System

Abstract

To provide a system by which a user can adjust the intensity of expression according to his / her preference.SOLUTION: A system according to an embodiment comprises a setting part, a generation part, and a providing part. In the setting part, a user sets from soft to harsh expression level. The generation part generates an expression on the basis of a level set by the setting part. The providing part provides the expression generated by the generation part to a user.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Conventional techniques do not allow users to adjust the intensity of expressions according to their own preferences, and there is a risk that users may feel uncomfortable with extreme expressions.

[0005] The system according to the embodiment aims to enable a user to adjust the strength of the expression according to his / her preference. [Means for solving the problem]

[0006] The system according to the embodiment includes a setting unit, a generating unit, and a providing unit. The setting unit allows a user to set a level from sweet to spicy. The generating unit generates an expression based on the level set by the setting unit. The providing unit provides the expression generated by the generating unit to the user. Effect of the Invention

[0007] The system according to the embodiment may allow the user to adjust the intensity of the expression according to his / her preference. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

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

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

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

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

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

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

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

[0028] (Example 1) The expression generation system according to the embodiment of the present invention is a system in which AI changes the expression of user-generated content such as comments on news and product reviews according to the level set by the user, from mild to harsh. In this system, the user sets the level from mild to harsh, and the AI ​​generates expressions based on the setting and provides them to the user. For example, the user can choose from three levels: mild, medium, and harsh. Next, the AI ​​generates expressions based on the user's setting. The AI ​​analyzes the contents of the input news and reviews and generates expressions according to the set level. For example, in the mild setting, gentle words and positive expressions are used frequently, and in the harsh setting, frank and harsh expressions are used. With this system, people who are not good at extreme words can enjoy content with peace of mind with mild expressions, and people who want to see the real opinions can enjoy real opinions with harsh expressions. For example, even for the same product review, in the mild setting, it is expressed as "This product is very easy to use and I am satisfied," and in the harsh setting, it is expressed as "This product is difficult to use and I am dissatisfied." In this way, by generating expressions according to the user's preferences, it is expected that the ways of enjoying news and reviews will expand and more people will use them. This allows the expression generation system to generate and provide expressions according to the user's preferences.

[0029] The expression generation system according to the embodiment includes a setting unit, a generation unit, and a provision unit. The setting unit allows a user to set a level from mild to spicy. The user can select a desired level of expression using an interface such as a slider or a drop-down menu. For example, the user can select from three levels: mild, medium, and spicy. The generation unit generates an expression based on the level set by the setting unit. The generation unit includes an analysis unit that analyzes input text using natural language processing technology and performs sentiment analysis. For example, the generation unit uses a lot of gentle words and positive expressions in the mild setting, and uses frank and harsh expressions in the spicy setting. The generation unit uses a generation AI to generate an expression based on the user's setting. The generation AI uses a text generation AI (for example, LLM) to analyze the contents of the input news and reviews, and generates an expression according to the set level. For example, the generation AI expresses "This product is very easy to use and I am satisfied" in the mild setting, and expresses "This product is difficult to use and I have many complaints" in the spicy setting. The provision unit provides the expression generated by the generation unit to the user. The providing unit displays the generated expression to the user through, for example, a web application or a mobile application, so that the expression generation system according to the embodiment can generate and provide an expression according to the user's preferences.

[0030] The setting unit allows the user to set the level of the taste, ranging from mild to spicy. The user can select the desired level of taste using an interface such as a slider or a drop-down menu. Specifically, the slider is designed to be intuitive, and the user can select from three levels, mild, medium, and spicy, by moving the slider left and right. In the case of a drop-down menu, the user can click on the menu to display the options and select the desired level. Furthermore, the setting unit also has a function to remember the user's past selection history and automatically suggest the optimal setting the next time the system is used. For example, if the user has frequently selected the mild setting in the past, the system can be set so that the mild setting is selected by default the next time the system is used. The setting unit also has a function to reflect the change in real time when the user changes the setting and to immediately notify the generation unit. This allows the user to immediately check the new taste every time the setting is changed. Furthermore, the setting unit also provides a user interface customization function, and the user can change the design and color scheme of the interface to suit his or her preferences. This allows the user to use the system more comfortably.

[0031] The generation unit generates an expression based on the level set by the setting unit. The generation unit includes an analysis unit that analyzes the input text using natural language processing technology and performs sentiment analysis. Specifically, the generation unit first tokenizes the input text and calculates a sentiment score for each token. Next, the generation unit evaluates the sentiment of the entire text based on the sentiment score and generates an expression according to the set level. The generation unit uses a generation AI to generate an expression based on the user's settings. The generation AI uses a text generation AI (e.g., LLM) to analyze the contents of the input news or review and generate an expression according to the set level. For example, the generation AI expresses "This product is very easy to use and I am satisfied" in the mild setting, and expresses "This product is difficult to use and I am dissatisfied" in the harsh setting. The generation AI has learned a large amount of text data in advance and can generate appropriate expressions according to various contexts and situations. Furthermore, the generation unit also has a function of checking whether the generated expression is grammatically correct and makes corrections as necessary. This allows the generation unit to generate and provide high-quality expressions based on the user's settings.

[0032] The providing unit provides the expression generated by the generating unit to the user. The providing unit displays the generated expression to the user through, for example, a web application or a mobile application. Specifically, the providing unit transmits the generated expression to the user's device in real time so that the user can immediately check it. In the case of a web application, the generated expression is displayed on the browser, and the user can check it on the spot. In the case of a mobile application, the generated expression is displayed in the app, and the user can receive a notification. Furthermore, the providing unit also has a function of saving the generated expression so that the user can recheck it later. For example, the user can register the generated expression as a favorite or save it as a history. In addition, the providing unit also provides a function of sharing the generated expression with other users, and the user can easily share the generated expression via SNS or email. In this way, the providing unit can quickly and effectively provide the generated expression to the user and improve the user's convenience. Furthermore, the providing unit contributes to improving the entire system by collecting feedback from the user and providing the feedback to the generating unit and the setting unit. For example, the user can leave an evaluation or comment on the generated expression, and the accuracy and usability of the system can be improved based on the feedback.

[0033] The generation unit may include an analysis unit that analyzes the input text using a natural language processing technique and performs sentiment analysis. The generation unit analyzes the input text using, for example, a natural language processing technique and performs sentiment analysis. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, the generation unit divides the text into words using morphological analysis, analyzes the structure of a sentence using grammatical analysis, and understands the meaning of the text using semantic analysis. Sentiment analysis is performed based on, for example, classification criteria of positive, negative, and neutral. The generation unit analyzes the input text using a generation AI and performs sentiment analysis. The generation AI analyzes the sentiment of the input text using a text generation AI (for example, LLM) and performs classification into positive, negative, and neutral. As a result, the generation unit can improve the analysis accuracy of the text by using the natural language processing technique.

[0034] The setting unit can select the level of expression desired by the user using at least one interface of a slider or a drop-down menu. The setting unit selects the level of expression desired by the user using, for example, a slider. The slider is displayed in the form of a horizontal slider, a vertical slider, or the like. For example, the horizontal slider allows the user to select the level of expression desired by moving the slider left and right. The vertical slider allows the user to select the level of expression desired by moving the slider up and down. The setting unit can also select the level of expression desired by the user using a drop-down menu. The drop-down menu is set to the number of options, the display order, and the like. For example, the drop-down menu displays three options, sweet, medium hot, and hot, and the user can select the level of expression desired. In this way, the setting unit enables the user to intuitively set the level of expression.

[0035] The generation unit can use gentle words or positive expressions in the sweet setting, and can use frank and harsh expressions in the harsh setting. For example, the generation unit uses gentle words and positive expressions in the sweet setting. The gentle words include positive adjectives and encouraging words. For example, expressions such as "great," "nice," and "great results" are used. The positive expressions include positive phrases and positive messages. For example, expressions such as "this product is very easy to use and I am satisfied," and "this service is very convenient" are used. The harsh setting uses frank and harsh expressions. The frank and harsh expressions include critical comments and direct criticism. For example, expressions such as "this product is difficult to use and I am dissatisfied," and "this service is disappointing" are used. The generation unit uses a generation AI to generate expressions based on the user's settings. The generation AI uses a text generation AI (e.g., LLM) to analyze the contents of the input news and reviews and generate expressions according to the set level. This allows the generation unit to generate appropriate expressions according to the user's settings.

[0036] The setting unit can analyze the user's past setting history and recommend an appropriate setting level. The setting unit, for example, analyzes the user's past setting history and recommends an optimal setting level. The past setting history includes the setting date and time, the setting content, etc. For example, the optimal setting level is recommended based on the level frequently selected by the user in the past. The level to be selected in a specific time period is predicted and recommended from the user's past setting history. The user's past setting history is analyzed and the most frequently used level is recommended. The setting unit uses a generation AI to analyze the user's past setting history and recommends an appropriate setting level. The generation AI uses a text generation AI (for example, LLM) to analyze the user's past setting history and recommend an optimal setting level. This allows the setting unit to recommend an optimal level based on the user's past setting history.

[0037] The setting unit can preferentially suggest highly relevant settings based on the geographical location information of the user at the time of setting. For example, the setting unit preferentially suggests highly relevant settings in consideration of the geographical location information of the user at the time of setting. The geographical location information is acquired by a method such as GPS data or an IP address. For example, when the user is in a specific area, a setting such as sweet or dry is suggested based on the culture and customs of the area. When the user is traveling, a setting that matches the culture of the travel destination is suggested. When the user is at home, an optimal setting is suggested based on the past setting history. The setting unit uses a generation AI to analyze the geographical location information of the user and propose a highly relevant setting. The generation AI uses a text generation AI (e.g., LLM) to analyze the geographical location information and propose an optimal setting. This allows the setting unit to propose an appropriate setting based on the geographical location information of the user.

[0038] The setting unit can analyze the user's social media activity at the time of setting and suggest relevant settings. For example, at the time of setting, the setting unit analyzes the user's social media activity and suggests relevant settings. The social media activity is analyzed based on data such as the content of the post and the number of likes. For example, if the user posts positively on social media, a mild setting is suggested. If the user posts negatively on social media, a harsh setting is suggested. From the user's social media activity, an optimal setting is suggested based on topics of interest. The setting unit uses a generation AI to analyze the user's social media activity and suggests relevant settings. The generation AI uses a text generation AI (e.g., LLM) to analyze social media activity and suggest optimal settings. This allows the setting unit to suggest appropriate settings based on the user's social media activity.

[0039] The generation unit can adjust the level of detail of the expression based on the importance of the text at the time of generation. For example, the generation unit adjusts the level of detail of the expression based on the importance of the text at the time of generation. The importance of the text is evaluated based on criteria such as the frequency of appearance of keywords and the importance of the context. For example, in the case of an important news article, a detailed expression is generated. In the case of a general product review, a concise expression is generated. In the case of a topic in which the user is particularly interested, a detailed expression is generated. The generation unit adjusts the level of detail of the expression based on the importance of the text using a generation AI. The generation AI uses a text generation AI (e.g., LLM) to analyze the importance of the text and generate an expression with an appropriate level of detail. This allows the generation unit to generate an expression with an appropriate level of detail according to the importance of the text.

[0040] The generation unit can apply different generation algorithms depending on the category of the text at the time of generation. For example, the generation unit applies different generation algorithms depending on the category of the text at the time of generation. The categories of text are classified based on criteria such as news, blogs, reviews, etc. For example, in the case of a news article, a generation algorithm dedicated to news is applied. In the case of a product review, a generation algorithm dedicated to reviews is applied. In the case of a social media post, a generation algorithm dedicated to social media is applied. The generation unit uses a generation AI to apply different generation algorithms depending on the category of the text. The generation AI uses a text generation AI (e.g., LLM) to analyze the category of the text and apply an appropriate generation algorithm. This allows the generation unit to apply an appropriate generation algorithm depending on the category of the text.

[0041] The generation unit can determine the priority of expressions based on the time of submission of the text at the time of generation. For example, the generation unit determines the priority of expressions based on the time of submission of the text at the time of generation. The submission time is evaluated based on criteria such as the submission date and time and the submission order. For example, for the latest news article, an expression is generated as a priority. For old product reviews, an expression is generated later. For information with high urgency, an expression is generated as a top priority. The generation unit uses a generation AI to determine the priority of expressions based on the time of submission of the text. The generation AI uses a text generation AI (e.g., LLM) to analyze the submission time and generate expressions with an appropriate priority. This allows the generation unit to generate expressions with an appropriate priority according to the time of submission of the text.

[0042] The generation unit can adjust the order of the expressions based on the relevance of the text at the time of generation. The generation unit, for example, adjusts the order of the expressions based on the relevance of the text at the time of generation. The relevance of the text is evaluated based on criteria such as common keywords, related topics, etc. For example, the order of the expressions is adjusted so that important information is displayed first. The order of the expressions is adjusted so that less relevant information is displayed later. The order of the expressions is adjusted so that highly relevant information is displayed preferentially based on the user's interest. The generation unit adjusts the order of the expressions based on the relevance of the text using a generation AI. The generation AI uses a text generation AI (e.g., LLM) to analyze the relevance of the text and generate expressions in an appropriate order. This allows the generation unit to generate expressions in an appropriate order according to the relevance of the text.

[0043] The providing unit can select an appropriate display method by referring to the user's past browsing history at the time of providing. For example, the providing unit selects the optimal display method by referring to the user's past browsing history at the time of providing. The browsing history includes the browsing date and time, the browsed pages, etc. For example, the optimal display method is selected based on the display method of the content that the user frequently browsed in the past. A display method suitable for a specific time period is selected from the user's past browsing history. The user's past browsing history is analyzed and the most frequently used display method is selected. The providing unit uses a generation AI to analyze the user's past browsing history and selects an appropriate display method. The generation AI uses a text generation AI (e.g., LLM) to analyze the browsing history and select the optimal display method. This allows the providing unit to select the optimal display method based on the user's past browsing history.

[0044] The providing unit can customize the display content based on the user's current field of interest at the time of providing. For example, the providing unit customizes the display content based on the user's current field of interest at the time of providing. The display content is customized based on criteria such as the type and order of information to be displayed. For example, the display content is customized based on topics in which the user is currently interested. Information related to the user's current field of interest is preferentially displayed. When the user's field of interest changes, the display content is customized in real time. The providing unit uses a generation AI to analyze the user's current field of interest and customize the display content. The generation AI uses a text generation AI (e.g., LLM) to analyze the field of interest and generate appropriate display content. This allows the providing unit to provide appropriate display content according to the user's current field of interest.

[0045] The providing unit can select the optimal display method in consideration of the geographical location information of the user at the time of providing. For example, the providing unit selects the optimal display method in consideration of the geographical location information of the user at the time of providing. The geographical location information is acquired by a method such as GPS data or an IP address. For example, when the user is in a specific area, the display method is selected based on the culture and customs of the area. When the user is traveling, the display method is selected according to the culture of the travel destination. When the user is at home, the optimal display method is selected based on the past browsing history. The providing unit uses a generation AI to analyze the geographical location information of the user and selects the optimal display method. The generation AI uses a text generation AI (e.g., LLM) to analyze the geographical location information and select an appropriate display method. This allows the providing unit to select an appropriate display method based on the geographical location information of the user.

[0046] The providing unit can customize the display content by analyzing the user's social media activity at the time of providing. For example, the providing unit customizes the display content by analyzing the user's social media activity at the time of providing. The social media activity is analyzed based on data such as the post content and the number of likes. For example, if the user posts positively on social media, the display unit preferentially provides sweet expressions. If the user posts negatively on social media, the display unit preferentially provides harsh expressions. The display content is customized based on the user's social media activity and topics of interest. The providing unit uses a generating AI to analyze the user's social media activity and customize the display content. The generating AI uses a text generating AI (e.g., LLM) to analyze the social media activity and generate appropriate display content. This allows the providing unit to provide appropriate display content based on the user's social media activity.

[0047] The analysis unit can optimize the analysis algorithm by referring to past analysis data during analysis. The analysis unit, for example, optimizes the analysis algorithm by referring to past analysis data during analysis. The past analysis data includes the analysis date and time, the analysis result, and the like. For example, an optimal analysis algorithm is selected based on the past analysis data. A specific pattern is extracted from the past analysis data, and the analysis algorithm is optimized. The past analysis data is analyzed to improve the accuracy of the analysis. The analysis unit uses a generation AI to analyze the past analysis data and optimize the analysis algorithm. The generation AI uses a text generation AI (for example, LLM) to analyze the past analysis data and select an optimal analysis algorithm. This allows the analysis unit to optimize the analysis algorithm based on the past analysis data.

[0048] The analysis unit can apply different analysis methods to each text category during analysis. For example, the analysis unit applies different analysis methods to each text category during analysis. Analysis methods include statistical analysis, machine learning, and the like. For example, in the case of a news article, an analysis method dedicated to news is applied. In the case of a product review, an analysis method dedicated to reviews is applied. In the case of a social media post, an analysis method dedicated to social media is applied. The analysis unit uses a generation AI to apply different analysis methods to each text category. The generation AI uses a text generation AI (e.g., LLM) to analyze the text category and apply an appropriate analysis method. This allows the analysis unit to apply an appropriate analysis method according to the text category.

[0049] The analysis unit can determine the analysis priority based on the time of submission of the text during analysis. For example, the analysis unit determines the analysis priority based on the time of submission of the text during analysis. The submission time is evaluated based on criteria such as the submission date and time and the submission order. For example, in the case of the latest news article, analysis is performed as a priority. In the case of an old product review, analysis is performed later. In the case of information with high urgency, analysis is performed as a top priority. The analysis unit uses a generation AI to determine the analysis priority based on the time of submission of the text. The generation AI uses a text generation AI (e.g., LLM) to analyze the submission time and perform analysis with appropriate priority. This allows the analysis unit to perform analysis with appropriate priority according to the time of submission of the text.

[0050] The analysis unit can improve the accuracy of the analysis by referring to the relevant market data of the text during analysis. The analysis unit, for example, improves the accuracy of the analysis by referring to the relevant market data of the text during analysis. The relevant market data is obtained by methods such as market reports, sales data, etc. For example, the accuracy of the analysis is improved based on the relevant market data. Specific trends are extracted from the market data and reflected in the analysis. The market data is analyzed to increase the reliability of the analysis results. The analysis unit uses the generation AI to analyze the relevant market data and improve the accuracy of the analysis. The generation AI uses a text generation AI (e.g., LLM) to analyze the market data and apply an appropriate analysis method. This allows the analysis unit to improve the accuracy of the analysis based on the relevant market data.

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

[0052] The setting unit can analyze the user's past behavior history and learn what expression level the user prefers. For example, if the user has chosen many mild expressions in the past, the setting unit can preferentially suggest a mild level the next time the user selects settings. In addition, if the user has a tendency to prefer spicy expressions during a specific time period, the setting unit can suggest a spicy level for that time period. Furthermore, if the user has consistently chosen medium-spicy expressions for a specific topic, the setting unit can suggest a medium-spicy level for content related to that topic. This allows the setting unit to provide more personalized settings based on the user's past behavior history.

[0053] The generation unit can customize the style of expression according to the user's preferences. For example, if the user prefers formal expressions, the generation unit can generate expressions using formal language and writing style. Conversely, if the user prefers casual expressions, the generation unit can generate expressions using casual language and writing style. In addition, if the user prefers humorous expressions, the generation unit can also generate humorous expressions. Furthermore, if the user has a specific cultural background, the generation unit can generate expressions suitable for that culture. In this way, the generation unit can provide a variety of expression styles according to the user's preferences.

[0054] The providing unit can optimize the display method according to the device and environment of the user. For example, when the user is using a smartphone, the providing unit can provide a mobile-friendly display method. When the user is using a personal computer, the providing unit can provide a display method for desktops. Also, when the user is in a dark place, the providing unit can display in dark mode. Furthermore, when the user is in a noisy environment, the providing unit can provide a visually emphasized display method. In this way, the providing unit can provide an optimal display method according to the device and environment of the user.

[0055] The generation unit can collect user feedback and improve the expression generation algorithm based on the feedback. For example, an interface is provided that allows the user to evaluate the generated expressions, and the evaluation data is collected. If the user provides a positive evaluation, the expression style can be reflected in future generation. Conversely, if the user provides a negative evaluation, the evaluation data can be used as data for improving the expression style. In addition, if the user provides specific feedback, the generation algorithm can be adjusted based on the feedback. This allows the generation unit to improve the accuracy and quality of expression generation based on the user feedback.

[0056] The providing unit can analyze the user's browsing history and preferentially display highly relevant content. For example, if the user has browsed a lot of content related to a specific topic in the past, new content related to the topic can be preferentially displayed. In addition, if the user has a tendency to prefer a specific type of content in a specific time period, content suitable for that time period can be displayed. Furthermore, if the user has a tendency to browse a specific type of content on a specific device, content suitable for that device can be displayed. This allows the providing unit to realize more personalized content display based on the user's browsing history.

[0057] The process flow of the first embodiment will be briefly described below.

[0058] Step 1: The setting section allows the user to set the level from mild to spicy. The user selects the desired expression level from three levels: mild, medium spicy, and spicy, using an interface such as a slider or a drop-down menu. Step 2: The generation unit generates expressions based on the level set by the setting unit. The generation unit includes an analysis unit that uses natural language processing technology to analyze the input text and perform sentiment analysis. Using the generation AI, the mild setting uses a lot of kind words and positive expressions, while the harsh setting uses frank and harsh expressions. For example, the mild setting would express "This product is very easy to use and I am very satisfied with it," while the harsh setting would express "This product is difficult to use and I am very dissatisfied with it." Step 3: The providing unit provides the representation generated by the generating unit to the user. The providing unit displays the generated representation to the user through a web application or a mobile application.

[0059] (Example 2) The expression generation system according to the embodiment of the present invention is a system in which AI changes the expression of user-generated content such as comments on news and product reviews according to the level set by the user, from mild to harsh. In this system, the user sets the level from mild to harsh, and the AI ​​generates expressions based on the setting and provides them to the user. For example, the user can choose from three levels: mild, medium, and harsh. Next, the AI ​​generates expressions based on the user's setting. The AI ​​analyzes the contents of the input news and reviews and generates expressions according to the set level. For example, in the mild setting, gentle words and positive expressions are used frequently, and in the harsh setting, frank and harsh expressions are used. With this system, people who are not good at extreme words can enjoy content with peace of mind with mild expressions, and people who want to see the real opinions can enjoy real opinions with harsh expressions. For example, even for the same product review, in the mild setting, it is expressed as "This product is very easy to use and I am satisfied," and in the harsh setting, it is expressed as "This product is difficult to use and I am dissatisfied." In this way, by generating expressions according to the user's preferences, it is expected that the ways of enjoying news and reviews will expand and more people will use them. This allows the expression generation system to generate and provide expressions according to the user's preferences.

[0060] The expression generation system according to the embodiment includes a setting unit, a generation unit, and a provision unit. The setting unit allows a user to set a level from mild to spicy. The user can select a desired level of expression using an interface such as a slider or a drop-down menu. For example, the user can select from three levels: mild, medium, and spicy. The generation unit generates an expression based on the level set by the setting unit. The generation unit includes an analysis unit that analyzes input text using natural language processing technology and performs sentiment analysis. For example, the generation unit uses a lot of gentle words and positive expressions in the mild setting, and uses frank and harsh expressions in the spicy setting. The generation unit uses a generation AI to generate an expression based on the user's setting. The generation AI uses a text generation AI (for example, LLM) to analyze the contents of the input news and reviews, and generates an expression according to the set level. For example, the generation AI expresses "This product is very easy to use and I am satisfied" in the mild setting, and expresses "This product is difficult to use and I have many complaints" in the spicy setting. The provision unit provides the expression generated by the generation unit to the user. The providing unit displays the generated expression to the user through, for example, a web application or a mobile application, so that the expression generation system according to the embodiment can generate and provide an expression according to the user's preferences.

[0061] The setting unit allows the user to set the level of the taste, ranging from mild to spicy. The user can select the desired level of taste using an interface such as a slider or a drop-down menu. Specifically, the slider is designed to be intuitive, and the user can select from three levels, mild, medium, and spicy, by moving the slider left and right. In the case of a drop-down menu, the user can click on the menu to display the options and select the desired level. Furthermore, the setting unit also has a function to remember the user's past selection history and automatically suggest the optimal setting the next time the system is used. For example, if the user has frequently selected the mild setting in the past, the system can be set so that the mild setting is selected by default the next time the system is used. The setting unit also has a function to reflect the change in real time when the user changes the setting and to immediately notify the generation unit. This allows the user to immediately check the new taste every time the setting is changed. Furthermore, the setting unit also provides a user interface customization function, and the user can change the design and color scheme of the interface to suit his or her preferences. This allows the user to use the system more comfortably.

[0062] The generation unit generates an expression based on the level set by the setting unit. The generation unit includes an analysis unit that analyzes the input text using natural language processing technology and performs sentiment analysis. Specifically, the generation unit first tokenizes the input text and calculates a sentiment score for each token. Next, the generation unit evaluates the sentiment of the entire text based on the sentiment score and generates an expression according to the set level. The generation unit uses a generation AI to generate an expression based on the user's settings. The generation AI uses a text generation AI (e.g., LLM) to analyze the contents of the input news or review and generate an expression according to the set level. For example, the generation AI expresses "This product is very easy to use and I am satisfied" in the mild setting, and expresses "This product is difficult to use and I am dissatisfied" in the harsh setting. The generation AI has learned a large amount of text data in advance and can generate appropriate expressions according to various contexts and situations. Furthermore, the generation unit also has a function of checking whether the generated expression is grammatically correct and makes corrections as necessary. This allows the generation unit to generate and provide high-quality expressions based on the user's settings.

[0063] The providing unit provides the expression generated by the generating unit to the user. The providing unit displays the generated expression to the user through, for example, a web application or a mobile application. Specifically, the providing unit transmits the generated expression to the user's device in real time so that the user can immediately check it. In the case of a web application, the generated expression is displayed on the browser, and the user can check it on the spot. In the case of a mobile application, the generated expression is displayed in the app, and the user can receive a notification. Furthermore, the providing unit also has a function of saving the generated expression so that the user can recheck it later. For example, the user can register the generated expression as a favorite or save it as a history. In addition, the providing unit also provides a function of sharing the generated expression with other users, and the user can easily share the generated expression via SNS or email. In this way, the providing unit can quickly and effectively provide the generated expression to the user and improve the user's convenience. Furthermore, the providing unit contributes to improving the entire system by collecting feedback from the user and providing the feedback to the generating unit and the setting unit. For example, the user can leave an evaluation or comment on the generated expression, and the accuracy and usability of the system can be improved based on the feedback.

[0064] The generation unit may include an analysis unit that analyzes the input text using a natural language processing technique and performs sentiment analysis. The generation unit analyzes the input text using, for example, a natural language processing technique and performs sentiment analysis. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, the generation unit divides the text into words using morphological analysis, analyzes the structure of a sentence using grammatical analysis, and understands the meaning of the text using semantic analysis. Sentiment analysis is performed based on, for example, classification criteria of positive, negative, and neutral. The generation unit analyzes the input text using a generation AI and performs sentiment analysis. The generation AI analyzes the sentiment of the input text using a text generation AI (for example, LLM) and performs classification into positive, negative, and neutral. As a result, the generation unit can improve the analysis accuracy of the text by using the natural language processing technique.

[0065] The setting unit can select the level of expression desired by the user using at least one interface of a slider or a drop-down menu. The setting unit selects the level of expression desired by the user using, for example, a slider. The slider is displayed in the form of a horizontal slider, a vertical slider, or the like. For example, the horizontal slider allows the user to select the level of expression desired by moving the slider left and right. The vertical slider allows the user to select the level of expression desired by moving the slider up and down. The setting unit can also select the level of expression desired by the user using a drop-down menu. The drop-down menu is set to the number of options, the display order, and the like. For example, the drop-down menu displays three options, sweet, medium hot, and hot, and the user can select the level of expression desired. In this way, the setting unit enables the user to intuitively set the level of expression.

[0066] The generation unit can use gentle words or positive expressions in the sweet setting, and can use frank and harsh expressions in the harsh setting. For example, the generation unit uses gentle words and positive expressions in the sweet setting. The gentle words include positive adjectives and encouraging words. For example, expressions such as "great," "nice," and "great results" are used. The positive expressions include positive phrases and positive messages. For example, expressions such as "this product is very easy to use and I am satisfied," and "this service is very convenient" are used. The harsh setting uses frank and harsh expressions. The frank and harsh expressions include critical comments and direct criticism. For example, expressions such as "this product is difficult to use and I am dissatisfied," and "this service is disappointing" are used. The generation unit uses a generation AI to generate expressions based on the user's settings. The generation AI uses a text generation AI (e.g., LLM) to analyze the contents of the input news and reviews and generate expressions according to the set level. This allows the generation unit to generate appropriate expressions according to the user's settings.

[0067] The setting unit can estimate the user's emotion and automatically suggest a level from mild to spicy based on the estimated user's emotion. The setting unit, for example, estimates the user's emotion and automatically suggests a level from mild to spicy based on the estimated user's emotion. The user's emotion is estimated using technologies such as facial expression recognition, voice analysis, and text analysis. For example, facial expression recognition technology is used to estimate the emotion from the user's facial expression. Voice analysis technology is used to estimate the emotion from the tone and speed of the user's voice. Text analysis technology is used to estimate the emotion from the user's input text. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, if the user is feeling stressed, a mild level is automatically suggested. If the user is relaxed, a medium level is automatically suggested. If the user is excited, a spicy level is automatically suggested. This allows the setting unit to automatically suggest an appropriate level according to the user's emotion.

[0068] The setting unit can analyze the user's past setting history and recommend an appropriate setting level. The setting unit, for example, analyzes the user's past setting history and recommends an optimal setting level. The past setting history includes the setting date and time, the setting content, etc. For example, the optimal setting level is recommended based on the level frequently selected by the user in the past. The level to be selected in a specific time period is predicted and recommended from the user's past setting history. The user's past setting history is analyzed and the most frequently used level is recommended. The setting unit uses a generation AI to analyze the user's past setting history and recommends an appropriate setting level. The generation AI uses a text generation AI (for example, LLM) to analyze the user's past setting history and recommend an optimal setting level. This allows the setting unit to recommend an optimal level based on the user's past setting history.

[0069] The setting unit can perform filtering based on the user's current psychological state and field of interest at the time of setting. For example, the setting unit performs filtering based on the user's current psychological state and field of interest at the time of setting. The psychological state is evaluated based on criteria such as stress level and happiness. The field of interest is identified based on data such as questionnaire results and browsing history. For example, if the user is feeling stressed in the current psychological state, a mild setting is preferentially suggested. If the user's field of interest is positive, a mild setting is preferentially suggested. If the user's psychological state is relaxed, a medium spicy setting is preferentially suggested. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. This allows the setting unit to propose an appropriate setting according to the user's psychological state and field of interest.

[0070] The setting unit can estimate the user's emotion and determine the priority of the level to be set based on the estimated user's emotion. The setting unit, for example, estimates the user's emotion and determines the priority of the level to be set based on the estimated user's emotion. The priority is determined based on criteria such as importance score and urgency. For example, when the user is stressed, the mild setting is given top priority. When the user is relaxed, the medium spicy setting is given top priority. When the user is excited, the spicy setting is given top priority. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. This allows the setting unit to determine the priority of an appropriate level according to the user's emotion.

[0071] The setting unit can preferentially suggest highly relevant settings based on the geographical location information of the user at the time of setting. For example, the setting unit preferentially suggests highly relevant settings in consideration of the geographical location information of the user at the time of setting. The geographical location information is acquired by a method such as GPS data or an IP address. For example, when the user is in a specific area, a setting such as sweet or dry is suggested based on the culture and customs of the area. When the user is traveling, a setting that matches the culture of the travel destination is suggested. When the user is at home, an optimal setting is suggested based on the past setting history. The setting unit uses a generation AI to analyze the geographical location information of the user and propose a highly relevant setting. The generation AI uses a text generation AI (e.g., LLM) to analyze the geographical location information and propose an optimal setting. This allows the setting unit to propose an appropriate setting based on the geographical location information of the user.

[0072] The setting unit can analyze the user's social media activity at the time of setting and suggest relevant settings. For example, at the time of setting, the setting unit analyzes the user's social media activity and suggests relevant settings. The social media activity is analyzed based on data such as the content of the post and the number of likes. For example, if the user posts positively on social media, a mild setting is suggested. If the user posts negatively on social media, a harsh setting is suggested. From the user's social media activity, an optimal setting is suggested based on topics of interest. The setting unit uses a generation AI to analyze the user's social media activity and suggests relevant settings. The generation AI uses a text generation AI (e.g., LLM) to analyze social media activity and suggest optimal settings. This allows the setting unit to suggest appropriate settings based on the user's social media activity.

[0073] The generation unit can estimate the user's emotion and adjust the tone of the expression to be generated based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the tone of the expression to be generated based on the estimated user's emotion. The tone is adjusted based on criteria such as formal, casual, and friendly. For example, when the user is relaxed, an expression is generated in a gentle tone. When the user is excited, an expression is generated in an energetic tone. When the user is stressed, an expression is generated in a gentle tone. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. This allows the generation unit to generate an expression in an appropriate tone according to the user's emotion.

[0074] The generation unit can adjust the level of detail of the expression based on the importance of the text at the time of generation. For example, the generation unit adjusts the level of detail of the expression based on the importance of the text at the time of generation. The importance of the text is evaluated based on criteria such as the frequency of appearance of keywords and the importance of the context. For example, in the case of an important news article, a detailed expression is generated. In the case of a general product review, a concise expression is generated. In the case of a topic in which the user is particularly interested, a detailed expression is generated. The generation unit adjusts the level of detail of the expression based on the importance of the text using a generation AI. The generation AI uses a text generation AI (e.g., LLM) to analyze the importance of the text and generate an expression with an appropriate level of detail. This allows the generation unit to generate an expression with an appropriate level of detail according to the importance of the text.

[0075] The generation unit can apply different generation algorithms depending on the category of the text at the time of generation. For example, the generation unit applies different generation algorithms depending on the category of the text at the time of generation. The categories of text are classified based on criteria such as news, blogs, reviews, etc. For example, in the case of a news article, a generation algorithm dedicated to news is applied. In the case of a product review, a generation algorithm dedicated to reviews is applied. In the case of a social media post, a generation algorithm dedicated to social media is applied. The generation unit uses a generation AI to apply different generation algorithms depending on the category of the text. The generation AI uses a text generation AI (e.g., LLM) to analyze the category of the text and apply an appropriate generation algorithm. This allows the generation unit to apply an appropriate generation algorithm depending on the category of the text.

[0076] The generation unit can estimate the user's emotion and adjust the length of the expression to be generated based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the length of the expression to be generated based on the estimated user's emotion. The length of the expression is adjusted based on criteria such as the number of characters and the number of sentences. For example, if the user is in a hurry, a short and to the point expression is generated. If the user is relaxed, a longer expression including a detailed explanation is generated. If the user is excited, an expression with a visually stimulating effect is generated. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. This allows the generation unit to generate an expression with an appropriate length according to the user's emotion.

[0077] The generation unit can determine the priority of expressions based on the time of submission of the text at the time of generation. For example, the generation unit determines the priority of expressions based on the time of submission of the text at the time of generation. The submission time is evaluated based on criteria such as the submission date and time and the submission order. For example, for the latest news article, an expression is generated as a priority. For old product reviews, an expression is generated later. For information with high urgency, an expression is generated as a top priority. The generation unit uses a generation AI to determine the priority of expressions based on the time of submission of the text. The generation AI uses a text generation AI (e.g., LLM) to analyze the submission time and generate expressions with an appropriate priority. This allows the generation unit to generate expressions with an appropriate priority according to the time of submission of the text.

[0078] The generation unit can adjust the order of the expressions based on the relevance of the text at the time of generation. The generation unit, for example, adjusts the order of the expressions based on the relevance of the text at the time of generation. The relevance of the text is evaluated based on criteria such as common keywords, related topics, etc. For example, the order of the expressions is adjusted so that important information is displayed first. The order of the expressions is adjusted so that less relevant information is displayed later. The order of the expressions is adjusted so that highly relevant information is displayed preferentially based on the user's interest. The generation unit adjusts the order of the expressions based on the relevance of the text using a generation AI. The generation AI uses a text generation AI (e.g., LLM) to analyze the relevance of the text and generate expressions in an appropriate order. This allows the generation unit to generate expressions in an appropriate order according to the relevance of the text.

[0079] The providing unit can estimate the user's emotion and adjust the display method of the expression to be provided based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and adjusts the display method of the expression to be provided based on the estimated user's emotion. The display method is adjusted based on criteria such as font size, color, and layout. For example, when the user is nervous, a simple and highly visible display method is provided. When the user is relaxed, a display method including detailed information is provided. When the user is in a hurry, a display method that focuses on the main points is provided. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. This allows the providing unit to provide the expression in an appropriate display method according to the user's emotion.

[0080] The providing unit can select an appropriate display method by referring to the user's past browsing history at the time of providing. For example, the providing unit selects the optimal display method by referring to the user's past browsing history at the time of providing. The browsing history includes the browsing date and time, the browsed pages, etc. For example, the optimal display method is selected based on the display method of the content that the user frequently browsed in the past. A display method suitable for a specific time period is selected from the user's past browsing history. The user's past browsing history is analyzed and the most frequently used display method is selected. The providing unit uses a generation AI to analyze the user's past browsing history and selects an appropriate display method. The generation AI uses a text generation AI (e.g., LLM) to analyze the browsing history and select the optimal display method. This allows the providing unit to select the optimal display method based on the user's past browsing history.

[0081] The providing unit can customize the display content based on the user's current field of interest at the time of providing. For example, the providing unit customizes the display content based on the user's current field of interest at the time of providing. The display content is customized based on criteria such as the type and order of information to be displayed. For example, the display content is customized based on topics in which the user is currently interested. Information related to the user's current field of interest is preferentially displayed. When the user's field of interest changes, the display content is customized in real time. The providing unit uses a generation AI to analyze the user's current field of interest and customize the display content. The generation AI uses a text generation AI (e.g., LLM) to analyze the field of interest and generate appropriate display content. This allows the providing unit to provide appropriate display content according to the user's current field of interest.

[0082] The providing unit can estimate the user's emotion and determine the priority of the expressions to be provided based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and determines the priority of the expressions to be provided based on the estimated user's emotion. The priority is determined based on criteria such as importance score and urgency. For example, when the user is stressed, a mild expression is preferentially provided. When the user is relaxed, a medium spicy expression is preferentially provided. When the user is excited, a spicy expression is preferentially provided. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. This allows the providing unit to provide expressions with appropriate priorities according to the user's emotion.

[0083] The providing unit can select the optimal display method in consideration of the geographical location information of the user at the time of providing. For example, the providing unit selects the optimal display method in consideration of the geographical location information of the user at the time of providing. The geographical location information is acquired by a method such as GPS data or an IP address. For example, when the user is in a specific area, the display method is selected based on the culture and customs of the area. When the user is traveling, the display method is selected according to the culture of the travel destination. When the user is at home, the optimal display method is selected based on the past browsing history. The providing unit uses a generation AI to analyze the geographical location information of the user and selects the optimal display method. The generation AI uses a text generation AI (e.g., LLM) to analyze the geographical location information and select an appropriate display method. This allows the providing unit to select an appropriate display method based on the geographical location information of the user.

[0084] The providing unit can customize the display content by analyzing the user's social media activity at the time of providing. For example, the providing unit customizes the display content by analyzing the user's social media activity at the time of providing. The social media activity is analyzed based on data such as the post content and the number of likes. For example, if the user posts positively on social media, the display unit preferentially provides sweet expressions. If the user posts negatively on social media, the display unit preferentially provides harsh expressions. The display content is customized based on the user's social media activity and topics of interest. The providing unit uses a generating AI to analyze the user's social media activity and customize the display content. The generating AI uses a text generating AI (e.g., LLM) to analyze the social media activity and generate appropriate display content. This allows the providing unit to provide appropriate display content based on the user's social media activity.

[0085] The analysis unit can estimate the user's emotion and adjust the accuracy of the analysis based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the accuracy of the analysis based on the estimated user's emotion. The accuracy of the analysis is adjusted based on criteria such as an error range and reliability. For example, if the user is relaxed, a detailed analysis is performed. If the user is stressed, a brief analysis is performed. If the user is excited, a quick analysis is performed. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. This allows the analysis unit to perform analysis with appropriate accuracy according to the user's emotion.

[0086] The analysis unit can optimize the analysis algorithm by referring to past analysis data during analysis. The analysis unit, for example, optimizes the analysis algorithm by referring to past analysis data during analysis. The past analysis data includes the analysis date and time, the analysis result, and the like. For example, an optimal analysis algorithm is selected based on the past analysis data. A specific pattern is extracted from the past analysis data, and the analysis algorithm is optimized. The past analysis data is analyzed to improve the accuracy of the analysis. The analysis unit uses a generation AI to analyze the past analysis data and optimize the analysis algorithm. The generation AI uses a text generation AI (for example, LLM) to analyze the past analysis data and select an optimal analysis algorithm. This allows the analysis unit to optimize the analysis algorithm based on the past analysis data.

[0087] The analysis unit can apply different analysis methods to each text category during analysis. For example, the analysis unit applies different analysis methods to each text category during analysis. Analysis methods include statistical analysis, machine learning, and the like. For example, in the case of a news article, an analysis method dedicated to news is applied. In the case of a product review, an analysis method dedicated to reviews is applied. In the case of a social media post, an analysis method dedicated to social media is applied. The analysis unit uses a generation AI to apply different analysis methods to each text category. The generation AI uses a text generation AI (e.g., LLM) to analyze the text category and apply an appropriate analysis method. This allows the analysis unit to apply an appropriate analysis method according to the text category.

[0088] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the display method of the analysis result based on the estimated user's emotion. The display method is adjusted based on criteria such as font size, color, and layout. For example, if the user is nervous, a simple and highly visible display method is provided. If the user is relaxed, a display method including detailed information is provided. If the user is in a hurry, a display method that focuses on the main points is provided. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. This allows the analysis unit to provide the analysis result in an appropriate display method according to the user's emotion.

[0089] The analysis unit can determine the analysis priority based on the time of submission of the text during analysis. For example, the analysis unit determines the analysis priority based on the time of submission of the text during analysis. The submission time is evaluated based on criteria such as the submission date and time and the submission order. For example, in the case of the latest news article, analysis is performed as a priority. In the case of an old product review, analysis is performed later. In the case of information with high urgency, analysis is performed as a top priority. The analysis unit uses a generation AI to determine the analysis priority based on the time of submission of the text. The generation AI uses a text generation AI (e.g., LLM) to analyze the submission time and perform analysis with appropriate priority. This allows the analysis unit to perform analysis with appropriate priority according to the time of submission of the text.

[0090] The analysis unit can improve the accuracy of the analysis by referring to the relevant market data of the text during analysis. The analysis unit, for example, improves the accuracy of the analysis by referring to the relevant market data of the text during analysis. The relevant market data is obtained by methods such as market reports, sales data, etc. For example, the accuracy of the analysis is improved based on the relevant market data. Specific trends are extracted from the market data and reflected in the analysis. The market data is analyzed to increase the reliability of the analysis results. The analysis unit uses the generation AI to analyze the relevant market data and improve the accuracy of the analysis. The generation AI uses a text generation AI (e.g., LLM) to analyze the market data and apply an appropriate analysis method. This allows the analysis unit to improve the accuracy of the analysis based on the relevant market data.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The setting unit can analyze the user's past behavior history and learn what expression level the user prefers. For example, if the user has chosen many mild expressions in the past, the setting unit can preferentially suggest a mild level the next time the user selects settings. In addition, if the user has a tendency to prefer spicy expressions during a specific time period, the setting unit can suggest a spicy level for that time period. Furthermore, if the user has consistently chosen medium-spicy expressions for a specific topic, the setting unit can suggest a medium-spicy level for content related to that topic. This allows the setting unit to provide more personalized settings based on the user's past behavior history.

[0093] The generation unit can customize the style of expression according to the user's preferences. For example, if the user prefers formal expressions, the generation unit can generate expressions using formal language and writing style. Conversely, if the user prefers casual expressions, the generation unit can generate expressions using casual language and writing style. In addition, if the user prefers humorous expressions, the generation unit can also generate humorous expressions. Furthermore, if the user has a specific cultural background, the generation unit can generate expressions suitable for that culture. In this way, the generation unit can provide a variety of expression styles according to the user's preferences.

[0094] The providing unit can optimize the display method according to the device and environment of the user. For example, when the user is using a smartphone, the providing unit can provide a mobile-friendly display method. When the user is using a personal computer, the providing unit can provide a display method for desktops. Also, when the user is in a dark place, the providing unit can display in dark mode. Furthermore, when the user is in a noisy environment, the providing unit can provide a visually emphasized display method. In this way, the providing unit can provide an optimal display method according to the device and environment of the user.

[0095] The generation unit can collect user feedback and improve the expression generation algorithm based on the feedback. For example, an interface is provided that allows the user to evaluate the generated expressions, and the evaluation data is collected. If the user provides a positive evaluation, the expression style can be reflected in future generation. Conversely, if the user provides a negative evaluation, the evaluation data can be used as data for improving the expression style. In addition, if the user provides specific feedback, the generation algorithm can be adjusted based on the feedback. This allows the generation unit to improve the accuracy and quality of expression generation based on the user feedback.

[0096] The providing unit can analyze the user's browsing history and preferentially display highly relevant content. For example, if the user has browsed a lot of content related to a specific topic in the past, new content related to the topic can be preferentially displayed. In addition, if the user has a tendency to prefer a specific type of content in a specific time period, content suitable for that time period can be displayed. Furthermore, if the user has a tendency to browse a specific type of content on a specific device, content suitable for that device can be displayed. This allows the providing unit to realize more personalized content display based on the user's browsing history.

[0097] The setting unit can estimate the user's emotion and adjust the tone of the expression based on the estimated emotion. For example, if the user is stressed, the setting unit can suggest an expression with a calm tone. If the user is relaxed, the setting unit can suggest an expression with a casual tone. If the user is excited, the setting unit can suggest an expression with an energetic tone. Also, if the user is sad, the setting unit can suggest an expression with a comforting tone. In this way, the setting unit can provide an expression with an appropriate tone according to the user's emotion.

[0098] The generation unit can estimate the user's emotion and adjust the level of detail of the expression based on the estimated emotion. For example, if the user is in a hurry, the generation unit can generate a concise and to-the-point expression. If the user is relaxed, the generation unit can generate an expression including detailed explanations. If the user is excited, the generation unit can generate an expression with a visually stimulating effect. Also, if the user is sad, the generation unit can generate an expression with a lot of kind words. This allows the generation unit to generate an expression with an appropriate level of detail according to the user's emotion.

[0099] The providing unit can estimate the user's emotion and adjust the display method based on the estimated emotion. For example, if the user is nervous, the providing unit can provide a simple and highly visible display method. If the user is relaxed, the providing unit can provide a display method including detailed information. If the user is in a hurry, the providing unit can provide a display method that focuses on the main points. Also, if the user is sad, the providing unit can provide a display method using gentle colors and fonts. This allows the providing unit to provide an expression in an appropriate display method according to the user's emotion.

[0100] The setting unit can estimate the user's emotion and determine the priority of the level to be set based on the estimated emotion. For example, if the user is stressed, a mild setting can be given top priority. If the user is relaxed, a medium spicy setting can be given top priority. If the user is excited, a spicy setting can be given top priority. Also, if the user is sad, a comforting mild setting can be given priority. This allows the setting unit to determine the priority of an appropriate level according to the user's emotion.

[0101] The generation unit can estimate the user's emotion and adjust the length of the generated expression based on the estimated emotion. For example, if the user is in a hurry, a short and to the point expression can be generated. If the user is relaxed, a longer expression including detailed explanations can be generated. If the user is excited, an expression with a visually stimulating effect can be generated. Also, if the user is sad, a shorter expression using a lot of kind words can be generated. This allows the generation unit to generate expressions with appropriate lengths according to the user's emotion.

[0102] The process flow of the second embodiment will be briefly described below.

[0103] Step 1: The setting section allows the user to set the level from mild to spicy. The user selects the desired expression level from three levels: mild, medium spicy, and spicy, using an interface such as a slider or a drop-down menu. Step 2: The generation unit generates expressions based on the level set by the setting unit. The generation unit includes an analysis unit that uses natural language processing technology to analyze the input text and perform sentiment analysis. Using the generation AI, the mild setting uses a lot of kind words and positive expressions, while the harsh setting uses frank and harsh expressions. For example, the mild setting would express "This product is very easy to use and I am very satisfied with it," while the harsh setting would express "This product is difficult to use and I am very dissatisfied with it." Step 3: The providing unit provides the representation generated by the generating unit to the user. The providing unit displays the generated representation to the user through a web application or a mobile application.

[0104] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0106] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0107] Each of the multiple elements including the setting unit, the generating unit, and the providing unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the smart device 14, and provides an interface for the user to set a level from sweet to spicy. The generating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an expression based on the set level. The providing unit is realized, for example, by the output device 40 of the smart device 14, and provides the generated expression to the user. The correspondence between each unit and the device or the control unit is not limited to the above example, and various changes are possible.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0110] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0111] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0112] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0113] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0114] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0115] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0116] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0117] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0118] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0119] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0120] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0121] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0122] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0123] Each of the multiple elements including the setting unit, the generating unit, and the providing unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the smart glasses 214, and provides an interface for the user to set a level from sweet to spicy. The generating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an expression based on the set level. The providing unit is realized, for example, by the speaker 240 of the smart glasses 214, and provides the generated expression to the user. The correspondence between each unit and the device or the control unit is not limited to the above example, and various changes are possible.

[0124] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0125] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0126] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0127] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0128] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0129] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0130] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0131] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0132] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0133] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0134] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0135] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0136] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0138] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0139] Each of the multiple elements including the setting unit, the generating unit, and the providing unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the headset type terminal 314, and provides an interface for the user to set a level from sweet to spicy. The generating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an expression based on the set level. The providing unit is realized, for example, by the display 343 of the headset type terminal 314, and provides the generated expression to the user. The correspondence between each unit and the device or the control unit is not limited to the above example, and various changes are possible.

[0140] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0141] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0142] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0143] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0144] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0145] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0146] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0147] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0148] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0149] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0150] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0151] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0152] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0153] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0155] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0156] Each of the multiple elements including the setting unit, the generating unit, and the providing unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the robot 414, and provides an interface for the user to set a level from sweet to spicy. The generating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates an expression based on the set level. The providing unit is realized, for example, by the speaker 240 of the robot 414, and provides the generated expression to the user. The correspondence between each unit and the device or the control unit is not limited to the above example, and various changes are possible.

[0157] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0158] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0159] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0160] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0161] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0162] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0163] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0164] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0165] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0166] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0167] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0168] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0169] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0170] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0171] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0172] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0173] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0174] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0175] (Appendix 1) A setting unit for allowing a user to set a level from sweet to spicy; a generating unit that generates an expression based on the level set by the setting unit; a providing unit that provides the expression generated by the generating unit to a user; Equipped A system characterized by: (Appendix 2) The generation unit is Includes an analysis unit that uses natural language processing technology to analyze input text and perform sentiment analysis. 2. The system of claim 1, (Appendix 3) The setting unit is A user selects the desired level of expression using at least one of a slider or a drop-down menu interface. 2. The system of claim 1, (Appendix 4) The generation unit is In a sweet setting, use kind words or positive expressions, and in a harsh setting, use blunt and harsh expressions. 2. The system of claim 1, (Appendix 5) The setting unit is Estimate the user's emotions and automatically suggest levels from mild to harsh based on the estimated user emotions. 2. The system of claim 1, (Appendix 6) The setting unit is Analyze the user's past settings history and recommend appropriate settings levels 2. The system of claim 1, (Appendix 7) The setting unit is At setup time, filtering is based on the user's current mood and interests 2. The system of claim 1, (Appendix 8) The setting unit is A user's emotion is estimated, and a priority of the level to be set is determined based on the estimated user's emotion. 2. The system of claim 1, (Appendix 9) The setting unit is During setup, prioritize and suggest relevant settings based on the user's geographic location 2. The system of claim 1, (Appendix 10) The setting unit is When configured, analyze your social media activity to suggest relevant settings 2. The system of claim 1, (Appendix 11) The generation unit is Estimating a user's emotion and adjusting the tone of the generated expression based on the estimated user's emotion 2. The system of claim 1, (Appendix 12) The generation unit is During generation, the level of detail of the representation is adjusted based on the importance of the text. 2. The system of claim 1, (Appendix 13) The generation unit is During generation, different generation algorithms are applied depending on the category of the text. 2. The system of claim 1, (Appendix 14) The generation unit is Estimate the user's emotion and adjust the length of the generated expression based on the estimated user's emotion. 2. The system of claim 1, (Appendix 15) The generation unit is At generation time, prioritize expressions based on when the text was submitted 2. The system of claim 1, (Appendix 16) The generation unit is At generation time, adjust the order of expressions based on text relevance 2. The system of claim 1, (Appendix 17) The providing unit is To estimate a user's emotion and adjust a display method of a provided expression based on the estimated user's emotion. 2. The system of claim 1, (Appendix 18) The providing unit is When providing the content, the appropriate display method is selected by referring to the user's past browsing history. 2. The system of claim 1, (Appendix 19) The providing unit is At the time of delivery, customize the content displayed based on the user's current interests 2. The system of claim 1, (Appendix 20) The providing unit is Estimate the user's emotions and determine the priority of expressions to provide based on the estimated user's emotions. 2. The system of claim 1, (Appendix 21) The providing unit is When providing the content, the optimal display method is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 22) The providing unit is When provided, analyze your social media activity to customize what you see 2. The system of claim 1, (Appendix 23) The analysis unit is Estimate user emotions and adjust analysis accuracy based on the estimated user emotions 3. The system of claim 2, (Appendix 24) The analysis unit is During analysis, the analysis algorithm is optimized by referencing past analysis data. 3. The system of claim 2, (Appendix 25) The analysis unit is During analysis, different analysis techniques are applied to different categories of text 3. The system of claim 2, (Appendix 26) The analysis unit is Infer user emotions and adjust the way analysis results are displayed based on the inferred user emotions 3. The system of claim 2, (Appendix 27) The analysis unit is During analysis, prioritize analysis based on when the text was submitted 3. The system of claim 2, (Appendix 28) The analysis unit is During analysis, refer to relevant market data in the text to improve the accuracy of the analysis 3. The system of claim 2, [Explanation of symbols]

[0176] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A setting unit for allowing a user to set a level from sweet to spicy; a generating unit that generates an expression based on the level set by the setting unit; a providing unit that provides the expression generated by the generating unit to a user; Equipped A system characterized by:

2. The generation unit is Includes an analysis unit that uses natural language processing technology to analyze input text and perform sentiment analysis.

2. The system of claim 1 .

3. The setting unit is A user selects the desired level of expression using at least one of a slider or a drop-down menu interface.

2. The system of claim 1 .

4. The generation unit is In a sweet setting, use kind words or positive expressions, and in a harsh setting, use blunt and harsh expressions.

2. The system of claim 1 .

5. The setting unit is Estimate the user's emotions and automatically suggest levels from mild to harsh based on the estimated user emotions.

2. The system of claim 1 .

6. The setting unit is Analyze the user's past settings history and recommend appropriate settings levels 2. The system of claim 1 .

7. The setting unit is At setup time, filtering is based on the user's current mood and interests 2. The system of claim 1 .

8. The setting unit is A user's emotion is estimated, and a priority of the level to be set is determined based on the estimated user's emotion.

2. The system of claim 1 .

9. The setting unit is During setup, prioritize and suggest relevant settings based on the user's geographic location 2. The system of claim 1 .

10. The setting unit is When configured, analyze your social media activity to suggest relevant settings 2. The system of claim 1 .

Images