System

Abstract

To provide a system that converts negative expressions into positive expressions in order to keep an emotion of a user calm.SOLUTION: A system comprises a detection unit, a rephrasing unit, and a customization unit. The detection unit detects negative expressions. The rephrasing unit rephrases the negative expressions detected by the detection unit into positive expressions. The customization unit customizes information rephrased by the rephrasing unit according to preferences of the 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] In conventional technology, negative expressions are displayed as they are, which may cause users to feel uncomfortable.

[0005] The system according to the embodiment aims to convert negative expressions into positive expressions and keep the user's emotions calm. [Means for solving the problem]

[0006] The system according to the embodiment includes a detection unit, a paraphrase unit, and a customization unit. The detection unit detects negative expressions. The paraphrase unit paraphrases the negative expressions detected by the detection unit into positive expressions. The customization unit customizes the information paraphrased by the paraphrase unit according to a user's preference. Effect of the Invention

[0007] The system according to the embodiment can convert negative expressions into positive expressions, thereby keeping the user's emotions calm. [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 positive surfing system according to the embodiment of the present invention is a system that supports users in interacting with information on a daily basis without getting upset by paraphrasing or filtering negative content and expressions in the world. The positive surfing system collects reviews and SNS posts that users browse, analyzes the collected posts, and detects negative expressions and extreme comments. The detected negative expressions and extreme comments are paraphrased into positive expressions or filtered. This allows users to browse information without feeling negative. For example, if a review of a product contains an expression such as "this product is completely no good," the expression is paraphrased into a positive expression such as "this product has room for improvement." It is also possible to filter and refrain from displaying posts that contain extreme comments. In this way, browsing can be performed without compromising information. Furthermore, the positive surfing system can be customized according to the user's preferences. For example, for a user who is particularly sensitive to a particular keyword, posts containing that keyword can be preferentially filtered. In addition, the tone and style of paraphrasing into positive expressions can also be adjusted according to the user's preferences. This mechanism allows users to interact with information on a daily basis without feeling negative. The positive surfing system is an effective way to keep users in a good mood without compromising the quality of the information. This allows users to browse information without feeling negative emotions.

[0029] The positive surfing system according to the embodiment includes a detection unit, a paraphrase unit, and a customization unit. The detection unit detects negative expressions. The detection unit detects keywords or phrases that indicate negative emotions, for example, using natural language processing technology. For example, the detection unit can detect aggressive or insulting words. The paraphrase unit paraphrases the negative expressions detected by the detection unit into positive expressions. For example, the paraphrase unit can paraphrase the detected expression "This product is no good at all" into a positive expression such as "This product has room for improvement." The customization unit customizes the information paraphrased by the paraphrase unit according to the user's preferences. The customization unit performs customization based on, for example, the user's past browsing history and feedback. For example, for a user who is particularly sensitive to a particular keyword, posts containing that keyword can be preferentially filtered. As a result, the positive surfing system according to the embodiment allows the user to browse information without feeling negative emotions.

[0030] The detection unit detects negative expressions. The detection unit detects keywords and phrases that indicate negative emotions using, for example, natural language processing technology. Specifically, as the natural language processing technology, morphological analysis and sentiment analysis algorithms can be used. Morphological analysis divides a sentence into words and analyzes the part of speech and meaning of each word. The sentiment analysis algorithm calculates the sentiment score of each word or phrase and identifies words or phrases that indicate negative emotions. For example, a sentence containing words such as "hate," "the worst," and "failure" is detected as a negative expression. In addition, analysis is performed taking into account the context, and the combination of words and the tone of the entire sentence are evaluated, making it possible to detect negative expressions with higher accuracy. Furthermore, the detection unit uses a machine learning model to learn patterns of negative expressions based on past data and can detect new negative expressions with high accuracy. As a result, the detection unit can quickly and accurately detect negative expressions from sentences and posted contents entered by users and pass them on to the next process.

[0031] The paraphrasing unit paraphrases the negative expressions detected by the detection unit into positive expressions. For example, the paraphrasing unit can paraphrase the detected expression "This product is completely useless" into a positive expression such as "This product has room for improvement." Specifically, the paraphrasing unit refers to a database of positive expressions prepared in advance and selects appropriate paraphrasing candidates. Furthermore, the paraphrasing unit can utilize a generation AI to perform natural paraphrasing taking into account the context. The generation AI analyzes the input negative expression and generates a positive expression appropriate to the context. For example, the expression "This service is difficult to use" can be paraphrased into an expression such as "This service has room for improvement and we can expect future updates." The generation AI can learn based on past data and user feedback and perform more natural and effective paraphrasing. As a result, the paraphrasing unit converts negative expressions into positive expressions, allowing the user to receive information with a more positive feeling.

[0032] The customization unit customizes the information paraphrased by the paraphrasing unit according to the user's preferences. The customization unit performs customization based on, for example, the user's past browsing history and feedback. Specifically, the customization unit analyzes the user's browsing history and learns what expressions and contents the user responds to positively. This allows the optimal paraphrased expression to be provided for each user. In addition, if the user is particularly sensitive to a specific keyword, posts containing that keyword are preferentially filtered to provide information that is less stressful for the user. Furthermore, the customization unit collects user feedback and continuously improves the accuracy and appropriateness of the paraphrased expression. For example, if the user evaluates that "this paraphrase was appropriate," the same paraphrase is applied to other users based on that feedback. In addition, if the user evaluates that "this paraphrase was inappropriate," the paraphrase algorithm is adjusted based on that feedback to improve the accuracy of paraphrasing from the next time onwards. As a result, the customization unit can perform flexible customization according to the user's preferences and needs, and provide information with a higher level of satisfaction.

[0033] The detection unit can detect keywords or phrases that indicate negative emotions using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the detection unit can use morphological analysis to divide a sentence into words and detect keywords that indicate negative emotions. The detection unit can also use grammatical analysis to analyze the structure of the sentence and detect negative phrases. Furthermore, the detection unit can use semantic analysis to understand the meaning of the sentence and detect expressions that indicate negative emotions. For example, the detection unit can use morphological analysis to divide the sentence "This product is no good at all" into words and detect the negative keyword "no good". The detection unit can also use grammatical analysis to analyze the structure of the sentence "This product is no good at all" and detect the negative phrase "no good at all". Furthermore, the detection unit can use semantic analysis to understand the meaning of the sentence "This product is no good at all" and detect expressions that indicate negative emotions. In this way, keywords and phrases that indicate negative emotions can be accurately detected by using natural language processing technology.

[0034] The paraphrasing unit can paraphrase the detected negative expression into a positive expression. Positive expressions include, for example, words of encouragement and words of gratitude. For example, the paraphrasing unit can paraphrase the detected expression "This product is no good at all" into a positive expression such as "This product has room for improvement." In addition, the paraphrasing unit can paraphrase the detected expression "This service is the worst" into a positive expression such as "This service needs improvement." In addition, the paraphrasing unit can paraphrase the detected expression "This app is difficult to use" into a positive expression such as "This app has room for improvement." For example, the paraphrasing unit can paraphrase the detected expression "This product is no good at all" into a positive expression such as "This product has room for improvement." In addition, the paraphrasing unit can paraphrase the detected expression "This service is the worst" into a positive expression such as "This service needs improvement." In addition, the paraphrasing unit can paraphrase the detected expression "This app is difficult to use" into a positive expression such as "This app has room for improvement." In this way, by paraphrasing the negative expression into a positive expression, it is possible to prevent the user from having negative emotions.

[0035] The customization unit can perform customization based on the user's past browsing history or feedback. The customization includes, for example, the type of user's preferences and the range of customization. For example, the customization unit can analyze the user's past browsing history, and for a user who is particularly sensitive to a particular keyword, preferentially filter posts containing the keyword. The customization unit can also adjust the tone and style when rephrasing in a positive expression based on the user's feedback. Furthermore, the customization unit can adjust the method of customization based on the user's past browsing history and feedback. For example, the customization unit can analyze the user's past browsing history, and for a user who is particularly sensitive to a particular keyword, preferentially filter posts containing the keyword. The customization unit can also adjust the tone and style when rephrasing in a positive expression based on the user's feedback. Furthermore, the customization unit can adjust the method of customization based on the user's past browsing history and feedback. As a result, by performing customization based on the user's past browsing history and feedback, it is possible to provide information according to the user's preferences.

[0036] The positive surfing system includes a filtering unit that filters out posts including radical statements and refrains from displaying them. The filtering unit filters out posts including radical statements and refrains from displaying them. Radical statements include, for example, violent words and discriminatory words. The filtering unit can, for example, filter out posts including violent words and refrain from displaying them. The filtering unit can also filter out posts including discriminatory words and refrain from displaying them. Furthermore, the filtering unit can filter out posts including radical statements and refrain from displaying them. For example, the filtering unit can filter out posts including violent words and refrain from displaying them. The filtering unit can also filter out posts including discriminatory words and refrain from displaying them. Furthermore, the filtering unit can filter out posts including radical statements and refrain from displaying them. In this way, by filtering out posts including radical statements, it is possible to prevent a user from coming into contact with unpleasant information.

[0037] The positive surfing system includes a training data collection unit that collects a plurality of data to improve the accuracy of the sentiment analysis. The training data collection unit collects a plurality of data to improve the accuracy of the sentiment analysis. The collected data includes, for example, text data, voice data, image data, and the like. The training data collection unit, for example, collects text data and can use it as training data for the sentiment analysis. The training data collection unit can also collect voice data and use it as training data for the sentiment analysis. Furthermore, the training data collection unit can also collect image data and use it as training data for the sentiment analysis. For example, the training data collection unit collects text data and can use it as training data for the sentiment analysis. The training data collection unit can also collect voice data and use it as training data for the sentiment analysis. Furthermore, the training data collection unit can collect image data and use it as training data for the sentiment analysis. This improves the accuracy of the sentiment analysis by collecting a large amount of data.

[0038] The detection unit can improve the detection accuracy of negative expressions by considering the context of the post. The detection unit, for example, analyzes the context before and after the post to determine whether the negative expression really has a negative meaning. For example, the detection unit can analyze the context before and after the post to determine whether the expression "this product is no good at all" really has a negative meaning. The detection unit can also consider the context according to the category of the post (for example, review, comment, etc.). For example, in the case of a product review, the detection unit can detect a negative expression based on a specific keyword. Furthermore, the detection unit can analyze the length and structure of the post and detect a negative expression based on the context. For example, the detection unit can analyze the length and structure of the post to determine whether the expression "this product is no good at all" really has a negative meaning. As a result, the detection accuracy of negative expressions is improved by considering the context of the post.

[0039] The detection unit can apply different detection algorithms depending on the category of the post. For example, in the case of a product review, the detection unit detects negative expressions based on a specific keyword. For example, the detection unit can detect keywords such as "bad" and "worst" in a product review. In addition, the detection unit can also detect negative expressions using sentiment analysis in the case of social media comments. For example, the detection unit can detect expressions showing emotions such as "anger" and "sadness" in social media comments using sentiment analysis. Furthermore, in the case of a news article, the detection unit can also detect negative expressions based on the tone and content of the article. For example, the detection unit can detect negative expressions such as "danger" and "problem" in a news article based on the tone and content of the article. Thereby, by applying different detection algorithms depending on the category of the post, the detection accuracy is improved.

[0040] The detection unit can detect negative expressions taking into account the geographical distribution of posts. The detection unit detects, for example, negative expressions frequently used in a specific region. For example, the detection unit can detect negative expressions such as "no good" and "the worst" that are frequently used in a specific region. The detection unit can also detect negative expressions taking into account differences in culture and language between regions. For example, the detection unit can detect negative expressions such as "danger" and "problem" taking into account differences in culture and language between regions. Furthermore, the detection unit can analyze geographical trends to detect negative expressions. For example, the detection unit can analyze geographical trends to detect negative expressions frequently used in a specific region. As a result, by taking into account the geographical distribution of posts, detection that reflects differences in culture and language between regions is possible.

[0041] The detection unit can improve the detection accuracy by referring to related literature of the post. The detection unit, for example, refers to literature related to the post and checks the meaning of negative expressions. For example, the detection unit can refer to academic papers related to the post and check the meaning of negative expressions. The detection unit can also adjust the detection criteria for negative expressions based on the content of the related literature. For example, the detection unit can adjust the detection criteria for negative expressions based on the content of the related literature. Furthermore, the detection unit can detect negative expressions by taking into account the tone and content of the related literature. For example, the detection unit can detect negative expressions by taking into account the tone and content of the related literature. Thereby, the detection accuracy of negative expressions is improved by referring to related literature of the post.

[0042] The paraphrasing unit can adjust the level of detail of the paraphrase based on the importance of the negative expression. For example, the paraphrasing unit evaluates the importance of the negative expression, and paraphrases the negative expression with high importance into a detailed positive expression. For example, the paraphrasing unit can paraphrase the expression with high importance, "This product is completely useless," into a detailed positive expression, such as "This product has room for improvement." In addition, the paraphrasing unit can also paraphrase the negative expression with low importance into a concise positive expression. For example, the paraphrasing unit can paraphrase the expression with low importance, "This service is the worst," into a concise positive expression, such as "This service needs improvement." In addition, the paraphrasing unit can adjust the tone and style of the paraphrase according to the importance. For example, the paraphrasing unit can paraphrase the negative expression with high importance in a polite and detailed tone, and paraphrase the negative expression with low importance in a concise and direct tone. In this way, by adjusting the level of detail of the paraphrase based on the importance of the negative expression, appropriate paraphrasing is possible.

[0043] The paraphrasing unit can apply different paraphrasing algorithms depending on the category of the post. For example, in the case of a product review, the paraphrasing unit paraphrases the feedback into positive feedback. For example, the paraphrasing unit can paraphrase the expression "this product is no good at all" in the product review into positive feedback such as "this product has room for improvement". In addition, the paraphrasing unit can paraphrase the comment on social media into a more emoting expression. For example, the paraphrasing unit can paraphrase the expression "this service is the worst" in the social media comment into a more emoting expression such as "this service needs improvement". In addition, the paraphrasing unit can paraphrase the comment on news articles into objective and positive expressions. For example, the paraphrasing unit can paraphrase the expression "this event is very problematic" in the news article into an objective and positive expression such as "this event has room for improvement". In this way, the accuracy of paraphrasing is improved by applying different paraphrasing algorithms depending on the category of the post.

[0044] The paraphrasing unit can determine the priority of paraphrasing based on the submission time of the post. The paraphrasing unit, for example, prioritizes paraphrasing recent posts. For example, the paraphrasing unit can rephrase an expression such as "this product is no good at all" in a recent post into a positive expression such as "this product has room for improvement." The paraphrasing unit can also prioritize paraphrasing posts related to a specific event or trend. For example, the paraphrasing unit can rephrase an expression such as "this service is the worst" in a post related to a specific event or trend into a positive expression such as "this service needs improvement." The paraphrasing unit can also determine the priority based on the user's past browsing history. For example, the paraphrasing unit can prioritize paraphrase posts containing a specific keyword based on the user's past browsing history. In this way, by determining the priority of paraphrasing based on the submission time of the post, the latest information can be prioritized.

[0045] The paraphrasing unit can adjust the order of paraphrasing based on the relevance of the post. For example, the paraphrasing unit preferentially paraphrases posts related to a topic in which the user is interested. For example, the paraphrasing unit can paraphrase an expression such as "this product is no good at all" in a post related to a topic in which the user is interested, into a positive expression such as "this product has room for improvement." In addition, the paraphrasing unit can preferentially paraphrase when the content of the post includes important information. For example, the paraphrasing unit can paraphrase an expression such as "this service is the worst" into a positive expression such as "this service needs improvement" when the content of the post includes important information. In addition, the paraphrasing unit can adjust the order of paraphrasing based on the relevance of the post. For example, the paraphrasing unit can preferentially paraphrase posts including a specific keyword based on the relevance of the post. In this way, by adjusting the order of paraphrasing based on the relevance of the post, information important to the user can be preferentially paraphrased.

[0046] At the time of customization, the customization unit can select an optimal customization method by analyzing the user's past browsing history. The customization unit, for example, analyzes the user's past browsing history and selects an optimal customization method. For example, the customization unit can suggest a customization method based on the content that the user frequently browsed in the past. The customization unit can also analyze the user's past feedback and select an optimal customization method. Furthermore, the customization unit can find a specific pattern from the user's past browsing history and suggest a customization method. For example, the customization unit can suggest a customization method based on the content that the user frequently browsed in the past. The customization unit can also analyze the user's past feedback and select an optimal customization method. Furthermore, the customization unit can find a specific pattern from the user's past browsing history and suggest a customization method. In this way, the optimal customization method can be selected by analyzing the user's past browsing history.

[0047] The customization unit can customize the means of customization based on the user's current field of interest at the time of customization. The customization unit, for example, suggests a customization method based on a topic in which the user is currently interested. For example, the customization unit can rephrase an expression such as "this product is no good at all" into a positive expression such as "this product has room for improvement" based on the topic in which the user is currently interested. The customization unit can also preferentially display information related to the user's current field of interest. For example, the customization unit can preferentially display information related to the topic in which the user is currently interested. Furthermore, the customization unit can adjust the means of customization based on the user's current field of interest. For example, the customization unit can preferentially display posts including a specific keyword based on the topic in which the user is currently interested. This makes it possible to provide more appropriate information by adjusting the means of customization based on the user's current field of interest.

[0048] The customization unit can select an optimal customization method in consideration of the geographical location information of the user at the time of customization. The customization unit, for example, preferentially displays information related to the area where the user is currently located. For example, the customization unit can preferentially display information related to the area where the user is currently located. The customization unit can also analyze geographical trends and suggest an optimal customization method. For example, the customization unit can analyze geographical trends and preferentially display information related to the area where the user is currently located. Furthermore, the customization unit can adjust the means of customization based on the geographical location information of the user. For example, the customization unit can preferentially display information related to the area where the user is currently located. Thereby, by considering the geographical location information of the user, an optimal customization method for each area can be selected.

[0049] The customization unit can analyze the user's social media activities at the time of customization and suggest a means of customization. The customization unit can suggest a customization method based on, for example, topics frequently mentioned by the user on social media. For example, the customization unit can rephrase an expression such as "this product is no good at all" to a positive expression such as "this product has room for improvement" based on topics frequently mentioned by the user on social media. The customization unit can also preferentially display information of interest to the user from the user's social media activities. For example, the customization unit can preferentially display information related to topics frequently mentioned by the user on social media. Furthermore, the customization unit can analyze the user's social media activities and select an optimal customization method. For example, the customization unit can preferentially display posts containing a specific keyword based on topics frequently mentioned by the user on social media. In this way, a more appropriate customization method can be suggested by analyzing the user's social media activities.

[0050] The filtering unit can improve the accuracy of filtering by considering the context of the post when filtering. For example, the filtering unit can analyze the context before and after the post and determine whether an extreme statement really has an extreme meaning. For example, the filtering unit can analyze the context before and after the post and determine whether the expression "this product is no good at all" really has an extreme meaning. The filtering unit can also consider the context according to the category of the post (for example, review, comment, etc.). For example, in the case of a product review, the filtering unit can filter out extreme expressions based on a specific keyword. Furthermore, the filtering unit can analyze the length and structure of the post and filter out extreme expressions based on the context. For example, the filtering unit can analyze the length and structure of the post and determine whether the expression "this product is no good at all" really has an extreme meaning. In this way, the accuracy of filtering is improved by considering the context of the post.

[0051] The filtering unit can perform filtering while taking into consideration the geographical distribution of posts. The filtering unit, for example, filters out extreme expressions that are frequently used in a specific region. For example, the filtering unit can filter out extreme expressions such as "no good" and "the worst" that are frequently used in a specific region. The filtering unit can also perform filtering while taking into consideration differences in culture and language between regions. For example, the filtering unit can filter out extreme expressions such as "danger" and "problem" while taking into consideration differences in culture and language between regions. Furthermore, the filtering unit can analyze geographical trends and filter out extreme expressions. For example, the filtering unit can analyze geographical trends and filter out extreme expressions that are frequently used in a specific region. As a result, filtering that reflects differences in culture and language between regions is possible by taking into consideration the geographical distribution of posts.

[0052] The training data collection unit can optimize the collection algorithm by referring to past data when collecting training data. The training data collection unit, for example, selects an optimal collection algorithm based on data collected in the past. For example, the training data collection unit can select an optimal collection algorithm based on text data collected in the past. The training data collection unit can also analyze trends in past data and adjust the collection algorithm. For example, the training data collection unit can analyze trends in past text data and adjust the collection algorithm. Furthermore, the training data collection unit can evaluate the quality of past data and optimize the collection algorithm. For example, the training data collection unit can evaluate the quality of past text data and optimize the collection algorithm. Thereby, by referring to past data, the collection algorithm can be optimized, enabling more efficient data collection.

[0053] The training data collection unit can weight data based on the submission time of the post when collecting training data. The training data collection unit, for example, preferentially collects recent posts and weights the data. For example, the training data collection unit can preferentially collect data including an expression such as "this product is no good at all" in recent posts and weight the data. The training data collection unit can also preferentially collect posts related to a specific event or trend and weight the data. For example, the training data collection unit can preferentially collect data including an expression such as "this service is the worst" in posts related to a specific event or trend and weight the data. Furthermore, the training data collection unit can weight data based on the user's past browsing history. For example, the training data collection unit can preferentially collect data including a specific keyword based on the user's past browsing history and weight the data. As a result, the latest information can be preferentially collected by weighting the data based on the submission time of the post.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The positive surfing system can further include a history analysis unit that analyzes the user's past browsing history and, for a user who is particularly sensitive to a particular keyword, preferentially filters out posts that include that keyword. For example, if a user has shown a strong reaction to the keyword "no" in the past, the history analysis unit can preferentially filter out posts that include that keyword. In addition, the tone and style of rephrasing in a positive way can be adjusted based on the user's feedback. Furthermore, the method of customization can be adjusted based on the user's past browsing history and feedback. This makes it possible to provide information according to the user's preferences by customizing based on the user's past browsing history and feedback.

[0056] The positive surfing system may further include an interest field customization unit that adjusts the means of customization based on the user's current field of interest. For example, the expression "this product is no good at all" may be rephrased as a positive expression such as "this product has room for improvement" based on the topic in which the user is currently interested. Also, information related to the user's current field of interest may be preferentially displayed. Furthermore, posts containing specific keywords may be preferentially displayed based on the user's current field of interest. This allows more appropriate information to be provided by adjusting the means of customization based on the user's current field of interest.

[0057] The positive surfing system may further include a geographic detection unit that detects negative expressions taking into account the geographic distribution of posts. For example, negative expressions that are frequently used in a particular region may be detected. In addition, negative expressions may be detected taking into account differences in culture and language between regions. Furthermore, negative expressions may be detected by analyzing geographic trends. In this way, by taking into account the geographic distribution of posts, detection that reflects differences in culture and language between regions is possible.

[0058] The positive surfing system may further include a literature reference unit that improves the detection accuracy by referring to related literature of the post. For example, the meaning of negative expressions may be confirmed by referring to academic papers related to the post. In addition, the detection criteria for negative expressions may be adjusted based on the contents of the related literature. Furthermore, negative expressions may be detected by taking into account the tone and contents of the related literature. In this way, the detection accuracy of negative expressions is improved by referring to related literature of the post.

[0059] The positive surfing system may further include a submission time weighting unit that weights data based on the submission time of the post. For example, recent posts may be collected and weighted preferentially. Also, posts related to a particular event or trend may be collected and weighted preferentially. Furthermore, data may be weighted based on the user's past browsing history. Thus, by weighting data based on the submission time of the post, the latest information may be collected preferentially.

[0060] The process flow of the first embodiment will be briefly described below.

[0061] Step 1: The detection unit detects negative expressions. The detection unit uses natural language processing techniques to detect keywords and phrases that indicate negative emotions. For example, it can detect offensive or insulting words. Step 2: The paraphrasing unit paraphrases the negative expressions detected by the detection unit into positive expressions. For example, the expression "This product is completely no good" can be paraphrased into a positive expression such as "This product has room for improvement." Step 3: The customization unit customizes the information paraphrased by the paraphrasing unit according to the user's preferences. The customization unit performs customization based on the user's past browsing history and feedback. For example, for a user who is particularly sensitive to a particular keyword, posts containing that keyword can be preferentially filtered.

[0062] (Example 2) The positive surfing system according to the embodiment of the present invention is a system that supports users in interacting with information on a daily basis without getting upset by paraphrasing or filtering negative content and expressions in the world. The positive surfing system collects reviews and SNS posts that users browse, analyzes the collected posts, and detects negative expressions and extreme comments. The detected negative expressions and extreme comments are paraphrased into positive expressions or filtered. This allows users to browse information without feeling negative. For example, if a review of a product contains an expression such as "this product is completely no good," the expression is paraphrased into a positive expression such as "this product has room for improvement." It is also possible to filter and refrain from displaying posts that contain extreme comments. In this way, browsing can be performed without compromising information. Furthermore, the positive surfing system can be customized according to the user's preferences. For example, for a user who is particularly sensitive to a particular keyword, posts containing that keyword can be preferentially filtered. In addition, the tone and style of paraphrasing into positive expressions can also be adjusted according to the user's preferences. This mechanism allows users to interact with information on a daily basis without feeling negative. The positive surfing system is an effective way to keep users in a good mood without compromising the quality of the information. This allows users to browse information without feeling negative emotions.

[0063] The positive surfing system according to the embodiment includes a detection unit, a paraphrase unit, and a customization unit. The detection unit detects negative expressions. The detection unit detects keywords or phrases that indicate negative emotions, for example, using natural language processing technology. For example, the detection unit can detect aggressive or insulting words. The paraphrase unit paraphrases the negative expressions detected by the detection unit into positive expressions. For example, the paraphrase unit can paraphrase the detected expression "This product is no good at all" into a positive expression such as "This product has room for improvement." The customization unit customizes the information paraphrased by the paraphrase unit according to the user's preferences. The customization unit performs customization based on, for example, the user's past browsing history and feedback. For example, for a user who is particularly sensitive to a particular keyword, posts containing that keyword can be preferentially filtered. As a result, the positive surfing system according to the embodiment allows the user to browse information without feeling negative emotions.

[0064] The detection unit detects negative expressions. The detection unit detects keywords and phrases that indicate negative emotions using, for example, natural language processing technology. Specifically, as the natural language processing technology, morphological analysis and sentiment analysis algorithms can be used. Morphological analysis divides a sentence into words and analyzes the part of speech and meaning of each word. The sentiment analysis algorithm calculates the sentiment score of each word or phrase and identifies words or phrases that indicate negative emotions. For example, a sentence containing words such as "hate," "the worst," and "failure" is detected as a negative expression. In addition, analysis is performed taking into account the context, and the combination of words and the tone of the entire sentence are evaluated, making it possible to detect negative expressions with higher accuracy. Furthermore, the detection unit uses a machine learning model to learn patterns of negative expressions based on past data and can detect new negative expressions with high accuracy. As a result, the detection unit can quickly and accurately detect negative expressions from sentences and posted contents entered by users and pass them on to the next process.

[0065] The paraphrasing unit paraphrases the negative expressions detected by the detection unit into positive expressions. For example, the paraphrasing unit can paraphrase the detected expression "This product is completely useless" into a positive expression such as "This product has room for improvement." Specifically, the paraphrasing unit refers to a database of positive expressions prepared in advance and selects appropriate paraphrasing candidates. Furthermore, the paraphrasing unit can utilize a generation AI to perform natural paraphrasing taking into account the context. The generation AI analyzes the input negative expression and generates a positive expression appropriate to the context. For example, the expression "This service is difficult to use" can be paraphrased into an expression such as "This service has room for improvement and we can expect future updates." The generation AI can learn based on past data and user feedback and perform more natural and effective paraphrasing. As a result, the paraphrasing unit converts negative expressions into positive expressions, allowing the user to receive information with a more positive feeling.

[0066] The customization unit customizes the information paraphrased by the paraphrasing unit according to the user's preferences. The customization unit performs customization based on, for example, the user's past browsing history and feedback. Specifically, the customization unit analyzes the user's browsing history and learns what expressions and contents the user responds to positively. This allows the optimal paraphrased expression to be provided for each user. In addition, if the user is particularly sensitive to a specific keyword, posts containing that keyword are preferentially filtered to provide information that is less stressful for the user. Furthermore, the customization unit collects user feedback and continuously improves the accuracy and appropriateness of the paraphrased expression. For example, if the user evaluates that "this paraphrase was appropriate," the same paraphrase is applied to other users based on that feedback. In addition, if the user evaluates that "this paraphrase was inappropriate," the paraphrase algorithm is adjusted based on that feedback to improve the accuracy of paraphrasing from the next time onwards. As a result, the customization unit can perform flexible customization according to the user's preferences and needs, and provide information with a higher level of satisfaction.

[0067] The detection unit can detect keywords or phrases that indicate negative emotions using natural language processing technology. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. For example, the detection unit can use morphological analysis to divide a sentence into words and detect keywords that indicate negative emotions. The detection unit can also use grammatical analysis to analyze the structure of the sentence and detect negative phrases. Furthermore, the detection unit can use semantic analysis to understand the meaning of the sentence and detect expressions that indicate negative emotions. For example, the detection unit can use morphological analysis to divide the sentence "This product is no good at all" into words and detect the negative keyword "no good". The detection unit can also use grammatical analysis to analyze the structure of the sentence "This product is no good at all" and detect the negative phrase "no good at all". Furthermore, the detection unit can use semantic analysis to understand the meaning of the sentence "This product is no good at all" and detect expressions that indicate negative emotions. In this way, keywords and phrases that indicate negative emotions can be accurately detected by using natural language processing technology.

[0068] The paraphrasing unit can paraphrase the detected negative expression into a positive expression. Positive expressions include, for example, words of encouragement and words of gratitude. For example, the paraphrasing unit can paraphrase the detected expression "This product is no good at all" into a positive expression such as "This product has room for improvement." In addition, the paraphrasing unit can paraphrase the detected expression "This service is the worst" into a positive expression such as "This service needs improvement." In addition, the paraphrasing unit can paraphrase the detected expression "This app is difficult to use" into a positive expression such as "This app has room for improvement." For example, the paraphrasing unit can paraphrase the detected expression "This product is no good at all" into a positive expression such as "This product has room for improvement." In addition, the paraphrasing unit can paraphrase the detected expression "This service is the worst" into a positive expression such as "This service needs improvement." In addition, the paraphrasing unit can paraphrase the detected expression "This app is difficult to use" into a positive expression such as "This app has room for improvement." In this way, by paraphrasing the negative expression into a positive expression, it is possible to prevent the user from having negative emotions.

[0069] The customization unit can perform customization based on the user's past browsing history or feedback. The customization includes, for example, the type of user's preferences and the range of customization. For example, the customization unit can analyze the user's past browsing history, and for a user who is particularly sensitive to a particular keyword, preferentially filter posts containing the keyword. The customization unit can also adjust the tone and style when rephrasing in a positive expression based on the user's feedback. Furthermore, the customization unit can adjust the method of customization based on the user's past browsing history and feedback. For example, the customization unit can analyze the user's past browsing history, and for a user who is particularly sensitive to a particular keyword, preferentially filter posts containing the keyword. The customization unit can also adjust the tone and style when rephrasing in a positive expression based on the user's feedback. Furthermore, the customization unit can adjust the method of customization based on the user's past browsing history and feedback. As a result, by performing customization based on the user's past browsing history and feedback, it is possible to provide information according to the user's preferences.

[0070] The positive surfing system includes a filtering unit that filters out posts including radical statements and refrains from displaying them. The filtering unit filters out posts including radical statements and refrains from displaying them. Radical statements include, for example, violent words and discriminatory words. The filtering unit can, for example, filter out posts including violent words and refrain from displaying them. The filtering unit can also filter out posts including discriminatory words and refrain from displaying them. Furthermore, the filtering unit can filter out posts including radical statements and refrain from displaying them. For example, the filtering unit can filter out posts including violent words and refrain from displaying them. The filtering unit can also filter out posts including discriminatory words and refrain from displaying them. Furthermore, the filtering unit can filter out posts including radical statements and refrain from displaying them. In this way, by filtering out posts including radical statements, it is possible to prevent a user from coming into contact with unpleasant information.

[0071] The positive surfing system includes a training data collection unit that collects a plurality of data to improve the accuracy of the sentiment analysis. The training data collection unit collects a plurality of data to improve the accuracy of the sentiment analysis. The collected data includes, for example, text data, voice data, image data, and the like. The training data collection unit, for example, collects text data and can use it as training data for the sentiment analysis. The training data collection unit can also collect voice data and use it as training data for the sentiment analysis. Furthermore, the training data collection unit can also collect image data and use it as training data for the sentiment analysis. For example, the training data collection unit collects text data and can use it as training data for the sentiment analysis. The training data collection unit can also collect voice data and use it as training data for the sentiment analysis. Furthermore, the training data collection unit can collect image data and use it as training data for the sentiment analysis. This improves the accuracy of the sentiment analysis by collecting a large amount of data.

[0072] The detection unit can estimate the user's emotion and adjust the detection criteria for negative expressions based on the estimated user's emotion. The detection unit estimates the user's emotion using techniques such as facial expression recognition, voice analysis, and text analysis. For example, the detection unit can analyze the user's facial expression data captured by a camera to estimate the user's emotion. The detection unit can also analyze the user's voice data recorded by a microphone to estimate the user's emotion. Furthermore, the detection unit can analyze the text data entered by the user to estimate the user's emotion. For example, the detection unit can analyze the user's facial expression data captured by a camera and detect negative expressions with stricter criteria when the user is stressed. The detection unit can also analyze the user's voice data recorded by a microphone and detect negative expressions with looser criteria when the user is relaxed. Furthermore, the detection unit can analyze the text data entered by the user and adjust the criteria so that the user can detect quickly when the user is in a hurry. This allows more appropriate detection by adjusting the detection criteria for negative expressions according to the user's emotion. The estimation of emotions is realized, for example, by using an emotion estimation function using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0073] The detection unit can improve the detection accuracy of negative expressions by considering the context of the post. The detection unit, for example, analyzes the context before and after the post to determine whether the negative expression really has a negative meaning. For example, the detection unit can analyze the context before and after the post to determine whether the expression "this product is no good at all" really has a negative meaning. The detection unit can also consider the context according to the category of the post (for example, review, comment, etc.). For example, in the case of a product review, the detection unit can detect a negative expression based on a specific keyword. Furthermore, the detection unit can analyze the length and structure of the post and detect a negative expression based on the context. For example, the detection unit can analyze the length and structure of the post to determine whether the expression "this product is no good at all" really has a negative meaning. As a result, the detection accuracy of negative expressions is improved by considering the context of the post.

[0074] The detection unit can apply different detection algorithms depending on the category of the post. For example, in the case of a product review, the detection unit detects negative expressions based on a specific keyword. For example, the detection unit can detect keywords such as "bad" and "worst" in a product review. In addition, the detection unit can also detect negative expressions using sentiment analysis in the case of social media comments. For example, the detection unit can detect expressions showing emotions such as "anger" and "sadness" in social media comments using sentiment analysis. Furthermore, in the case of a news article, the detection unit can also detect negative expressions based on the tone and content of the article. For example, the detection unit can detect negative expressions such as "danger" and "problem" in a news article based on the tone and content of the article. Thereby, by applying different detection algorithms depending on the category of the post, the detection accuracy is improved.

[0075] The detection unit can estimate the user's emotion and adjust the display method of the detection result based on the estimated user's emotion. The detection unit estimates the user's emotion using techniques such as facial expression recognition, voice analysis, and text analysis. For example, the detection unit can analyze the user's facial expression data captured by a camera to estimate the user's emotion. The detection unit can also analyze the user's voice data recorded by a microphone to estimate the user's emotion. Furthermore, the detection unit can analyze the text data entered by the user to estimate the user's emotion. For example, the detection unit can analyze the user's facial expression data captured by a camera and display the detection result simply when the user is feeling stressed. The detection unit can also analyze the user's voice data recorded by a microphone and display detailed detection results when the user is relaxed. Furthermore, the detection unit can analyze the text data entered by the user and display detection results that focus on the main points when the user is in a hurry. This allows the display method of the detection result to be adjusted according to the user's emotion, making it possible to display the detection result in a way that is easy for the user to see. The estimation of emotions is realized, for example, by using an emotion estimation function using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0076] The detection unit can detect negative expressions taking into account the geographical distribution of posts. The detection unit detects, for example, negative expressions frequently used in a specific region. For example, the detection unit can detect negative expressions such as "no good" and "the worst" that are frequently used in a specific region. The detection unit can also detect negative expressions taking into account differences in culture and language between regions. For example, the detection unit can detect negative expressions such as "danger" and "problem" taking into account differences in culture and language between regions. Furthermore, the detection unit can analyze geographical trends to detect negative expressions. For example, the detection unit can analyze geographical trends to detect negative expressions frequently used in a specific region. As a result, by taking into account the geographical distribution of posts, detection that reflects differences in culture and language between regions is possible.

[0077] The detection unit can improve the detection accuracy by referring to related literature of the post. The detection unit, for example, refers to literature related to the post and checks the meaning of negative expressions. For example, the detection unit can refer to academic papers related to the post and check the meaning of negative expressions. The detection unit can also adjust the detection criteria for negative expressions based on the content of the related literature. For example, the detection unit can adjust the detection criteria for negative expressions based on the content of the related literature. Furthermore, the detection unit can detect negative expressions by taking into account the tone and content of the related literature. For example, the detection unit can detect negative expressions by taking into account the tone and content of the related literature. Thereby, the detection accuracy of negative expressions is improved by referring to related literature of the post.

[0078] The paraphrasing unit can estimate the user's emotion and adjust the expression method of the paraphrase based on the estimated user's emotion. The paraphrasing unit estimates the user's emotion using technologies such as facial expression recognition, voice analysis, and text analysis. For example, the paraphrasing unit can analyze the user's facial expression data captured by a camera to estimate the user's emotion. The paraphrasing unit can also analyze the user's voice data recorded by a microphone to estimate the user's emotion. Furthermore, the paraphrasing unit can analyze the text data input by the user to estimate the user's emotion. For example, the paraphrasing unit can analyze the user's facial expression data captured by a camera and paraphrase the user's emotion into a simple and positive expression if the user is feeling stressed. The paraphrasing unit can also analyze the user's voice data recorded by a microphone and paraphrase the user's emotion into a detailed and positive expression if the user is relaxed. Furthermore, the paraphrasing unit can analyze the text data input by the user and paraphrase the user's emotion into a positive expression that can be quickly understood if the user is in a hurry. This allows for more appropriate paraphrasing by adjusting the expression method of the paraphrase according to the user's emotion. The estimation of emotions is realized, for example, by using an emotion estimation function using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0079] The paraphrasing unit can adjust the level of detail of the paraphrase based on the importance of the negative expression. For example, the paraphrasing unit evaluates the importance of the negative expression, and paraphrases the negative expression with high importance into a detailed positive expression. For example, the paraphrasing unit can paraphrase the expression with high importance, "This product is completely useless," into a detailed positive expression, such as "This product has room for improvement." In addition, the paraphrasing unit can also paraphrase the negative expression with low importance into a concise positive expression. For example, the paraphrasing unit can paraphrase the expression with low importance, "This service is the worst," into a concise positive expression, such as "This service needs improvement." In addition, the paraphrasing unit can adjust the tone and style of the paraphrase according to the importance. For example, the paraphrasing unit can paraphrase the negative expression with high importance in a polite and detailed tone, and paraphrase the negative expression with low importance in a concise and direct tone. In this way, by adjusting the level of detail of the paraphrase based on the importance of the negative expression, appropriate paraphrasing is possible.

[0080] The paraphrasing unit can apply different paraphrasing algorithms depending on the category of the post. For example, in the case of a product review, the paraphrasing unit paraphrases the feedback into positive feedback. For example, the paraphrasing unit can paraphrase the expression "this product is no good at all" in the product review into positive feedback such as "this product has room for improvement". In addition, the paraphrasing unit can paraphrase the comment on social media into a more emoting expression. For example, the paraphrasing unit can paraphrase the expression "this service is the worst" in the social media comment into a more emoting expression such as "this service needs improvement". In addition, the paraphrasing unit can paraphrase the comment on news articles into objective and positive expressions. For example, the paraphrasing unit can paraphrase the expression "this event is very problematic" in the news article into an objective and positive expression such as "this event has room for improvement". In this way, the accuracy of paraphrasing is improved by applying different paraphrasing algorithms depending on the category of the post.

[0081] The paraphrasing unit can estimate the user's emotion and adjust the length of the paraphrase based on the estimated user's emotion. The paraphrasing unit estimates the user's emotion using technologies such as facial expression recognition, voice analysis, and text analysis. For example, the paraphrasing unit can analyze the user's facial expression data captured by a camera and estimate the user's emotion. The paraphrasing unit can also analyze the user's voice data recorded by a microphone and estimate the user's emotion. Furthermore, the paraphrasing unit can analyze the text data input by the user and estimate the user's emotion. For example, the paraphrasing unit can analyze the user's facial expression data captured by a camera and perform a short, to-the-point paraphrase if the user is stressed. The paraphrasing unit can also analyze the user's voice data recorded by a microphone and perform a paraphrase including a detailed explanation if the user is relaxed. Furthermore, the paraphrasing unit can analyze the text data input by the user and perform a short paraphrase that can be quickly understood if the user is in a hurry. This allows for more appropriate paraphrasing by adjusting the length of the paraphrase according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0082] The paraphrasing unit can determine the priority of paraphrasing based on the submission time of the post. The paraphrasing unit, for example, prioritizes paraphrasing recent posts. For example, the paraphrasing unit can rephrase an expression such as "this product is no good at all" in a recent post into a positive expression such as "this product has room for improvement." The paraphrasing unit can also prioritize paraphrasing posts related to a specific event or trend. For example, the paraphrasing unit can rephrase an expression such as "this service is the worst" in a post related to a specific event or trend into a positive expression such as "this service needs improvement." The paraphrasing unit can also determine the priority based on the user's past browsing history. For example, the paraphrasing unit can prioritize paraphrase posts containing a specific keyword based on the user's past browsing history. In this way, by determining the priority of paraphrasing based on the submission time of the post, the latest information can be prioritized.

[0083] The paraphrasing unit can adjust the order of paraphrasing based on the relevance of the post. For example, the paraphrasing unit preferentially paraphrases posts related to a topic in which the user is interested. For example, the paraphrasing unit can paraphrase an expression such as "this product is no good at all" in a post related to a topic in which the user is interested, into a positive expression such as "this product has room for improvement." In addition, the paraphrasing unit can preferentially paraphrase when the content of the post includes important information. For example, the paraphrasing unit can paraphrase an expression such as "this service is the worst" into a positive expression such as "this service needs improvement" when the content of the post includes important information. In addition, the paraphrasing unit can adjust the order of paraphrasing based on the relevance of the post. For example, the paraphrasing unit can preferentially paraphrase posts including a specific keyword based on the relevance of the post. In this way, by adjusting the order of paraphrasing based on the relevance of the post, information important to the user can be preferentially paraphrased.

[0084] The customization unit can estimate the user's emotion and adjust the customization method based on the estimated user's emotion. The customization unit estimates the user's emotion using technologies such as facial expression recognition, voice analysis, and text analysis. For example, the customization unit can analyze the user's facial expression data captured by a camera to estimate the user's emotion. The customization unit can also analyze the user's voice data recorded by a microphone to estimate the user's emotion. Furthermore, the customization unit can analyze the text data entered by the user to estimate the user's emotion. For example, the customization unit can analyze the user's facial expression data captured by a camera and provide a simple customization method when the user is stressed. The customization unit can also analyze the user's voice data recorded by a microphone and provide detailed customization options when the user is relaxed. Furthermore, the customization unit can analyze the text data entered by the user and provide a method for quick customization when the user is in a hurry. This allows more appropriate customization by adjusting the customization method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0085] At the time of customization, the customization unit can select an optimal customization method by analyzing the user's past browsing history. The customization unit, for example, analyzes the user's past browsing history and selects an optimal customization method. For example, the customization unit can suggest a customization method based on the content that the user frequently browsed in the past. The customization unit can also analyze the user's past feedback and select an optimal customization method. Furthermore, the customization unit can find a specific pattern from the user's past browsing history and suggest a customization method. For example, the customization unit can suggest a customization method based on the content that the user frequently browsed in the past. The customization unit can also analyze the user's past feedback and select an optimal customization method. Furthermore, the customization unit can find a specific pattern from the user's past browsing history and suggest a customization method. In this way, the optimal customization method can be selected by analyzing the user's past browsing history.

[0086] The customization unit can customize the means of customization based on the user's current field of interest at the time of customization. The customization unit, for example, suggests a customization method based on a topic in which the user is currently interested. For example, the customization unit can rephrase an expression such as "this product is no good at all" into a positive expression such as "this product has room for improvement" based on the topic in which the user is currently interested. The customization unit can also preferentially display information related to the user's current field of interest. For example, the customization unit can preferentially display information related to the topic in which the user is currently interested. Furthermore, the customization unit can adjust the means of customization based on the user's current field of interest. For example, the customization unit can preferentially display posts including a specific keyword based on the topic in which the user is currently interested. This makes it possible to provide more appropriate information by adjusting the means of customization based on the user's current field of interest.

[0087] The customization unit can estimate the user's emotion and determine the priority of customization based on the estimated user's emotion. The customization unit estimates the user's emotion using technologies such as facial expression recognition, voice analysis, and text analysis. For example, the customization unit can analyze the user's facial expression data captured by a camera to estimate the user's emotion. The customization unit can also analyze the user's voice data recorded by a microphone to estimate the user's emotion. Furthermore, the customization unit can analyze the text data entered by the user to estimate the user's emotion. For example, the customization unit can analyze the user's facial expression data captured by a camera and preferentially display important information when the user is stressed. The customization unit can also analyze the user's voice data recorded by a microphone and preferentially display detailed information when the user is relaxed. Furthermore, the customization unit can analyze the text data entered by the user and preferentially display information that can be quickly understood when the user is in a hurry. This enables more appropriate information to be provided by determining the priority of customization according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0088] The customization unit can select an optimal customization method in consideration of the geographical location information of the user at the time of customization. The customization unit, for example, preferentially displays information related to the area where the user is currently located. For example, the customization unit can preferentially display information related to the area where the user is currently located. The customization unit can also analyze geographical trends and suggest an optimal customization method. For example, the customization unit can analyze geographical trends and preferentially display information related to the area where the user is currently located. Furthermore, the customization unit can adjust the means of customization based on the geographical location information of the user. For example, the customization unit can preferentially display information related to the area where the user is currently located. Thereby, by considering the geographical location information of the user, an optimal customization method for each area can be selected.

[0089] The customization unit can analyze the user's social media activities at the time of customization and suggest a means of customization. The customization unit can suggest a customization method based on, for example, topics frequently mentioned by the user on social media. For example, the customization unit can rephrase an expression such as "this product is no good at all" to a positive expression such as "this product has room for improvement" based on topics frequently mentioned by the user on social media. The customization unit can also preferentially display information of interest to the user from the user's social media activities. For example, the customization unit can preferentially display information related to topics frequently mentioned by the user on social media. Furthermore, the customization unit can analyze the user's social media activities and select an optimal customization method. For example, the customization unit can preferentially display posts containing a specific keyword based on topics frequently mentioned by the user on social media. In this way, a more appropriate customization method can be suggested by analyzing the user's social media activities.

[0090] The filtering unit can estimate the user's emotion and adjust the filtering criteria based on the estimated user's emotion. The filtering unit estimates the user's emotion using technologies such as facial expression recognition, voice analysis, and text analysis. For example, the filtering unit can analyze the user's facial expression data captured by a camera and estimate the user's emotion. The filtering unit can also analyze the user's voice data recorded by a microphone and estimate the user's emotion. Furthermore, the filtering unit can analyze the text data entered by the user and estimate the user's emotion. For example, the filtering unit can analyze the user's facial expression data captured by a camera and perform filtering with strict criteria when the user is stressed. The filtering unit can also analyze the user's voice data recorded by a microphone and perform filtering with loose criteria when the user is relaxed. Furthermore, the filtering unit can analyze the text data entered by the user and adjust the criteria so that filtering can be performed quickly when the user is in a hurry. This enables more appropriate filtering by adjusting the filtering criteria according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0091] The filtering unit can improve the accuracy of filtering by considering the context of the post when filtering. For example, the filtering unit can analyze the context before and after the post and determine whether an extreme statement really has an extreme meaning. For example, the filtering unit can analyze the context before and after the post and determine whether the expression "this product is no good at all" really has an extreme meaning. The filtering unit can also consider the context according to the category of the post (for example, review, comment, etc.). For example, in the case of a product review, the filtering unit can filter out extreme expressions based on a specific keyword. Furthermore, the filtering unit can analyze the length and structure of the post and filter out extreme expressions based on the context. For example, the filtering unit can analyze the length and structure of the post and determine whether the expression "this product is no good at all" really has an extreme meaning. In this way, the accuracy of filtering is improved by considering the context of the post.

[0092] The filtering unit can estimate the user's emotion and adjust the order of displaying the filtering results based on the estimated user's emotion. The filtering unit estimates the user's emotion using technologies such as facial expression recognition, voice analysis, and text analysis. For example, the filtering unit can analyze the user's facial expression data captured by a camera to estimate the user's emotion. The filtering unit can also analyze the user's voice data recorded by a microphone to estimate the user's emotion. Furthermore, the filtering unit can analyze the text data entered by the user to estimate the user's emotion. For example, the filtering unit can analyze the user's facial expression data captured by a camera and preferentially display important information when the user is stressed. The filtering unit can also analyze the user's voice data recorded by a microphone and preferentially display detailed information when the user is relaxed. Furthermore, the filtering unit can analyze the text data entered by the user and preferentially display information that can be quickly understood when the user is in a hurry. This makes it possible to provide more appropriate information by adjusting the order of displaying the filtering results according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0093] The filtering unit can perform filtering while taking into consideration the geographical distribution of posts. The filtering unit, for example, filters out extreme expressions that are frequently used in a specific region. For example, the filtering unit can filter out extreme expressions such as "no good" and "the worst" that are frequently used in a specific region. The filtering unit can also perform filtering while taking into consideration differences in culture and language between regions. For example, the filtering unit can filter out extreme expressions such as "danger" and "problem" while taking into consideration differences in culture and language between regions. Furthermore, the filtering unit can analyze geographical trends and filter out extreme expressions. For example, the filtering unit can analyze geographical trends and filter out extreme expressions that are frequently used in a specific region. As a result, filtering that reflects differences in culture and language between regions is possible by taking into consideration the geographical distribution of posts.

[0094] The training data collection unit can estimate the user's emotion and select training data based on the estimated user's emotion. The training data collection unit estimates the user's emotion using, for example, techniques such as facial expression recognition, voice analysis, and text analysis. For example, the training data collection unit can analyze the user's facial expression data captured by a camera and estimate the user's emotion. The training data collection unit can also analyze the user's voice data recorded by a microphone and estimate the user's emotion. Furthermore, the training data collection unit can analyze the text data entered by the user and estimate the user's emotion. For example, the training data collection unit can analyze the user's facial expression data captured by a camera, and when the user is feeling stressed, can preferentially collect data for reducing stress. Furthermore, the training data collection unit can analyze the user's voice data recorded by a microphone, and when the user is relaxed, can preferentially collect data for maintaining relaxation. Furthermore, the training data collection unit can analyze the text data entered by the user, and when the user is in a hurry, can preferentially collect data that can be collected quickly. This allows more appropriate data collection by selecting training data according to the user's emotion. The estimation of emotions is realized, for example, by using an emotion estimation function using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0095] The training data collection unit can optimize the collection algorithm by referring to past data when collecting training data. The training data collection unit, for example, selects an optimal collection algorithm based on data collected in the past. For example, the training data collection unit can select an optimal collection algorithm based on text data collected in the past. The training data collection unit can also analyze trends in past data and adjust the collection algorithm. For example, the training data collection unit can analyze trends in past text data and adjust the collection algorithm. Furthermore, the training data collection unit can evaluate the quality of past data and optimize the collection algorithm. For example, the training data collection unit can evaluate the quality of past text data and optimize the collection algorithm. Thereby, by referring to past data, the collection algorithm can be optimized, enabling more efficient data collection.

[0096] The training data collection unit can estimate the user's emotion and adjust the collection frequency of the training data based on the estimated user's emotion. The training data collection unit estimates the user's emotion using techniques such as facial expression recognition, voice analysis, and text analysis. For example, the training data collection unit can analyze the user's facial expression data captured by a camera to estimate the user's emotion. The training data collection unit can also analyze the user's voice data recorded by a microphone to estimate the user's emotion. Furthermore, the training data collection unit can analyze the text data entered by the user to estimate the user's emotion. For example, the training data collection unit can analyze the user's facial expression data captured by a camera, and when the user is feeling stressed, the training data collection unit can frequently collect data to improve the accuracy of the emotion analysis. The training data collection unit can also analyze the user's voice data recorded by a microphone, and when the user is relaxed, collect data at an appropriate frequency. Furthermore, the training data collection unit can analyze the text data entered by the user, and adjust the frequency so that data can be collected quickly when the user is in a hurry. This allows more appropriate data collection by adjusting the collection frequency of the training data according to the user's emotion. The estimation of emotions is realized, for example, by using an emotion estimation function using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0097] The training data collection unit can weight data based on the submission time of the post when collecting training data. The training data collection unit, for example, preferentially collects recent posts and weights the data. For example, the training data collection unit can preferentially collect data including an expression such as "this product is no good at all" in recent posts and weight the data. The training data collection unit can also preferentially collect posts related to a specific event or trend and weight the data. For example, the training data collection unit can preferentially collect data including an expression such as "this service is the worst" in posts related to a specific event or trend and weight the data. Furthermore, the training data collection unit can weight data based on the user's past browsing history. For example, the training data collection unit can preferentially collect data including a specific keyword based on the user's past browsing history and weight the data. As a result, the latest information can be preferentially collected by weighting the data based on the submission time of the post.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The positive surfing system may further include an emotion filtering unit that estimates the user's emotion and adjusts the filtering criteria based on the estimated emotion. For example, when the user is stressed, the emotion filtering unit may filter out negative expressions with stricter criteria. When the user is relaxed, the emotion filtering unit may filter with looser criteria. Furthermore, when the user is in a hurry, the criteria may be adjusted to allow for quick filtering. This allows for more appropriate information to be provided by adjusting the filtering criteria according to the user's emotion.

[0100] The positive surfing system can further include a history analysis unit that analyzes the user's past browsing history and, for a user who is particularly sensitive to a particular keyword, preferentially filters out posts that include that keyword. For example, if a user has shown a strong reaction to the keyword "no" in the past, the history analysis unit can preferentially filter out posts that include that keyword. In addition, the tone and style of rephrasing in a positive way can be adjusted based on the user's feedback. Furthermore, the method of customization can be adjusted based on the user's past browsing history and feedback. This makes it possible to provide information according to the user's preferences by customizing based on the user's past browsing history and feedback.

[0101] The positive surfing system may further include an emotion paraphrasing unit that estimates the emotion of the user and adjusts the manner of paraphrasing based on the estimated emotion. For example, if the user is stressed, the emotion paraphrasing unit may paraphrase the message into a simple and positive expression. If the user is relaxed, the emotion paraphrasing unit may paraphrase the message into a detailed and positive expression. If the user is in a hurry, the emotion paraphrasing unit may paraphrase the message into a positive expression that can be quickly understood. This allows for more appropriate paraphrasing by adjusting the manner of paraphrasing according to the emotion of the user.

[0102] The positive surfing system may further include an interest field customization unit that adjusts the means of customization based on the user's current field of interest. For example, the expression "this product is no good at all" may be rephrased as a positive expression such as "this product has room for improvement" based on the topic in which the user is currently interested. Also, information related to the user's current field of interest may be preferentially displayed. Furthermore, posts containing specific keywords may be preferentially displayed based on the user's current field of interest. This allows more appropriate information to be provided by adjusting the means of customization based on the user's current field of interest.

[0103] The positive surfing system may further include an emotion display unit that estimates the emotion of the user and adjusts the order in which the filtering results are displayed based on the estimated emotion. For example, when the user is feeling stressed, the emotion display unit may prioritize displaying important information. When the user is relaxed, the emotion display unit may prioritize displaying detailed information. When the user is in a hurry, the emotion display unit may prioritize displaying information that can be quickly understood. This allows more appropriate information to be provided by adjusting the order in which the filtering results are displayed based on the emotion of the user.

[0104] The positive surfing system may further include a geographic detection unit that detects negative expressions taking into account the geographic distribution of posts. For example, negative expressions that are frequently used in a particular region may be detected. In addition, negative expressions may be detected taking into account differences in culture and language between regions. Furthermore, negative expressions may be detected by analyzing geographic trends. In this way, by taking into account the geographic distribution of posts, detection that reflects differences in culture and language between regions is possible.

[0105] The positive surfing system may further include an emotion data selection unit that estimates the user's emotion and selects training data based on the estimated emotion. For example, if the user is feeling stressed, the emotion data selection unit may preferentially collect data for reducing stress. Also, if the user is relaxed, the emotion data selection unit may preferentially collect data for maintaining relaxation. Furthermore, if the user is in a hurry, the emotion data selection unit may preferentially collect data that can be collected quickly. This allows for more appropriate data collection by selecting training data according to the user's emotion.

[0106] The positive surfing system may further include a literature reference unit that improves the detection accuracy by referring to related literature of the post. For example, the meaning of negative expressions may be confirmed by referring to academic papers related to the post. In addition, the detection criteria for negative expressions may be adjusted based on the contents of the related literature. Furthermore, negative expressions may be detected by taking into account the tone and contents of the related literature. In this way, the detection accuracy of negative expressions is improved by referring to related literature of the post.

[0107] The positive surfing system may further include an emotion customization unit that estimates the user's emotion and determines the priority of customization based on the estimated emotion. For example, when the user is feeling stressed, the emotion customization unit may prioritize displaying important information. When the user is relaxed, the emotion customization unit may prioritize displaying detailed information. When the user is in a hurry, the emotion customization unit may prioritize displaying information that can be quickly understood. In this way, by determining the priority of customization according to the user's emotion, more appropriate information can be provided.

[0108] The positive surfing system may further include a submission time weighting unit that weights data based on the submission time of the post. For example, recent posts may be collected and weighted preferentially. Also, posts related to a particular event or trend may be collected and weighted preferentially. Furthermore, data may be weighted based on the user's past browsing history. Thus, by weighting data based on the submission time of the post, the latest information may be collected preferentially.

[0109] The process flow of the second embodiment will be briefly described below.

[0110] Step 1: The detection unit detects negative expressions. The detection unit uses natural language processing techniques to detect keywords and phrases that indicate negative emotions. For example, it can detect offensive or insulting words. Step 2: The paraphrasing unit paraphrases the negative expressions detected by the detection unit into positive expressions. For example, the expression "This product is completely no good" can be paraphrased into a positive expression such as "This product has room for improvement." Step 3: The customization unit customizes the information paraphrased by the paraphrasing unit according to the user's preferences. The customization unit performs customization based on the user's past browsing history and feedback. For example, for a user who is particularly sensitive to a particular keyword, posts containing that keyword can be preferentially filtered.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] Each of the multiple elements including the above-mentioned detection unit, paraphrasing unit, customization unit, filtering unit, and training data collection unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the detection unit is realized by the control unit 46A of the smart device 14 and detects negative expressions. The paraphrasing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and paraphrases the detected negative expressions into positive expressions. The customization unit is realized, for example, by the control unit 46A of the smart device 14 and customizes information according to the user's preferences. The filtering unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and filters posts containing extreme statements. The training data collection unit is realized, for example, by the control unit 46A of the smart device 14 and collects multiple data to improve the accuracy of emotion analysis. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] Each of the multiple elements including the above-mentioned detection unit, paraphrasing unit, customization unit, filtering unit, and training data collection unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the detection unit is realized by the control unit 46A of the smart glasses 214 and detects negative expressions. The paraphrasing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and paraphrases the detected negative expressions into positive expressions. The customization unit is realized, for example, by the control unit 46A of the smart glasses 214 and customizes information according to the user's preferences. The filtering unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and filters posts containing extreme statements. The training data collection unit is realized, for example, by the control unit 46A of the smart glasses 214 and collects multiple data to improve the accuracy of emotion analysis. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] Each of the multiple elements including the above-mentioned detection unit, paraphrasing unit, customization unit, filtering unit, and training data collection unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the detection unit is realized by the control unit 46A of the headset type terminal 314, and detects negative expressions. The paraphrasing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and paraphrases the detected negative expressions into positive expressions. The customization unit is realized, for example, by the control unit 46A of the headset type terminal 314, and customizes information according to the user's preferences. The filtering unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and filters posts containing extreme statements. The training data collection unit is realized, for example, by the control unit 46A of the headset type terminal 314, and collects multiple data to improve the accuracy of emotion analysis. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] 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.

[0150] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] Each of the multiple elements including the above-mentioned detection unit, paraphrasing unit, customization unit, filtering unit, and training data collection unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the detection unit is realized by the control unit 46A of the robot 414 and detects negative expressions. The paraphrasing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and paraphrases the detected negative expressions into positive expressions. The customization unit is realized, for example, by the control unit 46A of the robot 414 and customizes information according to the user's preferences. The filtering unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and filters posts containing extreme statements. The training data collection unit is realized, for example, by the control unit 46A of the robot 414 and collects multiple data to improve the accuracy of emotion analysis. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0164] 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.

[0165] 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.

[0166] These emotions are distributed in the three 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.

[0167] 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 you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] 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.

[0169] 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."

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] (Appendix 1) A detection unit that detects negative expressions; a paraphrase unit that paraphrases the negative expressions detected by the detection unit into positive expressions; A customization unit that customizes the information paraphrased by the paraphrase unit according to a user's preference. A system characterized by: (Appendix 2) The detection unit is Uses natural language processing techniques to detect keywords or phrases that indicate negative sentiment 2. The system of claim 1, (Appendix 3) The rephrasing unit is Rephrasing detected negative expressions into positive ones 2. The system of claim 1, (Appendix 4) The customization unit includes: Customize based on user's past browsing history or feedback 2. The system of claim 1, (Appendix 5) Equipped with a filtering section that filters out posts containing extreme statements and refrains from displaying them 2. The system of claim 1, (Appendix 6) Equipped with a training data collection section that collects multiple data to improve the accuracy of sentiment analysis 2. The system of claim 1, (Appendix 7) The detection unit is Estimate the user's emotions and adjust the criteria for detecting negative expressions based on the estimated user emotions. 2. The system of claim 1, (Appendix 8) The detection unit is Improve detection of negative comments by considering the context of posts 2. The system of claim 1, (Appendix 9) The detection unit is Apply different detection algorithms depending on the post category 2. The system of claim 1, (Appendix 10) The detection unit is Infer user emotions and adjust the way detection results are displayed based on the estimated user emotions 2. The system of claim 1, (Appendix 11) The detection unit is Detecting negative comments by considering the geographic distribution of posts 2. The system of claim 1, (Appendix 12) The detection unit is Improve detection accuracy by referring to related literature in the post 2. The system of claim 1, (Appendix 13) The rephrasing unit is Estimate the user's emotions and adjust the way the paraphrases are expressed based on the estimated user's emotions. 2. The system of claim 1, (Appendix 14) The rephrasing unit is Adjust the detail of the paraphrase based on the importance of the negative expression 2. The system of claim 1, (Appendix 15) The rephrasing unit is Apply different rephrasing algorithms depending on the post category 2. The system of claim 1, (Appendix 16) The rephrasing unit is Estimate user's emotions and adjust the length of the paraphrase based on the estimated user's emotions 2. The system of claim 1, (Appendix 17) The rephrasing unit is Prioritize paraphrases based on when posts were submitted 2. The system of claim 1, (Appendix 18) The rephrasing unit is Adjust the order of paraphrases based on the relevance of the post 2. The system of claim 1, (Appendix 19) The customization unit includes: Inferring a user's emotions and adjusting the customization method based on the inferred user's emotions 2. The system of claim 1, (Appendix 20) The customization unit includes: When customizing, analyze the user's past browsing history to select the optimal customization method. 2. The system of claim 1, (Appendix 21) The customization unit includes: During customization, customize the customization experience based on the user's current interests 2. The system of claim 1, (Appendix 22) The customization unit includes: To estimate a user's emotion and determine a priority of customization based on the estimated user's emotion. 2. The system of claim 1, (Appendix 23) The customization unit includes: During customization, select the optimal customization method by taking into account the user's geographic location information 2. The system of claim 1, (Appendix 24) The customization unit includes: When customizing, analyze users' social media activity to suggest customization options 2. The system of claim 1, (Appendix 25) The filtering unit is Inferring a user's emotions and adjusting filtering criteria based on the estimated user's emotions 2. The system of claim 1, (Appendix 26) The filtering unit is When filtering, consider the context of the post to improve filtering accuracy 2. The system of claim 1, (Appendix 27) The filtering unit is Infer user emotion and adjust the order in which filtering results are displayed based on the estimated user emotion 2. The system of claim 1, (Appendix 28) The filtering unit is When filtering, take into account the geographic distribution of posts. 2. The system of claim 1, (Appendix 29) The training data collection unit includes: Estimate the user's emotions and select training data based on the estimated user emotions. 2. The system of claim 1, (Appendix 30) The training data collection unit includes: When collecting training data, reference past data to optimize the collection algorithm 2. The system of claim 1, (Appendix 31) The training data collection unit includes: Inferring a user's emotion and adjusting the frequency of training data collection based on the estimated user's emotion. 2. The system of claim 1, (Appendix 32) The training data collection unit includes: When collecting training data, we weight the data based on when the post was submitted 2. The system of claim 1, [Explanation of symbols]

[0183] 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 detection unit that detects negative expressions; a paraphrase unit that paraphrases the negative expressions detected by the detection unit into positive expressions; A customization unit that customizes the information paraphrased by the paraphrase unit according to a user's preference. A system characterized by:

2. The detection unit is Uses natural language processing techniques to detect keywords or phrases that indicate negative sentiment 2. The system of claim 1 .

3. The customization unit includes: Customize based on user's past browsing history or feedback 2. The system of claim 1 .

4. Equipped with a filtering section that filters out posts containing extreme statements and refrains from displaying them 2. The system of claim 1 .

5. Equipped with a training data collection section that collects multiple data to improve the accuracy of sentiment analysis 2. The system of claim 1 .

6. The detection unit is Estimate the user's emotions and adjust the criteria for detecting negative expressions based on the estimated user emotions.

2. The system of claim 1 .

7. The detection unit is Improve detection of negative comments by considering the context of posts 2. The system of claim 1 .

8. The detection unit is Apply different detection algorithms depending on the post category 2. The system of claim 1 .

Images