system

Abstract

The system of the embodiment aims to automatically exclude similar proposals in generative AI contests and achieve efficient operation. [Solution] A system according to an embodiment includes an input unit, a vectorization unit, a similarity calculation unit, an exclusion unit, and an improvement unit. The input unit inputs suggestions as text. The vectorization unit vectorizes the suggestions input by the input unit. The similarity calculation unit calculates the similarity of the suggestions vectorized by the vectorization unit. The exclusion unit detects and excludes similar suggestions based on the similarity calculated by the similarity calculation unit, using a specific threshold as a criterion. The improvement unit receives feedback on the suggestions excluded by the exclusion unit and improves the algorithm.

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, manually filtering out similar proposals in generative AI contests was cumbersome, making it difficult to run efficiently.

[0005] The system of the embodiment aims to automatically exclude similar proposals in generative AI contests and achieve efficient operation. [Means for solving the problem]

[0006] The system according to the embodiment includes an input unit, a vectorization unit, a similarity calculation unit, an exclusion unit, and an improvement unit. The input unit inputs suggestions as text. The vectorization unit vectorizes the suggestions input by the input unit. The similarity calculation unit calculates the similarity of the suggestions vectorized by the vectorization unit. The exclusion unit detects and excludes similar suggestions based on the similarity calculated by the similarity calculation unit, using a specific threshold as a criterion. The improvement unit receives feedback on the suggestions excluded by the exclusion unit and improves the algorithm. [Effects of the Invention]

[0007] The system according to the embodiment can automatically exclude similar proposals in a generative AI contest, thereby achieving efficient operation. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

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

[0028] (Example 1) A system according to an embodiment of the present invention automatically excludes similar proposals in a generative AI contest. This system inputs proposals as text, vectorizes them using natural language processing technology, and calculates the similarity of the vectorized proposals using machine learning technology. Similar proposals are detected and excluded based on a set threshold. Feedback is then received while the algorithm is improved to improve accuracy. For example, a proposal is input as text. A detailed description of the proposal is required. For example, text including the purpose, method, and effects of the proposal is entered. This text is vectorized using natural language processing technology. Vectorization is the conversion of text into numerical data, which enables numerical comparison of the proposal contents. Next, machine learning technology is used to calculate the similarity of the vectorized proposals. A common similarity calculation method is used to calculate the similarity. This allows the similarity between proposals to be numerically evaluated. Highly similar proposals are detected and excluded based on a set threshold. For example, by configuring the system to exclude highly similar proposals, duplicate and similar proposals can be effectively eliminated. Feedback is then received while the algorithm is improved to improve accuracy. Feedback refers to evaluation of the results of proposal elimination and instructions for correction. For example, if a rejected proposal actually has different content, that information can be fed back to the algorithm to improve the accuracy of elimination in future contests. This allows contest organizers to receive more diverse proposals. This makes it easier for the system to reduce duplicate and similar proposals in generative AI contests, allowing for more diverse proposals. For example, it makes it possible to prevent multiple submissions of similar ideas and select proposals with a high level of originality. It also improves the efficiency of proposal evaluation and selection, allowing contests to run more smoothly.

[0029] A proposal exclusion system according to an embodiment includes an input unit, a vectorization unit, a similarity calculation unit, an exclusion unit, and an improvement unit. The input unit inputs proposals as text. Proposals include, but are not limited to, business proposals, technical proposals, and idea proposals. The input unit allows, for example, a user to input proposals through a dedicated interface. The input unit can also allow a user to input proposals using voice input or image input. The vectorization unit vectorizes the proposals input by the input unit using natural language processing technology. Vectorization, for example, converts text into numerical data, thereby enabling the contents of proposals to be compared numerically. The vectorization unit performs vectorization using algorithms such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec. The vectorization unit can also apply different vectorization algorithms depending on the category of the proposal. The similarity calculation unit calculates the similarity of the proposals vectorized by the vectorization unit. The similarity is calculated using, for example, cosine similarity or Euclidean distance, but is not limited to these examples. The similarity calculation unit calculates the similarity between proposals using, for example, cosine similarity. The similarity calculation unit can also improve the accuracy of the similarity calculation by taking into account the interrelationships between proposals. The exclusion unit detects and excludes similar proposals based on the similarity calculated by the similarity calculation unit, using a set threshold as a criterion. The exclusion unit can effectively exclude duplicate or similar proposals, for example, by setting the exclusion unit to exclude proposals with high similarity. The exclusion unit can also exclude proposals by taking into account attribute information of the submitters of the proposals. The improvement unit receives feedback on the proposals excluded by the exclusion unit and improves the algorithm. The improvement unit, for example, retrains the machine learning model or adjusts parameters based on the feedback. The improvement unit can also optimize the improved algorithm by referring to past user feedback. As a result, the proposal exclusion system according to the embodiment can automatically perform processes from proposal input to similarity calculation, exclusion, and algorithm improvement based on feedback.For example, a proposal exclusion system can automatically perform everything from inputting proposals to calculating similarity, exclusion, and improving the algorithm through feedback.

[0030] The input unit can analyze the user's past proposal history and select an appropriate input method. For example, the input unit can automatically display as candidates proposal formats that the user has frequently used in the past. The input unit can also prioritize and suggest input methods (voice, text, etc.) that the user has used in the past. The input unit can also predict and suggest an input method to be used in a specific time period based on the user's past proposal history. This allows for the efficient input of proposals by selecting the optimal input method based on the user's past proposal history. Some or all of the above-mentioned processing in the input unit can be performed using, for example, AI, or can be performed without using AI. For example, the input unit can input the user's past proposal history data into a generation AI and cause the generation AI to select the optimal input method.

[0031] When inputting suggestions, the input unit can filter the suggestions based on the user's current project or areas of interest. For example, the input unit prioritizes input of suggestions related to the project the user is currently working on. The input unit can also automatically filter related suggestions based on the user's areas of interest. The input unit can also input optimal suggestions by referring to the user's past project history. In this way, by filtering the suggestions based on the user's current project or areas of interest, highly relevant suggestions can be input. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's project data to the generation AI and cause the generation AI to filter relevant suggestions.

[0032] When inputting a suggestion, the input unit can select an appropriate input means depending on the user's input method (voice, text, image, etc.). For example, when the user inputs a suggestion by voice, the input unit converts it into text using voice recognition technology. Furthermore, when the user inputs a suggestion by text, the input unit can also provide an input assistance function. Furthermore, when the user inputs a suggestion by image, the input unit can also convert it into text using image recognition technology. This makes the input of suggestions more efficient by selecting the optimal input means depending on the user's input method. Some or all of the above-mentioned processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input voice data to a generation AI and have the generation AI convert the voice data into text data.

[0033] When inputting suggestions, the input unit can prioritize inputting highly relevant suggestions by taking into account the user's geographical location information. For example, if the user is in a specific area, the input unit prioritizes inputting suggestions related to that area. The input unit can also prioritize inputting suggestions related to locations close to the user's current location. The input unit can also prioritize inputting highly relevant suggestions by referring to the user's past location information. This makes the input of suggestions more efficient by prioritizing highly relevant suggestions by taking into account the user's geographical location information. Some or all of the above-described processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the user's geographical location information to the generation AI and cause the generation AI to select highly relevant suggestions.

[0034] When inputting suggestions, the input unit can analyze the user's social media activity and input related suggestions. The input unit can input related suggestions based on, for example, content shared by the user on social media. The input unit can also analyze the user's social media activity history and input related suggestions. The input unit can also input related suggestions with reference to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity and inputting related suggestions, the input of suggestions is made more efficient. Some or all of the above-mentioned processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's social media data to the generation AI and cause the generation AI to select related suggestions.

[0035] When inputting a suggestion, the input unit can customize the input method by reflecting the user's past feedback. The input unit customizes the input interface, for example, based on feedback provided by the user in the past. The input unit can also optimize the input procedure by referring to the user's past feedback. The input unit can also improve the input method by reflecting the user's feedback. In this way, customizing the input method by reflecting the user's past feedback makes the input of suggestions more efficient. Some or all of the above-mentioned processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's feedback data to the generation AI and cause the generation AI to customize the input method.

[0036] The vectorization unit can adjust the level of detail of the vectorization based on the importance of the proposal during vectorization. For example, the vectorization unit performs detailed vectorization on proposals with high importance. The vectorization unit can also perform simplified vectorization on proposals with low importance. The vectorization unit can also adjust the accuracy of the vectorization according to the importance of the proposal. This allows for efficient vectorization by adjusting the level of detail of the vectorization according to the importance of the proposal. Some or all of the above-described processing in the vectorization unit may be performed using, or without, AI, for example. For example, the vectorization unit can input proposal importance data to the generation AI and cause the generation AI to adjust the level of detail of the vectorization.

[0037] During vectorization, the vectorization unit can apply an appropriate vectorization algorithm depending on the category of the proposal. For example, the vectorization unit applies a vectorization algorithm that emphasizes technical terminology to a technical proposal. The vectorization unit can also apply a vectorization algorithm that emphasizes business terminology to a business proposal. The vectorization unit can also select an optimal vectorization algorithm depending on the category of the proposal. This improves the accuracy of vectorization by applying the optimal vectorization algorithm depending on the category of the proposal. Some or all of the above-described processing in the vectorization unit may be performed using, for example, AI, or may be performed without using AI. For example, the vectorization unit can input proposal category data to a generation AI and cause the generation AI to select an optimal vectorization algorithm.

[0038] During vectorization, the vectorization unit can improve the accuracy of vectorization by referring to the user's past vectorization results. The vectorization unit, for example, analyzes the user's past vectorization results to improve accuracy. The vectorization unit can also select an optimal vectorization algorithm based on the user's past vectorization results. The vectorization unit can also adjust vectorization parameters by referring to the user's past vectorization results. This improves the accuracy of vectorization by referring to the user's past vectorization results. Some or all of the above-described processing in the vectorization unit may be performed using, for example, AI, or may be performed without using AI. For example, the vectorization unit can input the user's past vectorization result data into the generation AI and cause the generation AI to improve the accuracy of vectorization.

[0039] During vectorization, the vectorization unit can determine the priority of vectorization based on the submission time of the proposal. For example, the vectorization unit prioritizes vectorization of proposals submitted more recently. The vectorization unit can also postpone vectorization of proposals submitted earlier. The vectorization unit can also adjust the priority of vectorization based on the submission time of the proposal. This allows for efficient vectorization by determining the priority of vectorization based on the submission time of the proposal. Some or all of the above-described processing in the vectorization unit may be performed using, or without, AI, for example. For example, the vectorization unit can input proposal submission time data into the generation AI and have the generation AI determine the priority of vectorization.

[0040] The vectorization unit can adjust the order of vectorization based on the relevance of the proposal during vectorization. For example, the vectorization unit prioritizes vectorization of proposals with high relevance. The vectorization unit can also postpone vectorization of proposals with low relevance. The vectorization unit can also adjust the order of vectorization based on the relevance of the proposal. As a result, efficient vectorization can be achieved by adjusting the order of vectorization based on the relevance of the proposal. Some or all of the above-described processing in the vectorization unit may be performed using, or without, AI, for example. For example, the vectorization unit can input the relevance data of the proposal to the generation AI and cause the generation AI to adjust the order of vectorization.

[0041] During vectorization, the vectorization unit can adjust the use of technical terminology in the vectorization according to the user's level of expertise. For example, if the user's level of expertise is high, the vectorization unit can perform vectorization that makes extensive use of technical terminology. Furthermore, if the user's level of expertise is low, the vectorization unit can also perform vectorization that avoids technical terminology. Furthermore, the vectorization unit can adjust the use of technical terminology in the vectorization according to the user's level of expertise. This allows for more appropriate vectorization by adjusting the use of technical terminology in the vectorization according to the user's level of expertise. Some or all of the above-described processing in the vectorization unit may be performed using, or without, AI, for example. For example, the vectorization unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0042] The similarity calculation unit can improve the accuracy of the similarity calculation by taking into account the interrelationships of the proposals when calculating the similarity. For example, the similarity calculation unit analyzes the interrelationships of the proposals to improve the accuracy of the similarity calculation. The similarity calculation unit can also select an optimal similarity calculation algorithm based on the interrelationships of the proposals. The similarity calculation unit can also adjust parameters for the similarity calculation by taking into account the interrelationships of the proposals. In this way, the accuracy of the similarity calculation is improved by taking into account the interrelationships of the proposals. Some or all of the above-mentioned processing in the similarity calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the similarity calculation unit can input proposal interrelationship data into the generation AI and cause the generation AI to improve the accuracy of the similarity calculation.

[0043] The similarity calculation unit can perform the similarity calculation taking into account the attribute information of the proposal submitter. The similarity calculation unit performs the similarity calculation taking into account, for example, the expertise level of the proposal submitter. The similarity calculation unit can also perform the similarity calculation by referring to the proposal submitter's past proposal history. The similarity calculation unit can also adjust the parameters of the similarity calculation based on the attribute information of the proposal submitter. This improves the accuracy of the similarity calculation by taking into account the attribute information of the proposal submitter. Some or all of the above-mentioned processing in the similarity calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the similarity calculation unit can input attribute information data of the proposal submitter to the generation AI and have the generation AI perform the similarity calculation.

[0044] The similarity calculation unit can weight the similarity calculation based on the frequency of proposal submission when calculating the similarity. For example, the similarity calculation unit prioritizes proposals with a high submission frequency in the similarity calculation. The similarity calculation unit can also postpone proposals with a low submission frequency. The similarity calculation unit can also adjust the weighting of the similarity calculation based on the frequency of proposal submission. In this way, weighting the similarity calculation based on the frequency of proposal submission enables efficient similarity calculation. Some or all of the above-mentioned processing in the similarity calculation unit may be performed using AI, for example, or may be performed without using AI. For example, the similarity calculation unit can input proposal submission frequency data to a generation AI and cause the generation AI to perform weighting in the similarity calculation.

[0045] The similarity calculation unit can perform the similarity calculation taking into account the geographical distribution of the proposals. For example, the similarity calculation unit analyzes the geographical distribution of the proposals to improve the accuracy of the similarity calculation. The similarity calculation unit can also select an optimal similarity calculation algorithm based on the geographical distribution of the proposals. The similarity calculation unit can also adjust parameters for the similarity calculation taking into account the geographical distribution of the proposals. In this way, the accuracy of the similarity calculation is improved by taking the geographical distribution of the proposals into account. Some or all of the above-mentioned processing in the similarity calculation unit can be performed using, for example, AI, or can be performed without using AI. For example, the similarity calculation unit can input geographical distribution data of the proposals to a generation AI and have the generation AI perform the similarity calculation.

[0046] The similarity calculation unit can improve the accuracy of the similarity calculation by referring to the proposed related literature when calculating the similarity. The similarity calculation unit can, for example, analyze the proposed related literature to improve the accuracy of the similarity calculation. The similarity calculation unit can also select an optimal similarity calculation algorithm based on the proposed related literature. The similarity calculation unit can also adjust parameters for the similarity calculation by referring to the proposed related literature. In this way, the accuracy of the similarity calculation is improved by referring to the proposed related literature. Some or all of the above-mentioned processing in the similarity calculation unit can be performed using, for example, AI, or can be performed without using AI. For example, the similarity calculation unit can input the proposed related literature data into a generation AI and have the generation AI perform the similarity calculation.

[0047] The similarity calculation unit can calculate the similarity taking into account the market value of the proposal when calculating the similarity. The similarity calculation unit, for example, analyzes the market value of the proposal and improves the accuracy of the similarity calculation. The similarity calculation unit can also select an optimal similarity calculation algorithm based on the market value of the proposal. The similarity calculation unit can also adjust the parameters of the similarity calculation taking into account the market value of the proposal. In this way, by taking the market value of the proposal into account, the accuracy of the similarity calculation is improved. Some or all of the above-mentioned processing in the similarity calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the similarity calculation unit can input market value data of the proposal to the generation AI and have the generation AI perform the similarity calculation.

[0048] The exclusion unit can improve the accuracy of exclusion by taking into account the interrelationships between proposals when excluding proposals. For example, the exclusion unit analyzes the interrelationships between proposals and improves the accuracy of exclusion. The exclusion unit can also select an optimal exclusion algorithm based on the interrelationships between proposals. The exclusion unit can also adjust exclusion parameters by taking into account the interrelationships between proposals. In this way, the accuracy of exclusion is improved by taking into account the interrelationships between proposals. Some or all of the above-described processing in the exclusion unit may be performed using AI, for example, or may be performed without using AI. For example, the exclusion unit can input interrelationship data between proposals into the generation AI and cause the generation AI to improve the accuracy of exclusion.

[0049] The exclusion unit can perform exclusion by taking into consideration attribute information of the proposal submitter. For example, the exclusion unit can perform exclusion by taking into consideration the expertise level of the proposal submitter. The exclusion unit can also perform exclusion by referring to the proposal submitter's past proposal history. The exclusion unit can also adjust exclusion parameters based on the attribute information of the proposal submitter. In this way, the accuracy of exclusion is improved by taking into consideration the attribute information of the proposal submitter. Some or all of the above-mentioned processing in the exclusion unit can be performed using AI, for example, or can be performed without using AI. For example, the exclusion unit can input attribute information data of the proposal submitter into the generation AI and have the generation AI perform the exclusion.

[0050] The exclusion unit can weight the exclusion based on the frequency of proposal submission at the time of exclusion. For example, the exclusion unit prioritizes exclusion of proposals with a high submission frequency. The exclusion unit can also postpone exclusion of proposals with a low submission frequency. The exclusion unit can also adjust the weight of exclusion based on the frequency of proposal submission. In this way, by weighting the exclusion based on the frequency of proposal submission, efficient proposal exclusion can be performed. Some or all of the above-described processing in the exclusion unit may be performed using AI, for example, or may be performed without using AI. For example, the exclusion unit can input proposal submission frequency data into the generation AI and cause the generation AI to perform the weighting of exclusion.

[0051] The exclusion unit can perform exclusion taking into account the geographic distribution of the proposals. For example, the exclusion unit analyzes the geographic distribution of the proposals to improve the accuracy of exclusion. The exclusion unit can also select an optimal exclusion algorithm based on the geographic distribution of the proposals. The exclusion unit can also adjust exclusion parameters taking into account the geographic distribution of the proposals. In this way, the accuracy of exclusion is improved by taking the geographic distribution of the proposals into account. Some or all of the above-mentioned processing in the exclusion unit can be performed using, for example, AI, or can be performed without using AI. For example, the exclusion unit can input geographic distribution data of the proposals into the generation AI and have the generation AI perform the exclusion.

[0052] The exclusion unit can improve the accuracy of exclusion by referring to the related literature of the proposal when excluding the relevant literature. The exclusion unit can, for example, analyze the related literature of the proposal to improve the accuracy of exclusion. The exclusion unit can also select an optimal exclusion algorithm based on the related literature of the proposal. The exclusion unit can also adjust exclusion parameters by referring to the related literature of the proposal. In this way, the accuracy of exclusion is improved by referring to the related literature of the proposal. Some or all of the above-mentioned processing in the exclusion unit can be performed using, for example, AI, or can be performed without using AI. For example, the exclusion unit can input the related literature data of the proposal into a generation AI and have the generation AI perform the exclusion.

[0053] The exclusion unit can perform exclusion taking into account the market value of the proposal when excluding a proposal. The exclusion unit, for example, analyzes the market value of the proposal and improves the accuracy of the exclusion. The exclusion unit can also select an optimal exclusion algorithm based on the market value of the proposal. The exclusion unit can also adjust exclusion parameters taking into account the market value of the proposal. In this way, the accuracy of exclusion is improved by taking into account the market value of the proposal. Some or all of the above-mentioned processing in the exclusion unit can be performed using, for example, AI, or can be performed without using AI. For example, the exclusion unit can input market value data of the proposal into the generation AI and have the generation AI perform the exclusion.

[0054] During improvement, the improvement unit can optimize the improvement algorithm by referring to past improvement data. For example, the improvement unit analyzes past improvement data and optimizes the improvement algorithm. The improvement unit can also select an optimal improvement algorithm based on the past improvement data. The improvement unit can also adjust parameters of the improvement algorithm by referring to past improvement data. In this way, the accuracy of the improvement algorithm is improved by referring to the past improvement data. Some or all of the above-mentioned processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input past improvement data into the generation AI and cause the generation AI to optimize the improvement algorithm.

[0055] During improvement, the improvement unit can update the improvement data by reflecting user feedback. The improvement unit updates the improvement data based on, for example, user feedback. The improvement unit can also adjust the improvement algorithm by referring to user feedback. The improvement unit can also improve the accuracy of the improvement data by reflecting user feedback. In this way, the accuracy of the improvement data is improved by reflecting user feedback. Some or all of the above-described processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input user feedback data into the generation AI and cause the generation AI to update the improvement data.

[0056] During improvement, the improvement unit can optimize the improvement algorithm by referring to the user's past feedback. For example, the improvement unit analyzes the user's past feedback and optimizes the improvement algorithm. The improvement unit can also select an optimal improvement algorithm based on the user's past feedback. The improvement unit can also adjust the parameters of the improvement algorithm by referring to the user's past feedback. This improves the accuracy of the improvement algorithm by referring to the user's past feedback. Some or all of the above-described processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input the user's past feedback data into the generation AI and cause the generation AI to optimize the improvement algorithm.

[0057] When making improvements, the improvement unit can weight the improvement data based on the time of proposal submission. For example, the improvement unit prioritizes improvements to proposals submitted more recently. The improvement unit can also postpone proposals submitted earlier. The improvement unit can also adjust the weighting of the improvement data based on the time of proposal submission. In this way, weighting the improvement data based on the time of proposal submission enables efficient improvements. Some or all of the above-mentioned processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input proposal submission time data into the generation AI and have the generation AI perform weighting of the improvement data.

[0058] During improvement, the improvement unit can integrate information from different data sources to expand the improvement data. For example, the improvement unit integrates information from different data sources to expand the improvement data. The improvement unit can also select optimal improvement data based on the different data sources. The improvement unit can also improve the accuracy of the improvement data by referring to the different data sources. In this way, the accuracy of the improvement data is improved by integrating information from the different data sources. Some or all of the above-described processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input different data sources into the generation AI and cause the generation AI to expand the improvement data.

[0059] During improvement, the improvement unit can optimize the improvement algorithm by referring to the user's past improvement history. For example, the improvement unit analyzes the user's past improvement history and optimizes the improvement algorithm. The improvement unit can also select an optimal improvement algorithm based on the user's past improvement history. The improvement unit can also adjust the parameters of the improvement algorithm by referring to the user's past improvement history. This improves the accuracy of the improvement algorithm by referring to the user's past improvement history. Some or all of the above-described processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input the user's past improvement history data into the generation AI and cause the generation AI to optimize the improvement algorithm.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The proposal exclusion system can further include a diversity evaluation unit that evaluates the diversity of proposals. The diversity evaluation unit analyzes the content of the proposals and highly values ​​proposals with different perspectives and approaches. For example, it compares technical proposals with business proposals and prioritizes proposals from different fields. The diversity evaluation unit can also take into account the background information of the proposal submitters and highly value proposals from submitters with different cultures and experiences. Furthermore, the diversity evaluation unit can evaluate whether the content of the proposals is novel and unique and prioritize the proposals based on this. This allows the proposal exclusion system to accept more diverse proposals and improve the quality of the contest.

[0062] The input unit can analyze the user's past proposal history and provide feedback on the content of the proposal. For example, it can suggest improvements to the current proposal based on examples of successful and unsuccessful proposals submitted by the user in the past. The input unit can also present examples of similar proposals from the user's past proposal history for reference. Furthermore, the input unit can evaluate the content of the proposal based on the user's past proposal history and provide advice for improving the quality of the proposal. In this way, providing feedback based on the user's past proposal history improves the quality of the proposal and increases the competitiveness of the contest.

[0063] When a proposal is input, the input unit can automatically generate the content of the proposal based on the user's current project or area of ​​interest. For example, a proposal related to a project the user is currently working on can be automatically generated, allowing the user to easily create a proposal. The input unit can also provide related proposal templates based on the user's area of ​​interest, allowing the user to efficiently create a proposal. Furthermore, the input unit can automatically generate optimal proposal content by referring to the user's past project history. This makes it more efficient to create proposals by automatically generating the content of the proposal based on the user's current project or area of ​​interest.

[0064] When a suggestion is input, the input unit can automatically convert the content of the suggestion according to the user's input method (voice, text, image, etc.). For example, when a user inputs a suggestion by voice, the input unit converts the suggestion into text using voice recognition technology and automatically generates the content of the suggestion. Also, when a user inputs a suggestion by text, the input unit can automatically complete the content of the suggestion based on the input text. Furthermore, when a user inputs a suggestion by image, the input unit can convert the suggestion into text using image recognition technology and automatically generate the content of the suggestion. This automatically converts the content of the suggestion according to the user's input method, thereby making the input of suggestions more efficient.

[0065] When inputting suggestions, the input unit can automatically customize the content of the suggestions by taking into account the user's geographical location information. For example, if the user is in a specific area, the input unit can automatically generate content of suggestions related to that area. The input unit can also automatically customize content of suggestions related to locations close to the user's current location. Furthermore, the input unit can automatically generate optimal content of suggestions by referring to the user's past location information. This makes it more efficient to input suggestions by automatically customizing content of suggestions by taking into account the user's geographical location information.

[0066] When a suggestion is input, the input unit can analyze the user's social media activity and automatically generate the suggestion content. For example, the input unit can automatically generate the relevant suggestion content based on the content the user has shared on social media. The input unit can also analyze the user's social media activity history and automatically generate the relevant suggestion content. Furthermore, the input unit can also automatically generate the relevant suggestion content by referring to the activities of the user's friends on social media. In this way, the suggestion input is made more efficient by automatically generating the suggestion content by analyzing the user's social media activity.

[0067] When a proposal is input, the input unit can automatically improve the content of the proposal by reflecting the user's past feedback. For example, the content of the proposal is automatically improved based on feedback provided by the user in the past. The input unit can also automatically optimize the content of the proposal by referring to the user's past feedback. Furthermore, the input unit can also automatically complement the content of the proposal by reflecting the user's feedback. In this way, by automatically improving the content of the proposal by reflecting the user's past feedback, the quality of the proposal improves and the competitiveness of the contest increases.

[0068] The processing flow of the first embodiment will be briefly explained below.

[0069] Step 1: The input unit inputs the proposal as text. Proposals include business proposals, technology proposals, idea proposals, etc. The user inputs the proposal into the input unit through a dedicated interface. Proposals can also be input using voice input or image input. Step 2: The vectorization unit uses natural language processing techniques to vectorize the suggestions input by the input unit. Vectorization converts text into numerical data, which makes it possible to compare the contents of suggestions numerically. The vectorization unit performs vectorization using algorithms such as TF-IDF and Word2Vec. It can also apply different vectorization algorithms depending on the category of the suggestion. Step 3: The similarity calculation unit calculates the similarity of the proposals vectorized by the vectorization unit. The similarity is calculated using methods such as cosine similarity or Euclidean distance. The similarity calculation unit calculates the similarity between proposals using cosine similarity. The accuracy of the similarity calculation can also be improved by taking into account the interrelationships between proposals. Step 4: The exclusion unit detects and excludes similar proposals based on the similarity calculated by the similarity calculation unit, using a set threshold as a criterion. The exclusion unit can effectively eliminate duplicate or similar proposals by setting it to exclude proposals with high similarity. It can also exclude proposals by taking into account attribute information of the proposal submitter. Step 5: The improver receives feedback on the proposals rejected by the rejecter and improves the algorithm. The improver uses the feedback to retrain the machine learning model and adjust parameters. The improver can also optimize the improved algorithm by taking into account past user feedback.

[0070] (Example 2) A system according to an embodiment of the present invention automatically excludes similar proposals in a generative AI contest. This system inputs proposals as text, vectorizes them using natural language processing technology, and calculates the similarity of the vectorized proposals using machine learning technology. Similar proposals are detected and excluded based on a set threshold. Feedback is then received while the algorithm is improved to improve accuracy. For example, a proposal is input as text. A detailed description of the proposal is required. For example, text including the purpose, method, and effects of the proposal is entered. This text is vectorized using natural language processing technology. Vectorization is the conversion of text into numerical data, which enables numerical comparison of the proposal contents. Next, machine learning technology is used to calculate the similarity of the vectorized proposals. A common similarity calculation method is used to calculate the similarity. This allows the similarity between proposals to be numerically evaluated. Highly similar proposals are detected and excluded based on a set threshold. For example, by configuring the system to exclude highly similar proposals, duplicate and similar proposals can be effectively eliminated. Feedback is then received while the algorithm is improved to improve accuracy. Feedback refers to evaluation of the results of proposal elimination and instructions for correction. For example, if a rejected proposal actually has different content, that information can be fed back to the algorithm to improve the accuracy of elimination in future contests. This allows contest organizers to receive more diverse proposals. This makes it easier for the system to reduce duplicate and similar proposals in generative AI contests, allowing for more diverse proposals. For example, it makes it possible to prevent multiple submissions of similar ideas and select proposals with a high level of originality. It also improves the efficiency of proposal evaluation and selection, allowing contests to run more smoothly.

[0071] A proposal exclusion system according to an embodiment includes an input unit, a vectorization unit, a similarity calculation unit, an exclusion unit, and an improvement unit. The input unit inputs proposals as text. Proposals include, but are not limited to, business proposals, technical proposals, and idea proposals. The input unit allows, for example, a user to input proposals through a dedicated interface. The input unit can also allow a user to input proposals using voice input or image input. The vectorization unit vectorizes the proposals input by the input unit using natural language processing technology. Vectorization, for example, converts text into numerical data, thereby enabling the contents of proposals to be compared numerically. The vectorization unit performs vectorization using algorithms such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec. The vectorization unit can also apply different vectorization algorithms depending on the category of the proposal. The similarity calculation unit calculates the similarity of the proposals vectorized by the vectorization unit. The similarity is calculated using, for example, cosine similarity or Euclidean distance, but is not limited to these examples. The similarity calculation unit calculates the similarity between proposals using, for example, cosine similarity. The similarity calculation unit can also improve the accuracy of the similarity calculation by taking into account the interrelationships between proposals. The exclusion unit detects and excludes similar proposals based on the similarity calculated by the similarity calculation unit, using a set threshold as a criterion. The exclusion unit can effectively exclude duplicate or similar proposals, for example, by setting the exclusion unit to exclude proposals with high similarity. The exclusion unit can also exclude proposals by taking into account attribute information of the submitters of the proposals. The improvement unit receives feedback on the proposals excluded by the exclusion unit and improves the algorithm. The improvement unit, for example, retrains the machine learning model or adjusts parameters based on the feedback. The improvement unit can also optimize the improved algorithm by referring to past user feedback. As a result, the proposal exclusion system according to the embodiment can automatically perform processes from proposal input to similarity calculation, exclusion, and algorithm improvement based on feedback.For example, a proposal exclusion system can automatically perform everything from inputting proposals to calculating similarity, exclusion, and improving the algorithm through feedback.

[0072] The input unit can estimate the user's emotions and adjust the timing of suggestion input based on the estimated user emotions. For example, when the user is stressed, the input unit simplifies the input interface and minimizes input steps. Furthermore, when the user is relaxed, the input unit can provide detailed input options and suggest customizable input methods. Furthermore, when the user is in a hurry, the input unit can prioritize voice input and enable prompt input of suggestions. By adjusting the timing of suggestion input according to the user's emotions, suggestions can be input at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the input unit may be performed using, for example, an AI. For example, the input unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the user's emotions.

[0073] The input unit can analyze the user's past proposal history and select an appropriate input method. For example, the input unit can automatically display as candidates proposal formats that the user has frequently used in the past. The input unit can also prioritize and suggest input methods (voice, text, etc.) that the user has used in the past. The input unit can also predict and suggest an input method to be used in a specific time period based on the user's past proposal history. This allows for the efficient input of proposals by selecting the optimal input method based on the user's past proposal history. Some or all of the above-mentioned processing in the input unit can be performed using, for example, AI, or can be performed without using AI. For example, the input unit can input the user's past proposal history data into a generation AI and cause the generation AI to select the optimal input method.

[0074] When inputting suggestions, the input unit can filter the suggestions based on the user's current project or areas of interest. For example, the input unit prioritizes input of suggestions related to the project the user is currently working on. The input unit can also automatically filter related suggestions based on the user's areas of interest. The input unit can also input optimal suggestions by referring to the user's past project history. In this way, by filtering the suggestions based on the user's current project or areas of interest, highly relevant suggestions can be input. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's project data to the generation AI and cause the generation AI to filter relevant suggestions.

[0075] When inputting a suggestion, the input unit can select an appropriate input means depending on the user's input method (voice, text, image, etc.). For example, when the user inputs a suggestion by voice, the input unit converts it into text using voice recognition technology. Furthermore, when the user inputs a suggestion by text, the input unit can also provide an input assistance function. Furthermore, when the user inputs a suggestion by image, the input unit can also convert it into text using image recognition technology. This makes the input of suggestions more efficient by selecting the optimal input means depending on the user's input method. Some or all of the above-mentioned processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input voice data to a generation AI and have the generation AI convert the voice data into text data.

[0076] The input unit can estimate the user's emotions and determine the priority of suggestions to be input based on the estimated user's emotions. For example, when the user is feeling stressed, the input unit postpones suggestions of lower importance. Furthermore, when the user is relaxed, the input unit can also prioritize input of suggestions of higher importance. Furthermore, when the user is in a hurry, the input unit can also prioritize input of suggestions that can be processed quickly. Thus, by determining the priority of suggestions according to the user's emotions, important suggestions can be input preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the input unit may be performed using, for example, an AI. For example, the input unit can input the user's facial expression data to the generation AI and cause the generation AI to estimate the user's emotions.

[0077] When inputting suggestions, the input unit can prioritize inputting highly relevant suggestions by taking into account the user's geographical location information. For example, if the user is in a specific area, the input unit prioritizes inputting suggestions related to that area. The input unit can also prioritize inputting suggestions related to locations close to the user's current location. The input unit can also prioritize inputting highly relevant suggestions by referring to the user's past location information. This makes the input of suggestions more efficient by prioritizing highly relevant suggestions by taking into account the user's geographical location information. Some or all of the above-described processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can input the user's geographical location information to the generation AI and cause the generation AI to select highly relevant suggestions.

[0078] When inputting suggestions, the input unit can analyze the user's social media activity and input related suggestions. The input unit can input related suggestions based on, for example, content shared by the user on social media. The input unit can also analyze the user's social media activity history and input related suggestions. The input unit can also input related suggestions with reference to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity and inputting related suggestions, the input of suggestions is made more efficient. Some or all of the above-mentioned processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's social media data to the generation AI and cause the generation AI to select related suggestions.

[0079] When inputting a suggestion, the input unit can customize the input method by reflecting the user's past feedback. The input unit customizes the input interface, for example, based on feedback provided by the user in the past. The input unit can also optimize the input procedure by referring to the user's past feedback. The input unit can also improve the input method by reflecting the user's feedback. In this way, customizing the input method by reflecting the user's past feedback makes the input of suggestions more efficient. Some or all of the above-mentioned processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's feedback data to the generation AI and cause the generation AI to customize the input method.

[0080] The vectorization unit can estimate the user's emotion and adjust the vectorization expression method based on the estimated user's emotion. For example, if the user is relaxed, the vectorization unit can perform detailed vectorization. If the user is in a hurry, the vectorization unit can also perform simplified vectorization. If the user is excited, the vectorization unit can also perform vectorization with a visually stimulating effect. This allows for more appropriate vectorization by adjusting the vectorization expression method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the vectorization unit can be performed using, for example, an AI, or without an AI. For example, the vectorization unit can input the user's facial expression data into the generation AI and have the generation AI adjust the vectorization expression method.

[0081] The vectorization unit can adjust the level of detail of the vectorization based on the importance of the proposal during vectorization. For example, the vectorization unit performs detailed vectorization on proposals with high importance. The vectorization unit can also perform simplified vectorization on proposals with low importance. The vectorization unit can also adjust the accuracy of the vectorization according to the importance of the proposal. This allows for efficient vectorization by adjusting the level of detail of the vectorization according to the importance of the proposal. Some or all of the above-described processing in the vectorization unit may be performed using, or without, AI, for example. For example, the vectorization unit can input proposal importance data to the generation AI and cause the generation AI to adjust the level of detail of the vectorization.

[0082] During vectorization, the vectorization unit can apply an appropriate vectorization algorithm depending on the category of the proposal. For example, the vectorization unit applies a vectorization algorithm that emphasizes technical terminology to a technical proposal. The vectorization unit can also apply a vectorization algorithm that emphasizes business terminology to a business proposal. The vectorization unit can also select an optimal vectorization algorithm depending on the category of the proposal. This improves the accuracy of vectorization by applying the optimal vectorization algorithm depending on the category of the proposal. Some or all of the above-described processing in the vectorization unit may be performed using, for example, AI, or may be performed without using AI. For example, the vectorization unit can input proposal category data to a generation AI and cause the generation AI to select an optimal vectorization algorithm.

[0083] During vectorization, the vectorization unit can improve the accuracy of vectorization by referring to the user's past vectorization results. The vectorization unit, for example, analyzes the user's past vectorization results to improve accuracy. The vectorization unit can also select an optimal vectorization algorithm based on the user's past vectorization results. The vectorization unit can also adjust vectorization parameters by referring to the user's past vectorization results. This improves the accuracy of vectorization by referring to the user's past vectorization results. Some or all of the above-described processing in the vectorization unit may be performed using, for example, AI, or may be performed without using AI. For example, the vectorization unit can input the user's past vectorization result data into the generation AI and cause the generation AI to improve the accuracy of vectorization.

[0084] The vectorization unit can estimate the user's emotion and adjust the length of vectorization based on the estimated user's emotion. For example, if the user is relaxed, the vectorization unit can perform detailed vectorization. If the user is in a hurry, the vectorization unit can also perform simplified vectorization. If the user is excited, the vectorization unit can also perform vectorization with a visually stimulating effect. This allows for more appropriate vectorization by adjusting the length of vectorization according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the vectorization unit can be performed using, for example, an AI, or without an AI. For example, the vectorization unit can input the user's facial expression data into the generation AI and have the generation AI adjust the length of vectorization.

[0085] During vectorization, the vectorization unit can determine the priority of vectorization based on the submission time of the proposal. For example, the vectorization unit prioritizes vectorization of proposals submitted more recently. The vectorization unit can also postpone vectorization of proposals submitted earlier. The vectorization unit can also adjust the priority of vectorization based on the submission time of the proposal. This allows for efficient vectorization by determining the priority of vectorization based on the submission time of the proposal. Some or all of the above-described processing in the vectorization unit may be performed using, or without, AI, for example. For example, the vectorization unit can input proposal submission time data into the generation AI and have the generation AI determine the priority of vectorization.

[0086] The vectorization unit can adjust the order of vectorization based on the relevance of the proposal during vectorization. For example, the vectorization unit prioritizes vectorization of proposals with high relevance. The vectorization unit can also postpone vectorization of proposals with low relevance. The vectorization unit can also adjust the order of vectorization based on the relevance of the proposal. As a result, efficient vectorization can be achieved by adjusting the order of vectorization based on the relevance of the proposal. Some or all of the above-described processing in the vectorization unit may be performed using, or without, AI, for example. For example, the vectorization unit can input the relevance data of the proposal to the generation AI and cause the generation AI to adjust the order of vectorization.

[0087] During vectorization, the vectorization unit can adjust the use of technical terminology in the vectorization according to the user's level of expertise. For example, if the user's level of expertise is high, the vectorization unit can perform vectorization that makes extensive use of technical terminology. Furthermore, if the user's level of expertise is low, the vectorization unit can also perform vectorization that avoids technical terminology. Furthermore, the vectorization unit can adjust the use of technical terminology in the vectorization according to the user's level of expertise. This allows for more appropriate vectorization by adjusting the use of technical terminology in the vectorization according to the user's level of expertise. Some or all of the above-described processing in the vectorization unit may be performed using, or without, AI, for example. For example, the vectorization unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0088] The similarity calculation unit can estimate the user's emotion and adjust the criteria for similarity calculation based on the estimated user's emotion. For example, if the user is relaxed, the similarity calculation unit can perform a detailed similarity calculation. Furthermore, if the user is in a hurry, the similarity calculation unit can perform a simplified similarity calculation. Furthermore, if the user is excited, the similarity calculation unit can perform a similarity calculation with a visually stimulating effect. This allows for more appropriate similarity calculation by adjusting the criteria for similarity calculation according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as 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. Some or all of the above-described processing in the similarity calculation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the similarity calculation unit can input the user's facial expression data into the generation AI and have the generation AI adjust the criteria for similarity calculation.

[0089] The similarity calculation unit can improve the accuracy of the similarity calculation by taking into account the interrelationships of the proposals when calculating the similarity. For example, the similarity calculation unit analyzes the interrelationships of the proposals to improve the accuracy of the similarity calculation. The similarity calculation unit can also select an optimal similarity calculation algorithm based on the interrelationships of the proposals. The similarity calculation unit can also adjust parameters for the similarity calculation by taking into account the interrelationships of the proposals. In this way, the accuracy of the similarity calculation is improved by taking into account the interrelationships of the proposals. Some or all of the above-mentioned processing in the similarity calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the similarity calculation unit can input proposal interrelationship data into the generation AI and cause the generation AI to improve the accuracy of the similarity calculation.

[0090] The similarity calculation unit can perform the similarity calculation taking into account the attribute information of the proposal submitter. The similarity calculation unit performs the similarity calculation taking into account, for example, the expertise level of the proposal submitter. The similarity calculation unit can also perform the similarity calculation by referring to the proposal submitter's past proposal history. The similarity calculation unit can also adjust the parameters of the similarity calculation based on the attribute information of the proposal submitter. This improves the accuracy of the similarity calculation by taking into account the attribute information of the proposal submitter. Some or all of the above-mentioned processing in the similarity calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the similarity calculation unit can input attribute information data of the proposal submitter to the generation AI and have the generation AI perform the similarity calculation.

[0091] The similarity calculation unit can weight the similarity calculation based on the frequency of proposal submission when calculating the similarity. For example, the similarity calculation unit prioritizes proposals with a high submission frequency in the similarity calculation. The similarity calculation unit can also postpone proposals with a low submission frequency. The similarity calculation unit can also adjust the weighting of the similarity calculation based on the frequency of proposal submission. In this way, weighting the similarity calculation based on the frequency of proposal submission enables efficient similarity calculation. Some or all of the above-mentioned processing in the similarity calculation unit may be performed using AI, for example, or may be performed without using AI. For example, the similarity calculation unit can input proposal submission frequency data to a generation AI and cause the generation AI to perform weighting in the similarity calculation.

[0092] The similarity calculation unit can estimate the user's emotion and adjust the order in which the similarity calculation results are displayed based on the estimated user's emotion. For example, if the user is relaxed, the similarity calculation unit can display detailed similarity calculation results. Furthermore, if the user is in a hurry, the similarity calculation unit can display simplified similarity calculation results. Furthermore, if the user is excited, the similarity calculation unit can display similarity calculation results with a visually stimulating effect. This allows for more appropriate results to be displayed by adjusting the order in which the similarity calculation results are displayed according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the similarity calculation unit can be performed using, for example, an AI, or without an AI. For example, the similarity calculation unit can input the user's facial expression data into the generation AI and have the generation AI adjust the order in which the results are displayed.

[0093] The similarity calculation unit can perform the similarity calculation taking into account the geographical distribution of the proposals. For example, the similarity calculation unit analyzes the geographical distribution of the proposals to improve the accuracy of the similarity calculation. The similarity calculation unit can also select an optimal similarity calculation algorithm based on the geographical distribution of the proposals. The similarity calculation unit can also adjust parameters for the similarity calculation taking into account the geographical distribution of the proposals. In this way, the accuracy of the similarity calculation is improved by taking the geographical distribution of the proposals into account. Some or all of the above-mentioned processing in the similarity calculation unit can be performed using, for example, AI, or can be performed without using AI. For example, the similarity calculation unit can input geographical distribution data of the proposals to a generation AI and have the generation AI perform the similarity calculation.

[0094] The similarity calculation unit can improve the accuracy of the similarity calculation by referring to the proposed related literature when calculating the similarity. The similarity calculation unit can, for example, analyze the proposed related literature to improve the accuracy of the similarity calculation. The similarity calculation unit can also select an optimal similarity calculation algorithm based on the proposed related literature. The similarity calculation unit can also adjust parameters for the similarity calculation by referring to the proposed related literature. In this way, the accuracy of the similarity calculation is improved by referring to the proposed related literature. Some or all of the above-mentioned processing in the similarity calculation unit can be performed using, for example, AI, or can be performed without using AI. For example, the similarity calculation unit can input the proposed related literature data into a generation AI and have the generation AI perform the similarity calculation.

[0095] The similarity calculation unit can calculate the similarity taking into account the market value of the proposal when calculating the similarity. The similarity calculation unit, for example, analyzes the market value of the proposal and improves the accuracy of the similarity calculation. The similarity calculation unit can also select an optimal similarity calculation algorithm based on the market value of the proposal. The similarity calculation unit can also adjust the parameters of the similarity calculation taking into account the market value of the proposal. In this way, by taking the market value of the proposal into account, the accuracy of the similarity calculation is improved. Some or all of the above-mentioned processing in the similarity calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the similarity calculation unit can input market value data of the proposal to the generation AI and have the generation AI perform the similarity calculation.

[0096] The excluding unit can estimate the user's emotions and determine the priority of suggestions to be excluded based on the estimated user's emotions. For example, if the user is feeling stressed, the excluding unit can postpone less important suggestions. Furthermore, if the user is relaxed, the excluding unit can also prioritize excluding more important suggestions. Furthermore, if the user is in a hurry, the excluding unit can also prioritize excluding suggestions that can be processed quickly. This allows efficient proposal elimination by determining the priority of suggestions to be excluded according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the excluding unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the excluding unit can input the user's facial expression data into the generation AI and cause the generation AI to determine the priority of suggestions to be excluded.

[0097] The exclusion unit can improve the accuracy of exclusion by taking into account the interrelationships between proposals when excluding proposals. For example, the exclusion unit analyzes the interrelationships between proposals and improves the accuracy of exclusion. The exclusion unit can also select an optimal exclusion algorithm based on the interrelationships between proposals. The exclusion unit can also adjust exclusion parameters by taking into account the interrelationships between proposals. In this way, the accuracy of exclusion is improved by taking into account the interrelationships between proposals. Some or all of the above-described processing in the exclusion unit may be performed using AI, for example, or may be performed without using AI. For example, the exclusion unit can input interrelationship data between proposals into the generation AI and cause the generation AI to improve the accuracy of exclusion.

[0098] The exclusion unit can perform exclusion by taking into consideration attribute information of the proposal submitter. For example, the exclusion unit can perform exclusion by taking into consideration the expertise level of the proposal submitter. The exclusion unit can also perform exclusion by referring to the proposal submitter's past proposal history. The exclusion unit can also adjust exclusion parameters based on the attribute information of the proposal submitter. In this way, the accuracy of exclusion is improved by taking into consideration the attribute information of the proposal submitter. Some or all of the above-mentioned processing in the exclusion unit can be performed using AI, for example, or can be performed without using AI. For example, the exclusion unit can input attribute information data of the proposal submitter into the generation AI and have the generation AI perform the exclusion.

[0099] The exclusion unit can weight the exclusion based on the frequency of proposal submission at the time of exclusion. For example, the exclusion unit prioritizes exclusion of proposals with a high submission frequency. The exclusion unit can also postpone exclusion of proposals with a low submission frequency. The exclusion unit can also adjust the weight of exclusion based on the frequency of proposal submission. In this way, by weighting the exclusion based on the frequency of proposal submission, efficient proposal exclusion can be performed. Some or all of the above-described processing in the exclusion unit may be performed using AI, for example, or may be performed without using AI. For example, the exclusion unit can input proposal submission frequency data into the generation AI and cause the generation AI to perform the weighting of exclusion.

[0100] The exclusion unit can estimate the user's emotions and adjust the display method of the suggestions to be excluded based on the estimated user's emotions. For example, the exclusion unit can provide a simple display method when the user is stressed. The exclusion unit can also provide a detailed display method when the user is relaxed. The exclusion unit can also provide a display method that allows the user to quickly check the suggestions when the user is in a hurry. This allows for more appropriate display by adjusting the display method of the suggestions to be excluded according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the exclusion unit can be performed using an AI, for example, or without an AI. For example, the exclusion unit can input the user's facial expression data into the generation AI and cause the generation AI to adjust the display method.

[0101] The exclusion unit can perform exclusion taking into account the geographic distribution of the proposals. For example, the exclusion unit analyzes the geographic distribution of the proposals to improve the accuracy of exclusion. The exclusion unit can also select an optimal exclusion algorithm based on the geographic distribution of the proposals. The exclusion unit can also adjust exclusion parameters taking into account the geographic distribution of the proposals. In this way, the accuracy of exclusion is improved by taking the geographic distribution of the proposals into account. Some or all of the above-mentioned processing in the exclusion unit can be performed using, for example, AI, or can be performed without using AI. For example, the exclusion unit can input geographic distribution data of the proposals into the generation AI and have the generation AI perform the exclusion.

[0102] The exclusion unit can improve the accuracy of exclusion by referring to the related literature of the proposal when excluding the relevant literature. The exclusion unit can, for example, analyze the related literature of the proposal to improve the accuracy of exclusion. The exclusion unit can also select an optimal exclusion algorithm based on the related literature of the proposal. The exclusion unit can also adjust exclusion parameters by referring to the related literature of the proposal. In this way, the accuracy of exclusion is improved by referring to the related literature of the proposal. Some or all of the above-mentioned processing in the exclusion unit can be performed using, for example, AI, or can be performed without using AI. For example, the exclusion unit can input the related literature data of the proposal into a generation AI and have the generation AI perform the exclusion.

[0103] The exclusion unit can perform exclusion taking into account the market value of the proposal when excluding a proposal. The exclusion unit, for example, analyzes the market value of the proposal and improves the accuracy of the exclusion. The exclusion unit can also select an optimal exclusion algorithm based on the market value of the proposal. The exclusion unit can also adjust exclusion parameters taking into account the market value of the proposal. In this way, the accuracy of exclusion is improved by taking into account the market value of the proposal. Some or all of the above-mentioned processing in the exclusion unit can be performed using, for example, AI, or can be performed without using AI. For example, the exclusion unit can input market value data of the proposal into the generation AI and have the generation AI perform the exclusion.

[0104] The improvement unit can estimate the user's emotions and select improvement data based on the estimated user's emotions. For example, if the user is relaxed, the improvement unit can select detailed improvement data. If the user is in a hurry, the improvement unit can also select simplified improvement data. If the user is excited, the improvement unit can also select improvement data with a visually stimulating effect. This allows for more appropriate improvement by selecting improvement data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the improvement unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the improvement unit can input the user's facial expression data into the generation AI and have the generation AI select improvement data.

[0105] During improvement, the improvement unit can optimize the improvement algorithm by referring to past improvement data. For example, the improvement unit analyzes past improvement data and optimizes the improvement algorithm. The improvement unit can also select an optimal improvement algorithm based on the past improvement data. The improvement unit can also adjust parameters of the improvement algorithm by referring to past improvement data. In this way, the accuracy of the improvement algorithm is improved by referring to the past improvement data. Some or all of the above-mentioned processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input past improvement data into the generation AI and cause the generation AI to optimize the improvement algorithm.

[0106] During improvement, the improvement unit can update the improvement data by reflecting user feedback. The improvement unit updates the improvement data based on, for example, user feedback. The improvement unit can also adjust the improvement algorithm by referring to user feedback. The improvement unit can also improve the accuracy of the improvement data by reflecting user feedback. In this way, the accuracy of the improvement data is improved by reflecting user feedback. Some or all of the above-described processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input user feedback data into the generation AI and cause the generation AI to update the improvement data.

[0107] During improvement, the improvement unit can optimize the improvement algorithm by referring to the user's past feedback. For example, the improvement unit analyzes the user's past feedback and optimizes the improvement algorithm. The improvement unit can also select an optimal improvement algorithm based on the user's past feedback. The improvement unit can also adjust the parameters of the improvement algorithm by referring to the user's past feedback. This improves the accuracy of the improvement algorithm by referring to the user's past feedback. Some or all of the above-described processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input the user's past feedback data into the generation AI and cause the generation AI to optimize the improvement algorithm.

[0108] The improvement unit can estimate the user's emotions and adjust the frequency of improvements based on the estimated user emotions. For example, the improvement unit can make improvements more frequently when the user is relaxed. Furthermore, the improvement unit can also reduce the frequency of improvements when the user is in a hurry. Furthermore, the improvement unit can make improvements with visually stimulating effects when the user is excited. This allows for more appropriate improvements by adjusting the frequency of improvements according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the improvement unit can be performed using, for example, an AI, or without an AI. For example, the improvement unit can input the user's facial expression data into the generation AI and have the generation AI adjust the frequency of improvements.

[0109] When making improvements, the improvement unit can weight the improvement data based on the time of proposal submission. For example, the improvement unit prioritizes improvements to proposals submitted more recently. The improvement unit can also postpone proposals submitted earlier. The improvement unit can also adjust the weighting of the improvement data based on the time of proposal submission. In this way, weighting the improvement data based on the time of proposal submission enables efficient improvements. Some or all of the above-mentioned processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input proposal submission time data into the generation AI and have the generation AI perform weighting of the improvement data.

[0110] During improvement, the improvement unit can integrate information from different data sources to expand the improvement data. For example, the improvement unit integrates information from different data sources to expand the improvement data. The improvement unit can also select optimal improvement data based on the different data sources. The improvement unit can also improve the accuracy of the improvement data by referring to the different data sources. In this way, the accuracy of the improvement data is improved by integrating information from the different data sources. Some or all of the above-described processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input different data sources into the generation AI and cause the generation AI to expand the improvement data.

[0111] During improvement, the improvement unit can optimize the improvement algorithm by referring to the user's past improvement history. For example, the improvement unit analyzes the user's past improvement history and optimizes the improvement algorithm. The improvement unit can also select an optimal improvement algorithm based on the user's past improvement history. The improvement unit can also adjust the parameters of the improvement algorithm by referring to the user's past improvement history. This improves the accuracy of the improvement algorithm by referring to the user's past improvement history. Some or all of the above-described processing in the improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the improvement unit can input the user's past improvement history data into the generation AI and cause the generation AI to optimize the improvement algorithm. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned input unit, vectorization unit, similarity calculation unit, exclusion unit, and improvement unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the input unit can input suggestions through the reception device 38 of the smart device 14. The vectorization unit is realized by the specific processing unit 290 of the data processing device 12 and vectorizes the suggestions using natural language processing technology. The similarity calculation unit is realized by the specific processing unit 290 of the data processing device 12 and calculates the similarity of the vectorized suggestions. The exclusion unit is realized by the specific processing unit 290 of the data processing device 12 and excludes similar suggestions based on a set threshold. The improvement unit is realized by the specific processing unit 290 of the data processing device 12 and improves the algorithm based on feedback. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned input unit, vectorization unit, similarity calculation unit, exclusion unit, and improvement unit is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the input unit can input suggestions by voice through the microphone 238 of the smart glasses 214. The vectorization unit is realized by the specific processing unit 290 of the data processing device 12 and vectorizes the suggestions using natural language processing techniques. The similarity calculation unit is realized by the specific processing unit 290 of the data processing device 12 and calculates the similarity of the vectorized suggestions. The exclusion unit is realized by the specific processing unit 290 of the data processing device 12 and excludes similar suggestions based on a set threshold. The improvement unit is realized by the specific processing unit 290 of the data processing device 12 and improves the algorithm based on feedback. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned input unit, vectorization unit, similarity calculation unit, exclusion unit, and improvement unit is realized, for example, in at least one of the headset-type terminal 314 and the data processing device 12. For example, the input unit can input suggestions by voice through the microphone 238 of the headset-type terminal 314. The vectorization unit is realized by the specific processing unit 290 of the data processing device 12 and vectorizes the suggestions using natural language processing techniques. The similarity calculation unit is realized by the specific processing unit 290 of the data processing device 12 and calculates the similarity of the vectorized suggestions. The exclusion unit is realized by the specific processing unit 290 of the data processing device 12 and excludes similar suggestions based on a set threshold. The improvement unit is realized by the specific processing unit 290 of the data processing device 12 and improves the algorithm based on feedback. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned input unit, vectorization unit, similarity calculation unit, exclusion unit, and improvement unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the input unit can input suggestions by voice through the microphone 238 of the robot 414. The vectorization unit is realized by the specific processing unit 290 of the data processing device 12 and vectorizes the suggestions using natural language processing techniques. The similarity calculation unit is realized by the specific processing unit 290 of the data processing device 12 and calculates the similarity of the vectorized suggestions. The exclusion unit is realized by the specific processing unit 290 of the data processing device 12 and excludes similar suggestions based on a set threshold. The improvement unit is realized by the specific processing unit 290 of the data processing device 12 and improves the algorithm based on feedback.

[0112] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0113] The proposal exclusion system can further include a diversity evaluation unit that evaluates the diversity of proposals. The diversity evaluation unit analyzes the content of the proposals and highly values ​​proposals with different perspectives and approaches. For example, it compares technical proposals with business proposals and prioritizes proposals from different fields. The diversity evaluation unit can also take into account the background information of the proposal submitters and highly value proposals from submitters with different cultures and experiences. Furthermore, the diversity evaluation unit can evaluate whether the content of the proposals is novel and unique and prioritize the proposals based on this. This allows the proposal exclusion system to accept more diverse proposals and improve the quality of the contest.

[0114] The input unit can estimate the user's emotions and automatically complete the input content of the suggestions based on the estimated user's emotions. For example, if the user is feeling stressed, the input unit can automatically complete the main points of the suggestions, reducing the burden on the user. Also, if the user is relaxed, the input unit can provide detailed input options, allowing the user to freely customize the suggestions. Furthermore, if the user is in a hurry, the input unit can provide a simplified input form, allowing the user to quickly enter the suggestions. In this way, the input content of the suggestions is automatically completed according to the user's emotions, thereby streamlining the input of suggestions.

[0115] The input unit can analyze the user's past proposal history and provide feedback on the content of the proposal. For example, it can suggest improvements to the current proposal based on examples of successful and unsuccessful proposals submitted by the user in the past. The input unit can also present examples of similar proposals from the user's past proposal history for reference. Furthermore, the input unit can evaluate the content of the proposal based on the user's past proposal history and provide advice for improving the quality of the proposal. In this way, providing feedback based on the user's past proposal history improves the quality of the proposal and increases the competitiveness of the contest.

[0116] When a proposal is input, the input unit can automatically generate the content of the proposal based on the user's current project or area of ​​interest. For example, a proposal related to a project the user is currently working on can be automatically generated, allowing the user to easily create a proposal. The input unit can also provide related proposal templates based on the user's area of ​​interest, allowing the user to efficiently create a proposal. Furthermore, the input unit can automatically generate optimal proposal content by referring to the user's past project history. This makes it more efficient to create proposals by automatically generating the content of the proposal based on the user's current project or area of ​​interest.

[0117] When a suggestion is input, the input unit can automatically convert the content of the suggestion according to the user's input method (voice, text, image, etc.). For example, when a user inputs a suggestion by voice, the input unit converts the suggestion into text using voice recognition technology and automatically generates the content of the suggestion. Also, when a user inputs a suggestion by text, the input unit can automatically complete the content of the suggestion based on the input text. Furthermore, when a user inputs a suggestion by image, the input unit can convert the suggestion into text using image recognition technology and automatically generate the content of the suggestion. This automatically converts the content of the suggestion according to the user's input method, thereby making the input of suggestions more efficient.

[0118] The input unit can estimate the user's emotions and customize the suggestion input interface based on the estimated user's emotions. For example, if the user is feeling stressed, the input unit can provide a simple and intuitive interface to reduce the user's burden. Alternatively, if the user is relaxed, the input unit can provide detailed input options to allow the user to freely customize the suggestions. Furthermore, if the user is in a hurry, the input unit can provide an interface that allows quick input, thereby streamlining the input of suggestions. In this way, customizing the input interface according to the user's emotions allows the user to smoothly input suggestions.

[0119] When inputting suggestions, the input unit can automatically customize the content of the suggestions by taking into account the user's geographical location information. For example, if the user is in a specific area, the input unit can automatically generate content of suggestions related to that area. The input unit can also automatically customize content of suggestions related to locations close to the user's current location. Furthermore, the input unit can automatically generate optimal content of suggestions by referring to the user's past location information. This makes it more efficient to input suggestions by automatically customizing content of suggestions by taking into account the user's geographical location information.

[0120] When a suggestion is input, the input unit can analyze the user's social media activity and automatically generate the suggestion content. For example, the input unit can automatically generate the relevant suggestion content based on the content the user has shared on social media. The input unit can also analyze the user's social media activity history and automatically generate the relevant suggestion content. Furthermore, the input unit can also automatically generate the relevant suggestion content by referring to the activities of the user's friends on social media. In this way, the suggestion input is made more efficient by automatically generating the suggestion content by analyzing the user's social media activity.

[0121] When a proposal is input, the input unit can automatically improve the content of the proposal by reflecting the user's past feedback. For example, the content of the proposal is automatically improved based on feedback provided by the user in the past. The input unit can also automatically optimize the content of the proposal by referring to the user's past feedback. Furthermore, the input unit can also automatically complement the content of the proposal by reflecting the user's feedback. In this way, by automatically improving the content of the proposal by reflecting the user's past feedback, the quality of the proposal improves and the competitiveness of the contest increases.

[0122] The vectorization unit can estimate the user's emotion and select a vectorization algorithm based on the estimated user's emotion. For example, if the user is relaxed, a detailed vectorization algorithm can be applied. If the user is in a hurry, a simplified vectorization algorithm can be applied. Furthermore, if the user is excited, a vectorization algorithm with a visually stimulating effect can be applied. In this way, by selecting a vectorization algorithm according to the user's emotion, more appropriate vectorization can be performed.

[0123] The processing flow of the second embodiment will be briefly explained below.

[0124] Step 1: The input unit inputs the proposal as text. Proposals include business proposals, technology proposals, idea proposals, etc. The user inputs the proposal into the input unit through a dedicated interface. Proposals can also be input using voice input or image input. Step 2: The vectorization unit uses natural language processing techniques to vectorize the suggestions input by the input unit. Vectorization converts text into numerical data, which makes it possible to compare the contents of suggestions numerically. The vectorization unit performs vectorization using algorithms such as TF-IDF and Word2Vec. It can also apply different vectorization algorithms depending on the category of the suggestion. Step 3: The similarity calculation unit calculates the similarity of the proposals vectorized by the vectorization unit. The similarity is calculated using methods such as cosine similarity or Euclidean distance. The similarity calculation unit calculates the similarity between proposals using cosine similarity. The accuracy of the similarity calculation can also be improved by taking into account the interrelationships between proposals. Step 4: The exclusion unit detects and excludes similar proposals based on the similarity calculated by the similarity calculation unit, using a set threshold as a criterion. The exclusion unit can effectively eliminate duplicate or similar proposals by setting it to exclude proposals with high similarity. It can also exclude proposals by taking into account attribute information of the proposal submitter. Step 5: The improver receives feedback on the proposals rejected by the rejecter and improves the algorithm. The improver uses the feedback to retrain the machine learning model and adjust parameters. The improver can also optimize the improved algorithm by taking into account past user feedback.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0130] 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.

[0131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0132] 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.

[0133] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0135] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0136] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0137] 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.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0139] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0144] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0145] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0146] 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.

[0147] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0148] 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.

[0149] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0151] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0152] 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.

[0153] 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.

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0155] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0156] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0160] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0161] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0162] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0165] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0167] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0168] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0169] 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.

[0170] 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.

[0171] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0172] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0173] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0175] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0177] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0178] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0180] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0181] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0182] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0185] 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.

[0186] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0187] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0188] 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.

[0189] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0190] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0191] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0193] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0194] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0195] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0196] [Explanation of symbols]

[0197] 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. an input section for inputting a suggestion as text; a vectorization unit that vectorizes the proposal input by the input unit; a similarity calculation unit that calculates a similarity of the proposals vectorized by the vectorization unit; an exclusion unit that detects and excludes similar proposals based on the similarity calculated by the similarity calculation unit and using a specific threshold as a criterion; an improvement unit that receives feedback on the proposals excluded by the exclusion unit and improves the algorithm; A system characterized by:

2. The input unit Estimate the user's emotions and adjust the timing of suggestion input based on the estimated user emotions.

2. The system of claim 1.

3. The input unit Analyze the user's past suggestions and select the appropriate input method 2. The system of claim 1.

4. The input unit Filter suggestions as they are entered based on your current projects and interests 2. The system of claim 1.

5. The input unit When entering suggestions, select the appropriate input method depending on the user's input method.

2. The system of claim 1.

6. The input unit Estimate the user's emotions and prioritize input suggestions based on the estimated user emotions.

2. The system of claim 1.

7. The input unit When entering suggestions, the app takes into account the user's geographic location to prioritize more relevant suggestions.

2. The system of claim 1.

8. The input unit When providing suggestions, analyze the user's social media activity and provide relevant suggestions 2. The system of claim 1.

Images