system

Abstract

The system according to this embodiment aims to effectively utilize past in-house assets and create high-quality slides quickly and inexpensively. [Solution] The system according to the embodiment comprises a vectorization unit, a reception unit, a search unit, and a generation unit. The vectorization unit converts past company assets into a vector database. The reception unit receives user requests. The search unit searches the vector database for relevant slides based on the information entered by the reception unit. The generation unit generates new slides by combining the slides found by the search unit.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that beneficial in-house assets in the past are not effectively utilized, and new slides are often created from scratch, resulting in poor efficiency.

[0005] The system according to the embodiment aims to effectively utilize past in-house assets and create high-quality slides quickly and at low cost.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a vectorization unit, a reception unit, a search unit, and a generation unit. The vectorization unit converts past company assets into a vector database. The reception unit receives user requests. The search unit searches the vector database for relevant slides based on the information entered by the reception unit. The generation unit generates new slides by combining the slides found by the search unit. [Effects of the Invention]

[0007] The system according to this embodiment can effectively utilize past in-house assets and create high-quality slides quickly and inexpensively. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

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

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, 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 slide generation system according to an embodiment of the present invention is a system that creates high-quality slides faster and cheaper by patching together existing slides like a crazy quilt. This slide generation system vectorizes past internal assets (such as slides) using a multimodal LLM to make them searchable. Next, when the user inputs the content of the slides they need, the system searches for relevant slides from the vector database and combines them like a crazy quilt to generate new slides. This mechanism makes it possible to generate slides in a clear and easy-to-understand format rooted in the company culture. For example, past internal assets are vectorized using a multimodal LLM to make them searchable. At this time, information such as the content, layout, and design of the slides is saved as vectors to make them searchable. For example, slides related to a specific theme or keyword can be easily searched. Next, the user inputs the content of the slides they need. For example, they input a specific request such as "I need slides for a new product presentation." This information is input into the system. Based on the input information, the system searches for relevant slides from the vector database. For example, it searches for past slides related to a new product presentation and selects appropriate slides from among them. The selected slides are combined like a crazy quilt to generate new slides. For example, by cutting out appropriate parts from past slides and pasting them into new slides, slides tailored to user requirements can be created. This mechanism allows for the creation of high-quality slides faster and at a lower cost by leveraging valuable past assets. Furthermore, because slides can be generated in a clear and easy-to-understand format rooted in the company culture, user satisfaction also improves. In short, the slide generation system can create high-quality slides faster and at a lower cost by utilizing past company assets.

[0029] The slide generation system according to this embodiment comprises a vectorization unit, a reception unit, a search unit, and a generation unit. The vectorization unit converts past company assets into a vector database. The vectorization unit saves information such as slide content, layout, and design as vectors. For example, the vectorization unit saves slide content as text data and layout information as coordinate data. The vectorization unit can also save design information as attribute data such as color and font size. For example, the vectorization unit analyzes slide content using natural language processing technology, extracts important keywords, and vectorizes them. The reception unit inputs user requests. For example, the reception unit allows users to input specific requests such as "I need slides for a new product presentation." For example, the reception unit provides an interface that accepts text input and voice input. The search unit searches the vector database for relevant slides based on the information entered by the reception unit. The search unit can search for slides related to specific themes or keywords. For example, the search unit searches the vector database for slides using keyword matching technology. Furthermore, the search unit can also search for related slides using an algorithm that evaluates the similarity of content. The generation unit generates new slides by combining the slides found by the search unit. The generation unit can, for example, cut out appropriate parts from past slides and paste them into new slides. For example, the generation unit can automatically adjust the slide layout to create a consistent design. The generation unit can also generate new slides using templates. For example, the generation unit can select an appropriate template based on the user's request and generate slides according to that template. As a result, the slide generation system according to this embodiment can utilize past in-house assets and create high-quality slides faster and at a lower cost.

[0030] The vectorization unit can save slide content, layout, and design information as vectors. For example, the vectorization unit can save slide content as text data. For example, the vectorization unit can analyze slide content using natural language processing technology, extract important keywords, and vectorize them. The vectorization unit can also save slide layout information as coordinate data. For example, the vectorization unit can save the position information of each element of the slide as coordinate data so that it can be reconstructed later. The vectorization unit can also save slide design information as attribute data such as color and font size. For example, the vectorization unit can save design information such as slide background color, font size, and font type as vectors. By saving slide content, layout, and design information as vectors, searchability is improved. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or without AI. For example, the vectorization unit can use an AI model that analyzes slide content using natural language processing technology, extracts important keywords, and vectorizes them.

[0031] The search unit can search for slides related to specific themes or keywords. For example, the search unit can search for slides in the vector database using keyword matching technology. The search unit can also search for related slides using algorithms that evaluate content similarity. For example, the search unit can evaluate the similarity of slide content using cosine similarity. Cosine similarity calculates the angle between two vectors in a vector space model; the smaller the angle, the higher the similarity. The search unit can also evaluate the similarity of slide content using the Jaccard coefficient. The Jaccard coefficient is the value obtained by dividing the size of the intersection of two sets by the size of the whole, indicating the degree of overlap between the sets. Furthermore, the search unit can evaluate the importance of slide content using TF-IDF. TF-IDF is an index that evaluates the importance of words in a document, and it is used to evaluate the importance of slide content. This allows for a quick response to user requests by searching for slides related to specific themes or keywords. Some or all of the processing described above in the search unit may be performed using AI, for example, or without AI. For example, the search unit can use an AI model that searches slides in a vector database using keyword matching technology.

[0032] The generation unit can cut out appropriate parts from past slides and paste them into new slides. For example, the generation unit can cut out appropriate parts from past slides and paste them into new slides. For example, the generation unit can automatically adjust the slide layout to create a consistent design. The generation unit can also generate new slides using templates. For example, the generation unit can select an appropriate template based on user requests and generate slides according to that template. Furthermore, the generation unit can automatically summarize the content of slides, extract important information, and reflect it in new slides. For example, the generation unit can summarize the content of slides using natural language processing technology, extract important keywords and phrases, and reflect them in new slides. This allows for efficient slide creation by cutting out appropriate parts from past slides and pasting them into new slides. Some or all of the above processes in the generation unit may be performed using AI, for example, or not. For example, the generation unit can use an AI model that automatically summarizes the content of slides, extracts important information, and reflects it in new slides.

[0033] The reception desk allows users to input specific requests, such as needing presentation slides for a new product. For example, the reception desk can provide an interface that accepts text and voice input. The reception desk can also analyze the user's input and extract information to generate appropriate slides. For example, the reception desk can use natural language processing to analyze the user's request and extract important keywords and phrases. Furthermore, the reception desk can suggest appropriate templates based on the user's request. For example, the reception desk can suggest templates suitable for the presentation's purpose and target audience based on the user's request. This allows the system to generate appropriate slides based on the user's input of specific requests. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk could use an AI model to analyze the user's request and extract information to generate appropriate slides.

[0034] The generation unit can create slides that meet the user's requirements. For example, the generation unit can select an appropriate template based on the user's requirements and generate slides according to that template. For example, the generation unit can select a template that is suitable for the purpose and target audience of the presentation based on the user's requirements. The generation unit can also automatically summarize the content of the slides, extract important information, and reflect it in the new slides. For example, the generation unit can use natural language processing technology to summarize the content of the slides, extract important keywords and phrases, and reflect them in the new slides. Furthermore, the generation unit can automatically adjust the layout of the slides to generate a consistent design. For example, the generation unit can save the positional information of each element of the slides as coordinate data so that it can be reconstructed later. This improves user satisfaction by creating slides that meet the user's requirements. Some or all of the above processes in the generation unit may be performed using AI, for example, or not. For example, the generation unit can use an AI model that automatically summarizes the content of the slides, extracts important information, and reflects it in the new slides.

[0035] The vectorization unit can save not only the content of the slides, but also the intentions and objectives of the slide creator as vectors. For example, if the slide creator wants to emphasize the features of a new product, that intention is saved as a vector. Also, if the slide creator has created a presentation aimed at a specific market segment, that objective is saved as a vector. Furthermore, if the slide creator has created slides for competitive analysis, that intention is saved as a vector. By saving the slide creator's intentions and objectives as vectors, it becomes possible to search for more appropriate slides. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or not. For example, the vectorization unit can use an AI model that analyzes the intentions and objectives of the slide creator and saves them as vectors.

[0036] The vectorization unit can weight the vectors during vectorization, taking into account the frequency of use and evaluation of each slide. For example, the vectorization unit weights the vectors by considering the frequency of use and evaluation of each slide. For instance, it might weight slides that are frequently used more highly so that they appear higher in search results. It might also weight slides that have received high ratings from users more highly so that they appear preferentially in search results. Furthermore, it might appropriately weight slides that are not frequently used but contain important information, making them easier to find when needed. By weighting the vectors while considering the frequency of use and evaluation of each slide, the accuracy of the search results is improved. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or without AI. For example, the vectorization unit can use an AI model that analyzes the frequency of use and evaluation of slides and weights the vectors based on that analysis.

[0037] The vectorization unit can save not only the content of the slides but also related audio and video as vectors. For example, the vectorization unit can save the audio of a presentation related to the slides as a vector so that it can be used when searching. It can also save a demo video related to the slides as a vector and display it in the search results. Furthermore, it can save an interview video related to the slides as a vector so that it can be referenced when searching. In this way, by saving related audio and video as vectors, a wider variety of information can be searched. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or without AI. For example, the vectorization unit can use an AI model that analyzes audio and video related to the slides and saves them as vectors.

[0038] The vectorization unit can add slide creation date and event information during the vectorization process. For example, the vectorization unit can add slide creation date and event information. For instance, it can save slide creation date as a vector, prioritizing the display of the most recent slide during searches. It can also save event information related to the slide as a vector, enabling searches for slides associated with relevant events. Furthermore, it can vectorize a combination of slide creation date and event information to search for slides related to a specific period or event. By adding slide creation date and event information, more appropriate slides can be found. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or without AI. For example, the vectorization unit can use an AI model that analyzes slide creation date and event information and saves it as a vector.

[0039] The reception desk can analyze the user's past request history and suggest the optimal input method. For example, the reception desk can analyze the user's past request history and suggest the optimal input method. For example, it can automatically display requests that the user has frequently entered in the past as candidates. It can also prioritize suggesting input methods that the user has used in the past (voice, text, etc.). Furthermore, it can predict and suggest requests that the user will use during specific time periods based on the user's past request history. In this way, by analyzing the user's past request history, the optimal input method can be suggested. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can use an AI model that analyzes the user's past request history and suggests the optimal input method based on that.

[0040] The reception unit can filter input content based on the user's current projects and areas of interest during the reception process. For example, the reception unit filters input content based on the user's current projects and areas of interest. For example, it prioritizes displaying slides related to the user's current ongoing projects. It also filters and displays relevant slides based on the user's areas of interest. Furthermore, it suggests appropriate slides according to the progress of the user's projects. In this way, by filtering input content based on the user's current projects and areas of interest, more appropriate slides can be provided. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can use an AI model that analyzes the user's current projects and areas of interest and filters input content based on that.

[0041] The reception unit can prioritize accepting highly relevant input content by considering the user's geographical location information during the reception process. For example, if the user is in a specific region, the reception unit will prioritize displaying slides related to that region. It will also filter and display relevant slides based on the user's current location. Furthermore, it will suggest appropriate slides based on the user's geographical location information. In this way, highly relevant slides can be provided by considering the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can use an AI model that analyzes the user's geographical location information and prioritizes accepting highly relevant input content based on that information.

[0042] The reception desk can analyze the user's social media activity and suggest relevant input content at the time of reception. For example, the reception desk can analyze the user's social media activity and suggest relevant input content. For example, it can suggest relevant slides based on information the user has shared on social media. It can also display slides related to topics of interest based on the user's social media activity. Furthermore, it can analyze the user's social media activity history and suggest appropriate slides. In this way, relevant slides can be provided by analyzing the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can use an AI model that analyzes the user's social media activity and suggests relevant input content based on that.

[0043] The search unit can improve search accuracy by considering the relationships between slides during a search. For example, the search unit improves search accuracy by considering the relationships between slides. For example, it prioritizes displaying relevant slides based on link information between slides. It also analyzes the relationships between slides and displays highly relevant slides in the search results. Furthermore, it improves the accuracy of the search results by considering the relationships between slides. As a result, the accuracy of the search results is improved by considering the relationships between slides. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can use an AI model that analyzes the relationships between slides and improves search accuracy based on that.

[0044] The search unit can perform searches while considering the attribute information of the slide creator. For example, the search unit can perform searches while considering the attribute information of the slide creator. For example, it can prioritize displaying relevant slides based on the slide creator's field of expertise. It can also search for appropriate slides while considering the slide creator's job title and department information. Furthermore, it can display relevant slides in the search results based on the slide creator's past achievements. In this way, by considering the attribute information of the slide creator, it is possible to find more appropriate slides. Some or all of the above processing in the search unit may be performed using AI, for example, or not using AI. For example, the search unit can use an AI model that analyzes the attribute information of the slide creator and performs searches based on that.

[0045] The search unit can perform searches while considering the geographical distribution of slides. For example, the search unit can perform searches while considering the geographical distribution of slides. For example, it can prioritize displaying slides related to a specific region. It can also display relevant slides in the search results based on the geographical distribution of slides. Furthermore, it can improve the accuracy of search results by considering the geographical distribution. In this way, by considering the geographical distribution of slides, it is possible to find more appropriate slides. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can use an AI model that analyzes the geographical distribution of slides and performs searches based on that.

[0046] The search unit can improve the accuracy of its search by referring to related literature in the slides during the search process. For example, the search unit improves the accuracy of its search by referring to related literature in the slides. For example, it prioritizes displaying highly relevant slides based on the literature related to the slides. It also improves the accuracy of the search results by referring to related literature. Furthermore, it searches for appropriate slides while considering the related literature in the slides. In this way, the accuracy of the search results is improved by referring to the related literature in the slides. Some or all of the above processing in the search unit may be performed using AI, for example, or not using AI. For example, the search unit can use an AI model that analyzes the related literature in the slides and improves the accuracy of the search based on that analysis.

[0047] The generation unit can adjust the level of detail of the generated slides based on their intended use. For example, the generation unit adjusts the level of detail based on the intended use of the slides. For example, for presentation slides, it provides a visually appealing design. For internal report slides, it provides a design that includes detailed information. Furthermore, for training slides, it provides a design that is easy to understand. By adjusting the level of detail based on the intended use of the slides, more appropriate slides can be provided. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can use an AI model that analyzes the intended use of the slides and adjusts the level of detail based on that.

[0048] The generation unit can apply different generation algorithms depending on the slide category during generation. For example, for marketing slides, it can apply an algorithm that generates a visually appealing design. For technical report slides, it can apply an algorithm that generates a design including detailed data and graphs. Furthermore, for training slides, it can apply an algorithm that generates a design including clear explanations and diagrams. By applying different generation algorithms depending on the slide category, more appropriate slides can be provided. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can use an AI model that analyzes the slide category and applies different generation algorithms based on that.

[0049] The generation unit can determine the generation priority based on the slide submission deadlines during generation. For example, the generation unit can prioritize the generation of slides based on their submission deadlines. For instance, it might prioritize generating slides with approaching deadlines and providing them quickly. It might also postpone generating slides with later submission deadlines, prioritizing other important slides. Furthermore, it can adjust the generation schedule according to the submission deadlines to create slides efficiently. This allows for efficient slide creation by determining the generation priority based on the slide submission deadlines. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or not. For example, the generation unit could use an AI model that analyzes the slide submission deadlines and determines the generation priority based on them.

[0050] The generation unit can adjust the generation order based on the relevance of the slides during generation. For example, the generation unit adjusts the generation order based on the relevance of the slides. For example, it places highly relevant slides first to make the overall flow smoother, and places less relevant slides later to prioritize important information. Furthermore, it generates slides in the optimal order, taking into account the relevance of the slides, to provide an easy-to-understand presentation. In this way, an easy-to-understand presentation can be provided by adjusting the generation order based on the relevance of the slides. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can use an AI model that analyzes the relevance of the slides and adjusts the generation order based on that.

[0051] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0052] The search function can analyze a user's past search history and prioritize displaying highly relevant slides. For example, it can display slides based on keywords the user has frequently searched for in the past. It can also prioritize displaying slides that the user has previously rated highly. Furthermore, it analyzes the user's past search patterns and suggests highly relevant slides. By considering the user's past search history, it can quickly provide more appropriate slides.

[0053] The reception desk can analyze a user's past input history and suggest the most suitable input method. For example, it prioritizes suggesting input methods that the user has frequently used in the past (such as voice or text). It also automatically displays relevant input suggestions based on the user's past input. Furthermore, it analyzes the user's past input patterns and suggests efficient input methods. In this way, by considering the user's past input history, it can provide a more efficient input method.

[0054] The search function can filter search results based on the user's current projects and areas of interest. For example, it prioritizes displaying slides related to the user's current project. It also filters and displays relevant slides based on the user's areas of interest. Furthermore, it suggests appropriate slides according to the user's project progress. By filtering search results based on the user's current projects and areas of interest, it can provide more relevant slides.

[0055] The reception desk can prioritize accepting input content that is highly relevant to the user, taking into account the user's geographical location. For example, if the user is in a specific region, slides related to that region will be displayed preferentially. Furthermore, relevant slides will be filtered and displayed based on the user's current location. In addition, appropriate slides will be suggested based on the user's geographical location. This allows the system to provide highly relevant slides by considering the user's geographical location.

[0056] The search function can improve search accuracy by referencing related literature in the slides during the search process. For example, it prioritizes displaying highly relevant slides based on the literature related to the slides. It also improves the accuracy of search results by referencing related literature. Furthermore, it searches for appropriate slides while considering the related literature in the slides. In this way, the accuracy of search results is improved by referencing related literature in the slides.

[0057] The following briefly describes the processing flow for example form 1.

[0058] Step 1: The vectorization unit converts past company assets into a vector database. Specifically, it saves information such as slide content, layout, and design as vectors. For example, slide content is saved as text data, and layout information is saved as coordinate data. Design information can also be saved as attribute data such as color and font size. Furthermore, natural language processing technology is used to analyze the slide content, extract important keywords, and vectorize them. Step 2: The reception desk inputs the user's request. For example, the user can input a specific request such as "I need presentation slides for a new product." The reception desk provides an interface that accepts text input and voice input. Step 3: The search unit searches the vector database for relevant slides based on the information entered by the reception unit. For example, it can search for slides related to a specific theme or keyword. The search unit uses keyword matching technology and algorithms that evaluate content similarity to find relevant slides. Step 4: The generation unit combines the slides found by the search unit to generate new slides. For example, it can cut out appropriate parts from past slides and paste them into new slides. The generation unit automatically adjusts the slide layout to create a consistent design. It can also generate new slides using templates. Based on the user's request, it selects an appropriate template and generates slides according to that template.

[0059] (Example of form 2) The slide generation system according to an embodiment of the present invention is a system that creates high-quality slides faster and cheaper by patching together existing slides like a crazy quilt. This slide generation system vectorizes past internal assets (such as slides) using a multimodal LLM to make them searchable. Next, when the user inputs the content of the slides they need, the system searches for relevant slides from the vector database and combines them like a crazy quilt to generate new slides. This mechanism makes it possible to generate slides in a clear and easy-to-understand format rooted in the company culture. For example, past internal assets are vectorized using a multimodal LLM to make them searchable. At this time, information such as the content, layout, and design of the slides is saved as vectors to make them searchable. For example, slides related to a specific theme or keyword can be easily searched. Next, the user inputs the content of the slides they need. For example, they input a specific request such as "I need slides for a new product presentation." This information is input into the system. Based on the input information, the system searches for relevant slides from the vector database. For example, it searches for past slides related to a new product presentation and selects appropriate slides from among them. The selected slides are combined like a crazy quilt to generate new slides. For example, by cutting out appropriate parts from past slides and pasting them into new slides, slides tailored to user requirements can be created. This mechanism allows for the creation of high-quality slides faster and at a lower cost by leveraging valuable past assets. Furthermore, because slides can be generated in a clear and easy-to-understand format rooted in the company culture, user satisfaction also improves. In short, the slide generation system can create high-quality slides faster and at a lower cost by utilizing past company assets.

[0060] The slide generation system according to this embodiment comprises a vectorization unit, a reception unit, a search unit, and a generation unit. The vectorization unit converts past company assets into a vector database. The vectorization unit saves information such as slide content, layout, and design as vectors. For example, the vectorization unit saves slide content as text data and layout information as coordinate data. The vectorization unit can also save design information as attribute data such as color and font size. For example, the vectorization unit analyzes slide content using natural language processing technology, extracts important keywords, and vectorizes them. The reception unit inputs user requests. For example, the reception unit allows users to input specific requests such as "I need slides for a new product presentation." For example, the reception unit provides an interface that accepts text input and voice input. The search unit searches the vector database for relevant slides based on the information entered by the reception unit. The search unit can search for slides related to specific themes or keywords. For example, the search unit searches the vector database for slides using keyword matching technology. Furthermore, the search unit can also search for related slides using an algorithm that evaluates the similarity of content. The generation unit generates new slides by combining the slides found by the search unit. The generation unit can, for example, cut out appropriate parts from past slides and paste them into new slides. For example, the generation unit can automatically adjust the slide layout to create a consistent design. The generation unit can also generate new slides using templates. For example, the generation unit can select an appropriate template based on the user's request and generate slides according to that template. As a result, the slide generation system according to this embodiment can utilize past in-house assets and create high-quality slides faster and at a lower cost.

[0061] The vectorization unit can save slide content, layout, and design information as vectors. For example, the vectorization unit can save slide content as text data. For example, the vectorization unit can analyze slide content using natural language processing technology, extract important keywords, and vectorize them. The vectorization unit can also save slide layout information as coordinate data. For example, the vectorization unit can save the position information of each element of the slide as coordinate data so that it can be reconstructed later. The vectorization unit can also save slide design information as attribute data such as color and font size. For example, the vectorization unit can save design information such as slide background color, font size, and font type as vectors. By saving slide content, layout, and design information as vectors, searchability is improved. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or without AI. For example, the vectorization unit can use an AI model that analyzes slide content using natural language processing technology, extracts important keywords, and vectorizes them.

[0062] The search unit can search for slides related to specific themes or keywords. For example, the search unit can search for slides in the vector database using keyword matching technology. The search unit can also search for related slides using algorithms that evaluate content similarity. For example, the search unit can evaluate the similarity of slide content using cosine similarity. Cosine similarity calculates the angle between two vectors in a vector space model; the smaller the angle, the higher the similarity. The search unit can also evaluate the similarity of slide content using the Jaccard coefficient. The Jaccard coefficient is the value obtained by dividing the size of the intersection of two sets by the size of the whole, indicating the degree of overlap between the sets. Furthermore, the search unit can evaluate the importance of slide content using TF-IDF. TF-IDF is an index that evaluates the importance of words in a document, and it is used to evaluate the importance of slide content. This allows for a quick response to user requests by searching for slides related to specific themes or keywords. Some or all of the processing described above in the search unit may be performed using AI, for example, or without AI. For example, the search unit can use an AI model that searches slides in a vector database using keyword matching technology.

[0063] The generation unit can cut out appropriate parts from past slides and paste them into new slides. For example, the generation unit can cut out appropriate parts from past slides and paste them into new slides. For example, the generation unit can automatically adjust the slide layout to create a consistent design. The generation unit can also generate new slides using templates. For example, the generation unit can select an appropriate template based on user requests and generate slides according to that template. Furthermore, the generation unit can automatically summarize the content of slides, extract important information, and reflect it in new slides. For example, the generation unit can summarize the content of slides using natural language processing technology, extract important keywords and phrases, and reflect them in new slides. This allows for efficient slide creation by cutting out appropriate parts from past slides and pasting them into new slides. Some or all of the above processes in the generation unit may be performed using AI, for example, or not. For example, the generation unit can use an AI model that automatically summarizes the content of slides, extracts important information, and reflects it in new slides.

[0064] The reception desk allows users to input specific requests, such as needing presentation slides for a new product. For example, the reception desk can provide an interface that accepts text and voice input. The reception desk can also analyze the user's input and extract information to generate appropriate slides. For example, the reception desk can use natural language processing to analyze the user's request and extract important keywords and phrases. Furthermore, the reception desk can suggest appropriate templates based on the user's request. For example, the reception desk can suggest templates suitable for the presentation's purpose and target audience based on the user's request. This allows the system to generate appropriate slides based on the user's input of specific requests. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk could use an AI model to analyze the user's request and extract information to generate appropriate slides.

[0065] The generation unit can create slides that meet the user's requirements. For example, the generation unit can select an appropriate template based on the user's requirements and generate slides according to that template. For example, the generation unit can select a template that is suitable for the purpose and target audience of the presentation based on the user's requirements. The generation unit can also automatically summarize the content of the slides, extract important information, and reflect it in the new slides. For example, the generation unit can use natural language processing technology to summarize the content of the slides, extract important keywords and phrases, and reflect them in the new slides. Furthermore, the generation unit can automatically adjust the layout of the slides to generate a consistent design. For example, the generation unit can save the positional information of each element of the slides as coordinate data so that it can be reconstructed later. This improves user satisfaction by creating slides that meet the user's requirements. Some or all of the above processes in the generation unit may be performed using AI, for example, or not. For example, the generation unit can use an AI model that automatically summarizes the content of the slides, extracts important information, and reflects it in the new slides.

[0066] The vectorization unit can estimate the user's emotions and determine vectorization priorities based on the estimated emotions. For example, if the user is stressed, the vectorization unit prioritizes vectorizing important slides to enable quick searching. If the user is relaxed, the unit vectorizes all slides to enable detailed searching. Furthermore, if the user is in a hurry, the vectorization unit prioritizes vectorizing frequently used slides to enable efficient searching. This enables efficient vectorization by determining vectorization priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the vectorization unit may be performed using AI or not. For example, the vectorization unit can use an AI model that estimates the user's emotions and determines vectorization priorities based on the estimated emotions.

[0067] The vectorization unit can save not only the content of the slides, but also the intentions and objectives of the slide creator as vectors. For example, if the slide creator wants to emphasize the features of a new product, that intention is saved as a vector. Also, if the slide creator has created a presentation aimed at a specific market segment, that objective is saved as a vector. Furthermore, if the slide creator has created slides for competitive analysis, that intention is saved as a vector. By saving the slide creator's intentions and objectives as vectors, it becomes possible to search for more appropriate slides. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or not. For example, the vectorization unit can use an AI model that analyzes the intentions and objectives of the slide creator and saves them as vectors.

[0068] The vectorization unit can weight the vectors during vectorization, taking into account the frequency of use and evaluation of each slide. For example, the vectorization unit weights the vectors by considering the frequency of use and evaluation of each slide. For instance, it might weight slides that are frequently used more highly so that they appear higher in search results. It might also weight slides that have received high ratings from users more highly so that they appear preferentially in search results. Furthermore, it might appropriately weight slides that are not frequently used but contain important information, making them easier to find when needed. By weighting the vectors while considering the frequency of use and evaluation of each slide, the accuracy of the search results is improved. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or without AI. For example, the vectorization unit can use an AI model that analyzes the frequency of use and evaluation of slides and weights the vectors based on that analysis.

[0069] The vectorization unit can estimate the user's emotions and adjust the level of detail in the vectorization based on the estimated emotions. For example, if the user is stressed, simplified vectorization is performed to enable quick searches. If the user is relaxed, detailed vectorization is performed to enable deeper searches. Furthermore, if the user is in a hurry, vectorization is performed to focus on important information to achieve efficient searches. In this way, efficient vectorization is possible by adjusting the level of detail in the vectorization based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or not using AI. For example, the vectorization unit can use an AI model that estimates the user's emotions and adjusts the level of detail in the vectorization based on the estimated emotions.

[0070] The vectorization unit can save not only the content of the slides but also related audio and video as vectors. For example, the vectorization unit can save the audio of a presentation related to the slides as a vector so that it can be used when searching. It can also save a demo video related to the slides as a vector and display it in the search results. Furthermore, it can save an interview video related to the slides as a vector so that it can be referenced when searching. In this way, by saving related audio and video as vectors, a wider variety of information can be searched. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or without AI. For example, the vectorization unit can use an AI model that analyzes audio and video related to the slides and saves them as vectors.

[0071] The vectorization unit can add slide creation date and event information during the vectorization process. For example, the vectorization unit can add slide creation date and event information. For instance, it can save slide creation date as a vector, prioritizing the display of the most recent slide during searches. It can also save event information related to the slide as a vector, enabling searches for slides associated with relevant events. Furthermore, it can vectorize a combination of slide creation date and event information to search for slides related to a specific period or event. By adding slide creation date and event information, more appropriate slides can be found. Some or all of the above processing in the vectorization unit may be performed using AI, for example, or without AI. For example, the vectorization unit can use an AI model that analyzes slide creation date and event information and saves it as a vector.

[0072] The reception desk can estimate the user's emotions and adjust the reception interface based on those emotions. For example, if the user is stressed, it can provide a simple and intuitive interface and minimize the input steps. If the user is relaxed, it can provide detailed input options and suggest a customizable interface. Furthermore, if the user is in a hurry, it can prioritize voice input to allow for quick information entry. This improves user convenience by adjusting the reception interface based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can use an AI model that estimates the user's emotions and adjusts the interface based on those emotions.

[0073] The reception desk can analyze the user's past request history and suggest the optimal input method. For example, the reception desk can analyze the user's past request history and suggest the optimal input method. For example, it can automatically display requests that the user has frequently entered in the past as candidates. It can also prioritize suggesting input methods that the user has used in the past (voice, text, etc.). Furthermore, it can predict and suggest requests that the user will use during specific time periods based on the user's past request history. In this way, by analyzing the user's past request history, the optimal input method can be suggested. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can use an AI model that analyzes the user's past request history and suggests the optimal input method based on that.

[0074] The reception unit can filter input content based on the user's current projects and areas of interest during the reception process. For example, the reception unit filters input content based on the user's current projects and areas of interest. For example, it prioritizes displaying slides related to the user's current ongoing projects. It also filters and displays relevant slides based on the user's areas of interest. Furthermore, it suggests appropriate slides according to the progress of the user's projects. In this way, by filtering input content based on the user's current projects and areas of interest, more appropriate slides can be provided. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can use an AI model that analyzes the user's current projects and areas of interest and filters input content based on that.

[0075] The reception desk can estimate the user's emotions and provide input guidance at the reception desk based on the estimated emotions. For example, if the user is stressed, it provides a concise and easy-to-understand input guide. If the user is relaxed, it provides a detailed input guide and suggests a customizable input method. Furthermore, if the user is in a hurry, it prioritizes voice input guidance to allow for quick information entry. This improves user convenience by providing input guidance at the reception desk based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can use an AI model that estimates the user's emotions and provides input guidance based on the estimated emotions.

[0076] The reception unit can prioritize accepting highly relevant input content by considering the user's geographical location information during the reception process. For example, if the user is in a specific region, the reception unit will prioritize displaying slides related to that region. It will also filter and display relevant slides based on the user's current location. Furthermore, it will suggest appropriate slides based on the user's geographical location information. In this way, highly relevant slides can be provided by considering the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can use an AI model that analyzes the user's geographical location information and prioritizes accepting highly relevant input content based on that information.

[0077] The reception desk can analyze the user's social media activity and suggest relevant input content at the time of reception. For example, the reception desk can analyze the user's social media activity and suggest relevant input content. For example, it can suggest relevant slides based on information the user has shared on social media. It can also display slides related to topics of interest based on the user's social media activity. Furthermore, it can analyze the user's social media activity history and suggest appropriate slides. In this way, relevant slides can be provided by analyzing the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can use an AI model that analyzes the user's social media activity and suggests relevant input content based on that.

[0078] The search unit can estimate the user's emotions and adjust how search results are displayed based on those emotions. For example, if the user is stressed, it displays simple and highly visible search results. If the user is relaxed, it displays search results containing detailed information. Furthermore, if the user is in a hurry, it displays concise search results. By adjusting how search results are displayed based on the user's emotions, user convenience is improved. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can use an AI model that estimates the user's emotions and adjusts how search results are displayed based on those estimated emotions.

[0079] The search unit can improve search accuracy by considering the relationships between slides during a search. For example, the search unit improves search accuracy by considering the relationships between slides. For example, it prioritizes displaying relevant slides based on link information between slides. It also analyzes the relationships between slides and displays highly relevant slides in the search results. Furthermore, it improves the accuracy of the search results by considering the relationships between slides. As a result, the accuracy of the search results is improved by considering the relationships between slides. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can use an AI model that analyzes the relationships between slides and improves search accuracy based on that.

[0080] The search unit can perform searches while considering the attribute information of the slide creator. For example, the search unit can perform searches while considering the attribute information of the slide creator. For example, it can prioritize displaying relevant slides based on the slide creator's field of expertise. It can also search for appropriate slides while considering the slide creator's job title and department information. Furthermore, it can display relevant slides in the search results based on the slide creator's past achievements. In this way, by considering the attribute information of the slide creator, it is possible to find more appropriate slides. Some or all of the above processing in the search unit may be performed using AI, for example, or not using AI. For example, the search unit can use an AI model that analyzes the attribute information of the slide creator and performs searches based on that.

[0081] The search unit can estimate the user's emotions and prioritize search results based on those emotions. For example, if the user is stressed, important slides are displayed preferentially. If the user is relaxed, slides containing detailed information are displayed preferentially. Furthermore, if the user is in a hurry, slides that get straight to the point are displayed preferentially. This improves user convenience by prioritizing search results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the search unit may be performed using AI, for example, or not using AI. For example, the search unit can use an AI model that estimates the user's emotions and prioritizes search results based on those emotions.

[0082] The search unit can perform searches while considering the geographical distribution of slides. For example, the search unit can perform searches while considering the geographical distribution of slides. For example, it can prioritize displaying slides related to a specific region. It can also display relevant slides in the search results based on the geographical distribution of slides. Furthermore, it can improve the accuracy of search results by considering the geographical distribution. In this way, by considering the geographical distribution of slides, it is possible to find more appropriate slides. Some or all of the above processing in the search unit may be performed using AI, for example, or without AI. For example, the search unit can use an AI model that analyzes the geographical distribution of slides and performs searches based on that.

[0083] The search unit can improve the accuracy of its search by referring to related literature in the slides during the search process. For example, the search unit improves the accuracy of its search by referring to related literature in the slides. For example, it prioritizes displaying highly relevant slides based on the literature related to the slides. It also improves the accuracy of the search results by referring to related literature. Furthermore, it searches for appropriate slides while considering the related literature in the slides. In this way, the accuracy of the search results is improved by referring to the related literature in the slides. Some or all of the above processing in the search unit may be performed using AI, for example, or not using AI. For example, the search unit can use an AI model that analyzes the related literature in the slides and improves the accuracy of the search based on that analysis.

[0084] The generation unit can estimate the user's emotions and adjust the design of the generated slides based on the estimated emotions. For example, if the user is stressed, it provides a simple and highly visible design. If the user is relaxed, it provides a design that includes detailed information. Furthermore, if the user is in a hurry, it provides a design that gets straight to the point. By adjusting the slide design based on the user's emotions, user satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can use an AI model that estimates the user's emotions and adjusts the slide design based on the estimated emotions.

[0085] The generation unit can adjust the level of detail of the generated slides based on their intended use. For example, the generation unit adjusts the level of detail based on the intended use of the slides. For example, for presentation slides, it provides a visually appealing design. For internal report slides, it provides a design that includes detailed information. Furthermore, for training slides, it provides a design that is easy to understand. By adjusting the level of detail based on the intended use of the slides, more appropriate slides can be provided. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can use an AI model that analyzes the intended use of the slides and adjusts the level of detail based on that.

[0086] The generation unit can apply different generation algorithms depending on the slide category during generation. For example, for marketing slides, it can apply an algorithm that generates a visually appealing design. For technical report slides, it can apply an algorithm that generates a design including detailed data and graphs. Furthermore, for training slides, it can apply an algorithm that generates a design including clear explanations and diagrams. By applying different generation algorithms depending on the slide category, more appropriate slides can be provided. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can use an AI model that analyzes the slide category and applies different generation algorithms based on that.

[0087] The generation unit can estimate the user's emotions and adjust the order of the generated slides based on the estimated emotions. For example, if the user is stressed, important information is placed first to allow for quick understanding. If the user is relaxed, detailed information is placed later, emphasizing the overall flow. Furthermore, if the user is in a hurry, concise information is placed first to convey information efficiently. By adjusting the order of slides based on the user's emotions, user satisfaction is improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can use an AI model that estimates the user's emotions and adjusts the order of slides based on the estimated emotions.

[0088] The generation unit can determine the generation priority based on the slide submission deadlines during generation. For example, the generation unit can prioritize the generation of slides based on their submission deadlines. For instance, it might prioritize generating slides with approaching deadlines and providing them quickly. It might also postpone generating slides with later submission deadlines, prioritizing other important slides. Furthermore, it can adjust the generation schedule according to the submission deadlines to create slides efficiently. This allows for efficient slide creation by determining the generation priority based on the slide submission deadlines. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or not. For example, the generation unit could use an AI model that analyzes the slide submission deadlines and determines the generation priority based on them.

[0089] The generation unit can adjust the generation order based on the relevance of the slides during generation. For example, the generation unit adjusts the generation order based on the relevance of the slides. For example, it places highly relevant slides first to make the overall flow smoother, and places less relevant slides later to prioritize important information. Furthermore, it generates slides in the optimal order, taking into account the relevance of the slides, to provide an easy-to-understand presentation. In this way, an easy-to-understand presentation can be provided by adjusting the generation order based on the relevance of the slides. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can use an AI model that analyzes the relevance of the slides and adjusts the generation order based on that. === Hard Collateral 1-1 === Each of the multiple elements described above, including the vectorization unit, reception unit, search unit, and generation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the vectorization unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The reception unit is implemented by the reception device 38 of the smart device 14 or the communication I / F 26 of the data processing device 12. The search unit is implemented by the specific processing unit 290 of the data processing device 12. The generation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements described above, including the vectorization unit, reception unit, search unit, and generation unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the vectorization unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The reception unit is implemented by the microphone 238 of the smart glasses 214 or the communication I / F 26 of the data processing unit 12. The search unit is implemented by the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. === Hard Collateral 1-3 === Each of the multiple elements described above, including the vectorization unit, reception unit, search unit, and generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the vectorization unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The reception unit is implemented by the microphone 238 of the headset terminal 314 or the communication I / F 26 of the data processing unit 12. The search unit is implemented by the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. === Hard Collateral 1-4 === Each of the multiple elements described above, including the vectorization unit, reception unit, search unit, and generation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the vectorization unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The reception unit is implemented by the microphone 238 of the robot 414 or the communication I / F 26 of the data processing unit 12. The search unit is implemented by the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12.

[0090] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0091] The generation unit can estimate the user's emotions and adjust the slide's color scheme based on those emotions. For example, if the user is stressed, it can use calming colors to reduce visual strain. Conversely, if the user is relaxed, it can use brighter colors to make the presentation more engaging. Furthermore, if the user is in a hurry, it can use simple, highly visible colors to quickly convey information. By adjusting the slide's color scheme based on the user's emotions, it is possible to improve both visual comfort and the efficiency of information transmission.

[0092] The search function can analyze a user's past search history and prioritize displaying highly relevant slides. For example, it can display slides based on keywords the user has frequently searched for in the past. It can also prioritize displaying slides that the user has previously rated highly. Furthermore, it analyzes the user's past search patterns and suggests highly relevant slides. By considering the user's past search history, it can quickly provide more appropriate slides.

[0093] The generation unit can estimate the user's emotions and adjust the slide animation effects based on those emotions. For example, if the user is stressed, simple and understated animations can be used to reduce visual strain. Conversely, if the user is relaxed, dynamic animations can be used to make the presentation more engaging. Furthermore, if the user is in a hurry, animations can be minimized to quickly convey the information. In this way, adjusting the slide animation effects based on the user's emotions can improve both visual comfort and the efficiency of information delivery.

[0094] The reception desk can analyze a user's past input history and suggest the most suitable input method. For example, it prioritizes suggesting input methods that the user has frequently used in the past (such as voice or text). It also automatically displays relevant input suggestions based on the user's past input. Furthermore, it analyzes the user's past input patterns and suggests efficient input methods. In this way, by considering the user's past input history, it can provide a more efficient input method.

[0095] The generation unit can estimate the user's emotions and adjust the font style of the slides based on those emotions. For example, if the user is stressed, it can use an easy-to-read font to reduce visual strain. If the user is relaxed, it can use a more aesthetically pleasing font to make the presentation more engaging. Furthermore, if the user is in a hurry, it can use a simple, highly legible font to quickly convey information. In this way, adjusting the font style of the slides based on the user's emotions can improve both visual comfort and the efficiency of information transmission.

[0096] The search function can filter search results based on the user's current projects and areas of interest. For example, it prioritizes displaying slides related to the user's current project. It also filters and displays relevant slides based on the user's areas of interest. Furthermore, it suggests appropriate slides according to the user's project progress. By filtering search results based on the user's current projects and areas of interest, it can provide more relevant slides.

[0097] The generation unit can estimate the user's emotions and adjust the slide layout based on those emotions. For example, if the user is stressed, a simple and organized layout can be used to reduce visual strain. Conversely, if the user is relaxed, a complex layout can be used to make the presentation more engaging. Furthermore, if the user is in a hurry, a layout that emphasizes key points can be used to quickly convey information. In this way, adjusting the slide layout based on the user's emotions can improve both visual comfort and the efficiency of information delivery.

[0098] The reception desk can prioritize accepting input content that is highly relevant to the user, taking into account the user's geographical location. For example, if the user is in a specific region, slides related to that region will be displayed preferentially. Furthermore, relevant slides will be filtered and displayed based on the user's current location. In addition, appropriate slides will be suggested based on the user's geographical location. This allows the system to provide highly relevant slides by considering the user's geographical location.

[0099] The generation unit can estimate the user's emotions and adjust the graphic elements of the slides based on those emotions. For example, if the user is stressed, simple, highly visible graphics can be used to reduce visual strain. If the user is relaxed, detailed graphics can be used to make the presentation more engaging. Furthermore, if the user is in a hurry, graphics that highlight key points can be used to quickly convey information. In this way, adjusting the graphic elements of the slides based on the user's emotions can improve both visual comfort and the efficiency of information transmission.

[0100] The search function can improve search accuracy by referencing related literature in the slides during the search process. For example, it prioritizes displaying highly relevant slides based on the literature related to the slides. It also improves the accuracy of search results by referencing related literature. Furthermore, it searches for appropriate slides while considering the related literature in the slides. In this way, the accuracy of search results is improved by referencing related literature in the slides.

[0101] The following briefly describes the processing flow for example form 2.

[0102] Step 1: The vectorization unit converts past company assets into a vector database. Specifically, it saves information such as slide content, layout, and design as vectors. For example, slide content is saved as text data, and layout information is saved as coordinate data. Design information can also be saved as attribute data such as color and font size. Furthermore, natural language processing technology is used to analyze the slide content, extract important keywords, and vectorize them. Step 2: The reception desk inputs the user's request. For example, the user can input a specific request such as "I need presentation slides for a new product." The reception desk provides an interface that accepts text input and voice input. Step 3: The search unit searches the vector database for relevant slides based on the information entered by the reception unit. For example, it can search for slides related to a specific theme or keyword. The search unit uses keyword matching technology and algorithms that evaluate content similarity to find relevant slides. Step 4: The generation unit combines the slides found by the search unit to generate new slides. For example, it can cut out appropriate parts from past slides and paste them into new slides. The generation unit automatically adjusts the slide layout to create a consistent design. It can also generate new slides using templates. Based on the user's request, it selects an appropriate template and generates slides according to that template.

[0103] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0104] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0105] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0106] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0107] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0108] As shown in Figure 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.

[0109] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0110] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0111] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0113] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0114] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0115] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0116] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0117] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0119] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, 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 specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0121] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0122] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0123] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0124] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0126] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0127] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0129] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0130] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0131] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0132] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0133] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0134] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0135] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, 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 specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0137] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0138] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0139] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0140] As shown in Figure 7, the 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.

[0141] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0142] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0143] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0145] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0146] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0147] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0148] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0149] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0150] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0151] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0152] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0153] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, 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 specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0154] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0155] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0156] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0157] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0158] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0159] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0160] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0161] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0162] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0163] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0164] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0165] 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.

[0166] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0167] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0168] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0169] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0170] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0171] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0172] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0173] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0174] [Explanation of symbols]

[0175] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The vectorization department converts past company assets into a vector database, A reception area where user requests are entered, A search unit searches for relevant slides from a vector database based on the information entered by the reception unit, A generation unit that generates a new slide by combining the slides found by the search unit, Equipped with A system characterized by the following features.

2. The vectorization unit is Save the slide content, layout, and design information as a vector. The system according to feature 1.

3. The aforementioned search unit, Search for slides related to a specific theme or keyword. The system according to feature 1.

4. The generating unit is Cut out the appropriate parts from previous slides and paste them into new slides. The system according to feature 1.

5. The aforementioned reception unit is The user enters a specific request, such as needing presentation slides for a new product. The system according to feature 1.

6. The generating unit is Create slides that meet user requirements. The system according to feature 1.

7. The vectorization unit is The system estimates the user's emotions and determines the vectorization priority based on the estimated user emotions. The system according to feature 1.

8. The vectorization unit is Not only the content of the slides, but also the intentions and objectives of the slide creators are saved as vectors. The system according to feature 1.

Images