. This can improve the user's input efficiency by providing input fields based on the geographical location information. Some or all of the above-described processing by the reception unit can be performed, for example, using AI, or can be performed without using AI. For example, the reception unit can display input fields using an AI model that inputs the user's geographical location information and outputs relevant input fields.

[0075] The reception desk can analyze a user's social media activity and suggest relevant input fields. For example, the reception desk can analyze a user's social media activity. Social media activity includes, but is not limited to, posts, likes, and follower counts. For example, if a user indicates on social media that they will be participating in a particular event, the reception desk can suggest input fields for an application form related to that event. The reception desk can also suggest input fields for an application form related to a particular project if a user indicates on social media that they are involved in that project. Furthermore, if a user shares information about a particular job on social media, the reception desk can suggest input fields for an application form related to that job. This improves the efficiency of user input by providing input fields based on social media activity. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can suggest input fields using an AI model that takes a user's social media activity as input and outputs relevant input fields.

[0076] The suggestion unit can estimate the user's emotion and adjust the way the suggestion is expressed based on the estimated user's emotion. The suggestion unit, for example, estimates the user's emotion. Methods for estimating the user's emotion include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the suggestion unit can recognize the user's facial expression using a camera and estimate the emotion. The suggestion unit can also analyze the user's voice using a microphone to estimate the emotion. Furthermore, the suggestion unit can analyze the user's input text to estimate the emotion. The suggestion unit adjusts the way the suggestion is expressed based on the estimated user's emotion. For example, if the user is stressed, the suggestion unit can make a simple and easy-to-understand suggestion. If the user is relaxed, the suggestion unit can make a suggestion that includes detailed information. Furthermore, if the user is in a hurry, the suggestion unit can make a quick suggestion that covers the main points. This improves user convenience by providing a way to express the suggestion based on the user's emotion. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI or without AI. For example, the suggestion unit can adjust the way the suggestion is expressed using an AI model that takes the user's emotional data as input and outputs the way the suggestion is expressed.

[0077] The proposal function can adjust the level of detail of a proposal based on the importance of the document. For example, the proposal function can adjust the level of detail of a proposal based on the importance of the document. Criteria for evaluating the importance of a document include, but are not limited to, frequency of use, user ratings, and relevance. For example, the proposal function can provide a detailed explanation along with the proposal for important documents. For less important documents, it can provide a concise explanation along with the proposal. Furthermore, for documents of moderate importance, it can provide a proposal with an appropriate level of detail. This improves user convenience by providing a level of detail of proposals that matches the importance of the document. Some or all of the above processing in the proposal function may be performed using, for example, AI, or not using AI. For example, the proposal function can adjust the level of detail of a proposal using an AI model that takes the importance of the document as input and outputs the level of detail of the proposal.

[0078] The proposal unit can apply different proposal algorithms depending on the category of the document. For example, the proposal unit can apply different proposal algorithms depending on the category of the document. Document categories include, but are not limited to, technical documents, marketing documents, and educational documents. For example, in the case of technical documents, the proposal unit can apply a proposal algorithm that emphasizes technical details. In the case of marketing documents, it can also apply a proposal algorithm that emphasizes visual elements. Furthermore, in the case of legal documents, it can also apply a proposal algorithm that emphasizes legal requirements. This improves user convenience by providing proposal algorithms tailored to the category of the document. Some or all of the above processing in the proposal unit may be performed using, for example, AI, or not using AI. For example, the proposal unit can apply a proposal algorithm using an AI model that takes the category of the document as input and outputs a proposal algorithm.

[0079] The suggestion unit can estimate the user's emotion and adjust the length of the suggestion based on the estimated user's emotion. The suggestion unit, for example, estimates the user's emotion. Methods for estimating the user's emotion include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the suggestion unit can recognize the user's facial expression using a camera and estimate the emotion. The suggestion unit can also analyze the user's voice using a microphone to estimate the emotion. Furthermore, the suggestion unit can analyze the user's input text to estimate the emotion. The suggestion unit adjusts the length of the suggestion based on the estimated user's emotion. For example, if the user is stressed, the suggestion unit can make a short, concise suggestion. If the user is relaxed, the suggestion unit can make a longer suggestion with detailed explanations. Furthermore, if the user is in a hurry, the suggestion unit can make a quick, concise suggestion. This improves user convenience by providing a suggestion length that corresponds to the user's emotion. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI or without AI. For example, the suggestion section can adjust the length of a suggestion using an AI model that takes user emotion data as input and outputs the length of the suggestion.

[0080] The proposal department can determine the priority of proposals based on the submission timing of the materials. For example, the proposal department can determine the priority of proposals based on the submission timing of the materials. The submission timing of materials includes, but is not limited to, submission date and time, submission deadline, and submission frequency. For example, the proposal department may prioritize proposals with approaching deadlines. It may also postpone proposals with later submission dates. Furthermore, it may assign appropriate priority to proposals with medium submission dates. This improves user convenience by providing a priority of proposals according to the submission timing. Some or all of the above processing in the proposal department may be performed using, for example, AI, or not using AI. For example, the proposal department can determine the priority of proposals using an AI model that takes the submission timing of materials as input and outputs the priority of proposals.

[0081] The suggestion unit can adjust the order of suggestions based on the relevance of the materials. The suggestion unit, for example, adjusts the order of suggestions based on the relevance of the materials. Criteria for evaluating the relevance of materials include, but are not limited to, content similarity, common keywords, and related topics. For example, the suggestion unit can suggest the most relevant material first. Alternatively, the suggestion unit can suggest materials with a moderate relevance next. Furthermore, the suggestion unit can suggest materials with little relevance last. This improves user convenience by providing a suggestion order based on relevance. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can adjust the order of suggestions using an AI model that inputs the relevance of materials and outputs the order of suggestions.

[0082] The evaluation unit can estimate the user's emotions and adjust the evaluation collection method based on the estimated user emotions. For example, the evaluation unit estimates the user's emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, voice analysis, and text analysis. For example, the evaluation unit can use a camera to recognize the user's facial expressions and estimate their emotions. The evaluation unit can also use a microphone to analyze the user's voice and estimate their emotions. Furthermore, the evaluation unit can analyze the user's input text and estimate their emotions. Based on the estimated user emotions, the evaluation unit adjusts the evaluation collection method. For example, if the user is stressed, the evaluation unit provides a simple evaluation method. If the user is relaxed, the evaluation unit can also provide a detailed evaluation method. Furthermore, if the user is in a hurry, the evaluation unit can provide a method that allows for rapid evaluation collection. This improves user convenience by providing evaluation collection methods that are tailored to the user's emotions. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can adjust the method of collecting evaluations using an AI model that takes user emotional data as input and outputs a method of collecting evaluations.

[0083] The evaluation unit can select the optimal evaluation method by referring to the user's past evaluation history. The evaluation unit, for example, refers to the user's past evaluation history. The past evaluation history includes, for example, evaluation date and time, evaluation content, evaluation score, etc., but is not limited to these examples. The evaluation unit, for example, preferentially suggests evaluation methods used by the user in the past. The evaluation unit can also select the most appropriate evaluation method from the user's past evaluation history. Furthermore, the evaluation unit can analyze the user's past evaluation history and customize the evaluation method. This can improve user convenience by providing the optimal evaluation method based on the past evaluation history. Some or all of the above-mentioned processing in the evaluation unit can be performed, for example, using AI or without AI. For example, the evaluation unit can select the evaluation method using an AI model that inputs the past evaluation history and outputs the optimal evaluation method.

[0084] The evaluation unit can customize evaluation items based on the user's job duties and position. For example, the evaluation unit can customize evaluation items based on the user's job duties. Job duties include, but are not limited to, sales, marketing, and development. For example, if the user is in sales, the evaluation unit will customize evaluation items related to sales activities. The evaluation unit can also customize evaluation items based on the user's position. Positions include, but are not limited to, manager, engineer, and assistant. For example, if the user is in a management position, the evaluation unit will prioritize displaying evaluation items related to management tasks. This improves user convenience by providing evaluation items tailored to job duties and position. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can customize evaluation items using an AI model that takes the user's job duties and position as input and customizes the evaluation items.

[0085] The evaluation unit can estimate the user's emotions and determine the priority of the evaluations based on the estimated user's emotions. The evaluation unit, for example, estimates the user's emotions. Methods for estimating the user's emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the evaluation unit can recognize the user's facial expressions using a camera and estimate the user's emotions. The evaluation unit can also analyze the user's voice using a microphone to estimate the user's emotions. Furthermore, the evaluation unit can analyze the user's input text to estimate the user's emotions. The evaluation unit determines the priority of the evaluations based on the estimated user's emotions. For example, if the user is feeling stressed, the evaluation unit can prioritize displaying important evaluation items and postpone other items. Also, if the user is relaxed, the evaluation unit can display all evaluation items equally. Furthermore, if the user is in a hurry, the evaluation unit can display only the most important evaluation items to enable the user to complete the evaluation quickly. This improves user convenience by providing evaluation priorities according to the user's emotions. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may determine the priority of evaluations using an AI model that receives user emotion data as input and outputs the priority of evaluations.

[0086] The evaluation unit can prioritize the collection of relevant evaluation items by taking into account the user's geographical location information. For example, the evaluation unit collects evaluation items by taking into account the user's geographical location information. Geographical location information includes, but is not limited to, GPS data, IP addresses, and location services. For example, if the user is in a specific region, the evaluation unit will prioritize displaying evaluation items related to that region. The evaluation unit can also prioritize displaying evaluation items related to the user's business trip destination if the user is on a business trip. Furthermore, if the evaluation unit is at home, it can prioritize displaying evaluation items related to home. This improves user convenience by providing evaluation items based on geographical location information. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can collect evaluation items using an AI model that takes the user's geographical location information as input and outputs relevant evaluation items.

[0087] The evaluation unit can analyze the user's social media activity and collect related evaluation items. The evaluation unit can analyze, for example, the user's social media activity. Social media activity includes, but is not limited to, the content of posts, the number of likes, and the number of followers. For example, if the user indicates on social media that they will participate in a specific event, the evaluation unit can collect evaluation items related to the event. Furthermore, if the user indicates on social media that they are involved in a specific project, the evaluation unit can also collect evaluation items related to the project. Furthermore, if the user shares information about a specific business on social media, the evaluation unit can also collect evaluation items related to the business. This can improve user convenience by providing evaluation items based on social media activity. Some or all of the above-described processing by the evaluation unit can be performed using, for example, AI, or without AI. For example, the evaluation unit can collect evaluation items using an AI model that inputs the user's social media activity and outputs related evaluation items.

[0088] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, the learning unit estimates the user's emotions. Methods for estimating user emotions include, but are not limited to, facial recognition, speech analysis, and text analysis. For example, the learning unit can use a camera to recognize the user's facial expressions and estimate their emotions. The learning unit can also use a microphone to analyze the user's voice and estimate their emotions. Furthermore, the learning unit can analyze the user's input text and estimate their emotions. Based on the estimated emotions of the user, the learning unit selects training data. For example, if the user is stressed, the learning unit selects training data that helps reduce stress. If the user is relaxed, the learning unit can also select training data to maintain that relaxed state. Furthermore, if the user is in a hurry, the learning unit can select data that allows for rapid learning. This improves the efficiency of learning by providing training data that corresponds to the user's emotions. Some or all of the above-described processes in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can select learning data using an AI model that takes user emotional data as input and selects learning data.

[0089] The learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, refers to past learning data. Past learning data includes, for example, learning date and time, learning content, learning results, etc., but is not limited to these examples. The learning unit, for example, selects an optimal learning algorithm based on the past learning data. The learning unit can also select an algorithm that improves learning efficiency from the past learning data. Furthermore, the learning unit can analyze the past learning data and customize the learning algorithm. This can improve learning efficiency by providing an optimal learning algorithm based on the past learning data. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI or without AI. For example, the learning unit can optimize the learning algorithm using an AI model that uses past learning data as input and optimizes the learning algorithm.

[0090] The learning unit can customize training data based on the user's job duties and position. For example, the learning unit can customize training data based on the user's job duties. Job duties include, but are not limited to, sales, marketing, and development. For example, if the user is in sales, the learning unit will customize training data related to sales activities. The learning unit can also customize training data based on the user's position. Positions include, but are not limited to, manager, engineer, and assistant. For example, if the user is in a management position, the learning unit will prioritize providing training data related to management tasks. This improves the efficiency of learning by providing training data tailored to job duties and position. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can customize training data using an AI model that takes the user's job duties and position as input and customizes the training data.

[0091] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. The learning unit, for example, estimates the user's emotions. Methods for estimating the user's emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the learning unit recognizes the user's facial expressions using a camera and estimates the user's emotions. The learning unit can also analyze the user's voice using a microphone to estimate the user's emotions. Furthermore, the learning unit can analyze the user's input text to estimate the user's emotions. The learning unit adjusts the frequency of learning based on the estimated user emotions. For example, if the user is stressed, the learning unit can reduce the frequency of learning to reduce the burden. Also, if the user is relaxed, the learning unit can increase the frequency of learning to improve efficiency. Furthermore, if the user is in a hurry, the learning unit can adjust the frequency of learning to allow the user to complete the learning quickly. This can improve learning efficiency by providing a learning frequency that corresponds to the user's emotions. Some or all of the above-described processing in the learning unit can be performed using, for example, AI or without AI. For example, the learning unit can adjust the frequency of learning using an AI model that takes user emotional data as input and outputs the frequency of learning.

[0092] The learning unit can weight the training data based on the submission timing of the evaluation data. For example, the learning unit weights the training data based on the submission timing of the evaluation data. The submission timing of the evaluation data includes, but is not limited to, the submission date and time, submission deadline, and submission frequency. For example, the learning unit weights the training data by giving more weight to recent evaluation data. The learning unit can also weight the training data by downplaying older evaluation data. Furthermore, the learning unit can weight moderately evaluation data. By providing training data weighting according to submission timing, the efficiency of learning can be improved. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can weight the training data using an AI model that takes the submission timing of the evaluation data as input and outputs the training data weights.

[0093] The learning unit can analyze a user's social media activity and collect relevant learning data. For example, the learning unit can analyze a user's social media activity. Social media activity includes, but is not limited to, posts, the number of likes, and the number of followers. For example, if a user indicates on social media that they are participating in a particular event, the learning unit can collect learning data related to that event. The learning unit can also collect learning data related to a particular project if a user indicates on social media that they are involved in that project. Furthermore, if a user shares information about a particular job on social media, the learning unit can collect learning data related to that job. This improves the efficiency of learning by providing learning data based on social media activity. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can collect learning data using an AI model that takes a user's social media activity as input and outputs relevant learning data. === Hard Collateral 1-1 === Each of the multiple elements described above, including the reception unit, proposal unit, evaluation unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives user input using the touch panel 38A or microphone 38B of the smart device 14. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and proposes relevant materials using an AI recommendation engine. The evaluation unit is implemented, for example, by the control unit 46A of the smart device 14, and collects feedback from the user. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and optimizes the proposal algorithm based on the collected evaluations. === Hard Collateral 1-2 === Each of the multiple elements described above, including the reception unit, proposal unit, evaluation unit, and learning unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives the user's voice input using the microphone 238 of the smart glasses 214. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and proposes relevant materials using an AI recommendation engine. The evaluation unit is implemented, for example, by the control unit 46A of the smart glasses 214, and collects feedback from the user. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and optimizes the proposal algorithm based on the collected evaluations. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, proposal unit, evaluation unit, and learning unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit receives a user's voice input using the microphone 238 of the headset-type terminal 314. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and suggests related materials using an AI recommendation engine. The evaluation unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and collects feedback from the user. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and optimizes the proposal algorithm based on the collected evaluations. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, proposal unit, evaluation unit, and learning unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives a user's voice input using the microphone 238 of the robot 414. The proposal unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and proposes related materials using an AI recommendation engine. The evaluation unit is realized, for example, by the control unit 46A of the robot 414 and collects feedback from the user. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and optimizes the proposal algorithm based on the collected evaluations.

[0094] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0095] The related material suggestion system can also collect real-time behavioral data of the user and reflect it in the suggestions. For example, if the user frequently visits a specific website, it can suggest materials related to that website. Also, if the user uses a specific application, it can suggest materials related to that application. Furthermore, if the user is participating in a specific event, it can suggest materials related to that event. In this way, it is possible to suggest more appropriate materials based on the user's real-time behavioral data.

[0096] The suggestion unit can analyze the user's social media activity in addition to the user's past purchase history and search history to suggest related materials. For example, if the user frequently posts about a specific topic on social media, it can suggest materials related to that topic. Also, if the user is a member of a specific group, it can suggest materials related to that group. Furthermore, if the user is attending a specific event, it can suggest materials related to that event. This makes it possible to suggest more appropriate materials based on the user's social media activity.

[0097] The suggestion unit can suggest relevant materials taking into consideration the user's skill set in addition to the user's job content and job title. For example, if the user is familiar with a specific programming language, materials related to that language can be suggested. Also, if the user has specific business skills, materials related to those skills can be suggested. Furthermore, if the user has specific qualifications, materials related to those qualifications can be suggested. This makes it possible to suggest more appropriate materials based on the user's skill set.

[0098] The evaluation unit can analyze the user's behavioral data in addition to the user's feedback to evaluate how useful the suggested materials were. For example, it can analyze how much the user viewed the suggested materials. It can also analyze how much the user used the suggested materials. It can also analyze whether the user shared the suggested materials with other users. In this way, it is possible to evaluate the usefulness of the suggested materials based on the user's behavioral data.

[0099] The learning unit allows the AI ​​to learn based on collected evaluations as well as user behavioral data, thereby improving the accuracy of suggestions. For example, it can learn based on how much a user has viewed the suggested materials. It can also learn based on how much a user has used the suggested materials. It can also learn based on whether a user has shared the suggested materials with other users. This allows the accuracy of suggestions to be improved based on user behavioral data.

[0100] The suggestion unit can estimate the user's emotions and adjust the timing of suggestions based on the estimated user's emotions. For example, if the user is feeling stressed, the suggestion unit can delay the timing of suggestions. Also, if the user is relaxed, the suggestion unit can advance the timing of suggestions. Furthermore, if the user is in a hurry, the suggestion unit can make suggestions quickly. In this way, by providing the timing of suggestions according to the user's emotions, convenience for the user can be improved.

[0101] The suggestion unit can estimate the user's emotions and customize the content of the suggestions based on the estimated user's emotions. For example, if the user is feeling stressed, the suggestion unit can suggest simple and easy-to-understand content. If the user is relaxed, the suggestion unit can also suggest content that includes detailed information. Furthermore, if the user is in a hurry, the suggestion unit can also suggest quick content that gets to the point. In this way, by providing suggested content that corresponds to the user's emotions, convenience for the user can be improved.

[0102] The evaluation unit can estimate the user's emotions and adjust the evaluation feedback method based on the estimated user's emotions. For example, if the user is feeling stressed, the evaluation unit can provide a simple feedback method. If the user is relaxed, the evaluation unit can provide a detailed feedback method. Furthermore, if the user is in a hurry, the evaluation unit can provide a method for quickly collecting feedback. In this way, by providing a feedback method according to the user's emotions, it is possible to improve user convenience.

[0103] The learning unit can estimate the user's emotions and adjust the learning content based on the estimated user's emotions. For example, if the user is feeling stressed, the learning unit can provide content that helps reduce stress. Also, if the user is relaxed, the learning unit can provide content to help the user maintain a relaxed state. Furthermore, if the user is in a hurry, the learning unit can provide content that allows the user to learn quickly. In this way, learning efficiency can be improved by providing learning content that corresponds to the user's emotions.

[0104] The suggestion unit can estimate the user's emotions and determine the priority of suggestions based on the estimated user's emotions. For example, if the user is feeling stressed, the suggestion unit can prioritize and display important suggestions. Also, if the user is relaxed, the suggestion unit can display all suggestions evenly. Furthermore, if the user is in a hurry, the suggestion unit can display only the most important suggestions so that the suggestions can be completed quickly. This can improve user convenience by providing the priority of suggestions according to the user's emotions.

[0105] The processing flow of the second embodiment will be briefly explained below.

[0106] Step 1: The reception unit receives user input. User input includes text input, voice input, image input, etc. For example, the reception unit receives text input when the user selects an application form, receives user instructions using voice input, or receives instructions by uploading an image of the application form using image input. Step 2: The suggestion unit suggests related materials based on the information received by the reception unit. Using an AI recommendation engine, the suggestion unit suggests related materials based on past purchase history and search history. For example, if a user selects Application Form A, the suggestion unit suggests creation manuals and service materials that were previously purchased together with Application Form A. It can also suggest related materials taking into account the user's job description and position. Step 3: The evaluation section collects evaluations of the materials proposed by the proposal section. The evaluation section collects feedback from users and evaluates whether the proposed materials were useful. For example, evaluations are collected using questionnaires, comments, evaluation scores, etc. Step 4: The learning unit trains the AI ​​based on the evaluations collected by the evaluation unit. The learning unit uses machine learning algorithms and deep learning to improve the accuracy of the suggestions. The suggestion algorithm can be optimized based on the collected evaluations.

[0107] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0108] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0109] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0110] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0114] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, 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 microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, 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.

[0119] 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 processing 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.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0121] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0122] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0125] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0126] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0127] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0128] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0129] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0130] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. 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 microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, 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.

[0135] 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 processing 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.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0137] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0141] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0142] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0143] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0144] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0145] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0146] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. 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 microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0147] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0150] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0151] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, 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.

[0152] 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 processing 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.

[0153] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0154] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0155] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0156] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0157] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0158] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0161] FIG. 9 illustrates 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. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0162] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically 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.

[0163] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0164] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0165] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0166] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, 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. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0167] 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.

[0168] 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 the specific processing in accordance with the specific processing program 56.

[0169] 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.

[0170] 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.

[0171] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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. A processor also includes 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.

[0172] The hardware resource that executes the specific process 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 process may be a single processor.

[0173] 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.

[0174] 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.

[0175] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0176] 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.

[0177] 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.

[0178] [Explanation of symbols]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives input from a user; a suggestion unit that suggests related materials based on the information received by the reception unit; an evaluation unit that collects evaluations of the materials proposed by the proposal unit; A learning unit that allows AI to learn based on the evaluations collected by the evaluation unit. A system characterized by:

2. The proposal unit Suggest related materials based on past purchase and search history The system of claim 1 .

3. The proposal unit Suggest relevant materials based on the user's job description and position The system of claim 1 .

4. The evaluation unit Gather user feedback and evaluate whether the proposed materials were helpful The system of claim 1 .

5. The learning unit AI learns from collected evaluations and improves the accuracy of its suggestions The system of claim 1 .

6. The proposal unit Regularly check for updates to the materials to ensure the suggested materials are up to date. The system of claim 1 .

7. The proposal unit Provide a description of how the proposed materials will fit into the business flow The system of claim 1 .

8. The proposal unit Quantitatively show how much work time will be saved by using the proposed materials The system of claim 1 .

Images