system

Abstract

The system according to this embodiment aims to automatically analyze image data within patent documents and evaluate their similarity. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, an evaluation unit, and a provision unit. The collection unit collects image data within patent documents. The analysis unit analyzes the image data collected by the collection unit. The evaluation unit evaluates the similarity based on the data analyzed by the analysis unit. The provision unit provides the evaluation results obtained by the evaluation unit.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, image data in patent documents is often manually checked, which is time-consuming and costly. In addition, there is a problem that the evaluation of similarity is subjective and varies in accuracy.

[0005] The system according to the embodiment aims to automatically analyze image data in patent documents and evaluate similarity.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a collection unit, an analysis unit, an evaluation unit, and a provision unit. The collection unit collects image data within patent documents. The analysis unit analyzes the image data collected by the collection unit. The evaluation unit evaluates the similarity based on the data analyzed by the analysis unit. The provision unit provides the evaluation results obtained by the evaluation unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically analyze image data within patent documents and evaluate similarity. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The patent document search AI agent according to an embodiment of the present invention is a system that automatically collects image data within patent documents, analyzes it using a generating AI, and evaluates its similarity to existing designs and structures. This system automatically scans image data within patent documents and evaluates its similarity to other existing designs and structures, thereby efficiently confirming the novelty required for patents and quickly identifying similar designs. For example, the patent document search AI agent collects image data within patent documents. For example, the patent document search AI agent can scan handwritten drawings or photographs and convert them into digital data, or it can directly input data in digital format. This data is converted into a format that is easy for the generating AI to analyze. Next, the patent document search AI agent analyzes the image data within patent documents using the generating AI. The input to the generating AI is the image data within the patent documents themselves, and the generating AI performs analysis based on its content. For example, the generating AI receives a prompt such as "Please extract the features of this image," and extracts and analyzes the features of the image. Next, the patent document search AI agent evaluates the similarity between the data analyzed by the generating AI and a pre-prepared existing patent database. Image recognition technology and pattern matching technology are used to evaluate similarity. For example, a generating AI compares image features and calculates a similarity score. Next, a patent document search AI agent evaluates the novelty of the patent document based on the similarity score. For example, a lower similarity score indicates higher novelty. The final evaluation result is fed back to the user. This allows the user to quickly and accurately verify the novelty of the patent document. The patent document search AI agent also analyzes 3D CAD data through the generating AI and automatically compares it with existing patent databases. For example, for a new design of an automobile part, it automatically searches for existing similar parts and evaluates the possibility of it being a new application. This automates the patent document search process, significantly reducing search time and costs. The highly accurate similarity evaluation by AI reduces human oversight and variability due to subjective judgment. As a result, the novelty of patents is confirmed more reliably, and risk management is strengthened.Furthermore, rapid feedback makes the design process and strategic patent acquisition more effective. This allows the patent document search AI agent to efficiently verify the novelty of patent documents and quickly identify similar designs.

[0029] The patent document search AI agent according to this embodiment comprises a collection unit, an analysis unit, an evaluation unit, and a provision unit. The collection unit collects image data within patent documents. Image data within patent documents includes, but is not limited to, drawings, photographs, scanned images, etc. The collection unit can, for example, digitize and collect handwritten drawings using scanning technology. The collection unit can also directly collect image data submitted in digital format. Furthermore, the collection unit can read printed image data using OCR technology. For example, the collection unit scans handwritten drawings with a high-resolution scanner and converts them into text information using OCR technology. Digital image data can be directly collected if submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The analysis unit analyzes the image data collected by the collection unit using a generative AI. The analysis is performed based on, for example, image recognition technology or pattern matching technology, but is not limited to such examples. For example, the generative AI analyzes the image data using a deep learning model. The analysis unit can also extract features of the image data using a generative-opposed network (GAN). Furthermore, the analysis unit can also analyze patterns in image data using generative AI. For example, deep learning models have learned from large amounts of image data and possess advanced image recognition capabilities. Generative counter-networks (GANs) extract image features by generating and identifying image data. Generative AI analyzes patterns in image data and extracts features for evaluating similarity. The evaluation unit evaluates similarity based on the data analyzed by the analysis unit. Similarity is evaluated by methods such as comparing image features or calculating a similarity score, but is not limited to these examples. For example, the evaluation unit calculates a similarity score by comparing image features. The evaluation unit can also evaluate similarity using pattern matching technology. The evaluation unit can also evaluate the similarity of image data using generative AI. For example, the evaluation unit evaluates similarity by vectorizing image features and calculating the distance between vectors. Pattern matching technology compares patterns in image data and evaluates similarity.The generating AI evaluates similarity based on the features of the image data. Some or all of the processing described above in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can evaluate similarity using an AI model that takes data analyzed by the analysis unit as input and outputs similarity. The providing unit provides the evaluation results obtained by the evaluation unit. The provision is performed by methods such as report format or dashboard display, but is not limited to such examples. For example, the providing unit provides the evaluation results in report format. The providing unit can also display the evaluation results on a dashboard. The providing unit can also provide the evaluation results through a notification system. For example, the providing unit generates the evaluation results as a PDF report and provides it to the user. The dashboard display visually displays the evaluation results so that the user can easily understand them. The notification system notifies the user of the evaluation results in real time. As a result, the patent document search AI agent according to the embodiment can efficiently confirm the novelty of patent documents and quickly identify similar designs. Some or all of the processing described above in the providing unit may be performed using AI, for example, or without AI. For example, the provisioning unit can use an AI model that takes the evaluation results obtained by the evaluation unit as input and generates a report to provide the evaluation results. For example, the outputting unit can display the evaluation results to the user through a web application or a mobile application. If feedback in paper format is desired, the results can be printed using a printer. Sending the results via email provides quick feedback by directly sending the results to the user. Some or all of the above processing in the outputting unit may be performed using AI, for example, or without using AI.

[0030] The collection unit collects image data from patent documents. Image data from patent documents includes, but is not limited to, drawings, photographs, and scanned images. For example, the collection unit digitizes and collects handwritten drawings using scanning technology. It can also directly collect image data submitted in digital format. Furthermore, the collection unit can read printed image data using OCR technology. For example, the collection unit scans handwritten drawings with a high-resolution scanner and converts them into text information using OCR technology. Digital image data submitted in specific file formats can be collected directly. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The collection unit centrally manages this data and has established infrastructure for efficient collection. For example, the collection unit uses cloud storage to store large amounts of image data and allows for quick access as needed. The collection unit also implements algorithms to eliminate data duplication and maintain data integrity. This allows the collection unit to efficiently collect image data from patent documents and provide it to the analysis unit. Furthermore, the collection unit can flexibly adjust the frequency and method of data collection. For example, it is possible to set the system to automatically collect data whenever a new patent document is published, or to collect data periodically at specific intervals. This allows the data collection unit to always maintain the latest information and quickly provide the data required by the analysis and evaluation units. The data collection unit can select the optimal collection method according to the type and format of the patent document, enabling efficient and accurate data collection.

[0031] The analysis unit analyzes image data collected by the collection unit using generative AI. The analysis is performed based on, for example, image recognition technology and pattern matching technology, but is not limited to these examples. For example, the generative AI analyzes image data using a deep learning model. The analysis unit can also extract features of image data using a generative opposite network (GAN). The analysis unit can also analyze patterns in image data using generative AI. For example, a deep learning model has been trained on a large amount of image data and has advanced image recognition capabilities. A generative opposite network (GAN) extracts image features by generating and identifying image data. The generative AI analyzes patterns in image data and extracts features for evaluating similarity. The analysis unit combines these technologies to perform a detailed analysis of the image data. For example, a deep learning model can automatically identify and classify specific patterns and features from image data. A generative opposite network (GAN) achieves more accurate feature extraction by repeatedly generating and identifying image data. The analysis unit utilizes these technologies to perform a detailed analysis of image data within patent documents and generates data to provide to the evaluation unit. Furthermore, before providing the analysis results to the evaluation unit, the analysis unit performs a verification process to confirm the integrity and consistency of the data. This allows the analysis unit to provide accurate and reliable data to the evaluation unit. The analysis unit can select the optimal analysis method according to the type and content of the patent document, enabling efficient and accurate data analysis.

[0032] The evaluation unit evaluates similarity based on the data analyzed by the analysis unit. Similarity is evaluated by methods such as comparing image features or calculating a similarity score, but is not limited to these examples. For example, the evaluation unit calculates a similarity score by comparing image features. The evaluation unit can also evaluate similarity using pattern matching technology. The evaluation unit can also evaluate the similarity of image data using generative AI. For example, the evaluation unit evaluates similarity by vectorizing image features and calculating the distance between vectors. Pattern matching technology compares patterns in image data and evaluates similarity. Generative AI evaluates similarity based on the features of image data. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can evaluate similarity using an AI model that takes data analyzed by the analysis unit as input and outputs similarity. The evaluation unit combines these technologies to evaluate the similarity of image data in patent documents with high accuracy. For example, in the comparison of image features, specific features are extracted, vectorized, and compared to calculate a similarity score. Pattern matching technology compares patterns in image data and evaluates similarity. Generative AI evaluates similarity based on the features of the image data. The evaluation unit utilizes these technologies to evaluate the similarity of image data within patent documents with high accuracy and generates data to be provided to the provider. Furthermore, the evaluation unit can verify and re-evaluate the evaluation process to ensure the reliability of the evaluation results. This allows the evaluation unit to provide accurate and reliable evaluation results to the provider. The evaluation unit can select the optimal evaluation method according to the type and content of the patent document, and evaluate the data efficiently and accurately.

[0033] The provisioning unit provides the evaluation results obtained by the evaluation unit. The provision is carried out, for example, in the form of a report or a dashboard display, but is not limited to such examples. For example, the provisioning unit provides the evaluation results in report format. The provisioning unit can also display the evaluation results on a dashboard. Furthermore, the provisioning unit can provide the evaluation results through a notification system. For example, the provisioning unit generates the evaluation results as a PDF report and provides it to the user. The dashboard display visually displays the evaluation results, making them easily understandable to the user. The notification system notifies the user of the evaluation results in real time. This allows the patent document search AI agent according to the embodiment to efficiently verify the novelty of patent documents and quickly identify similar designs. Some or all of the processing described above in the provisioning unit may be performed using, for example, AI, or not using AI. For example, the provisioning unit can provide the evaluation results using an AI model that takes the evaluation results obtained by the evaluation unit as input and generates a report. The provisioning unit combines these techniques to efficiently provide the evaluation results. For example, in report format, the evaluation results are described in detail, making them easily understandable to the user. The dashboard display visually shows evaluation results, allowing users to understand them intuitively. The notification system notifies users of evaluation results in real time, providing prompt feedback. The service provider utilizes these technologies to efficiently deliver evaluation results, enabling users to obtain information quickly and accurately. Furthermore, the service provider can collect user feedback and use it to improve delivery methods and enhance the accuracy of evaluation results. This allows the service provider to provide users with accurate and reliable evaluation results, improving the efficiency of novelty verification and similarity identification of patent documents. The service provider can select the optimal delivery method according to the type and content of the patent document, enabling efficient and accurate delivery of evaluation results.

[0034] The analysis unit can analyze 3D CAD data through a generative AI. For example, the analysis unit inputs 3D CAD data into the generative AI, which then analyzes the data. For example, the generative AI uses a deep learning model to analyze the 3D CAD data. The analysis unit can also extract features from the 3D CAD data using a Generative Parallel Network (GAN). For example, the generative AI analyzes the shape and structure of the 3D CAD data and extracts features. This enables the analysis of the 3D CAD data. For example, the generative AI vectorizes the shape of the 3D CAD data and calculates the distance between the vectors to evaluate similarity. The deep learning model has learned from a large amount of 3D data and possesses advanced shape recognition capabilities. The Generative Parallel Network (GAN) extracts shape features by generating and identifying 3D data. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit inputs 3D CAD data into the generative AI, which then analyzes the data. This allows for efficient analysis of 3D CAD data.

[0035] The evaluation unit can automatically compare data with existing patent databases. For example, the evaluation unit compares data analyzed by the analysis unit with existing patent databases. For example, the evaluation unit evaluates the similarity between image data in the patent database and the analyzed image data. The evaluation unit can also evaluate the similarity between 3D CAD data in the patent database and the analyzed 3D CAD data. For example, the evaluation unit compares image features in the patent database and calculates a similarity score. This enables automatic comparison with existing patent databases. For example, the evaluation unit evaluates similarity by vectorizing the image data in the patent database and calculating the distance between the vectors. Some or all of the above processing in the evaluation unit may be performed using AI, or not using AI. For example, the evaluation unit inputs image data from the patent database into a generating AI, and the generating AI evaluates the similarity. This allows for efficient comparison with patent databases.

[0036] The service provider can provide feedback on the evaluation results. For example, the service provider can provide feedback on the evaluation results to the user. For example, the service provider can provide the evaluation results in report format. The service provider can also display the evaluation results on a dashboard. For example, the service provider can generate the evaluation results as a PDF report and provide it to the user. This enables feedback on the evaluation results. For example, the service provider can notify the user of the evaluation results in real time through a notification system. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider inputs the evaluation results into a generating AI, and the generating AI generates a report. This enables efficient feedback on the evaluation results.

[0037] The collection unit can automatically scan image data within patent documents. For example, the collection unit can read image data within patent documents using a scanner and save it as digital data. The collection unit can also convert image data into text data using OCR technology. For example, the collection unit can read handwritten drawings using a scanner and convert them into text information using OCR technology. The collection unit can also directly collect image data submitted in digital format. This enables the automatic scanning of image data within patent documents. Some or all of the above-described processes in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit inputs image data acquired by the scanner into a generating AI, which then analyzes the data. This allows for efficient automatic scanning of image data.

[0038] The evaluation unit can verify the novelty required for a patent. For example, the evaluation unit evaluates the novelty of a patent based on data analyzed by the analysis unit. For example, the evaluation unit compares the analyzed data with existing patents in the patent database to verify novelty. The evaluation unit can also set criteria for evaluating the novelty of a patent. For example, the evaluation unit evaluates novelty based on the number of similar patents and similarity scores in the patent database. This makes it possible to verify the novelty required for a patent. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs the analyzed data into a generating AI, and the generating AI evaluates the novelty. This makes the verification of novelty more efficient.

[0039] The collection unit can set priorities for the image data to be collected according to the type and field of the patent document. For example, the collection unit prioritizes the collection of image data for patent documents in the medical field. The collection unit can also prioritize the collection of 3D models for patent documents in the automotive field. The collection unit can also prioritize the collection of software-related image data for patent documents in the IT field. This makes it possible to set priorities according to the type and field of the patent document. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit inputs the type and field of the patent document into a generating AI, and the generating AI sets the priorities. This allows for efficient collection of image data.

[0040] The collection unit can acquire update information on patent documents in real time during collection and collect the latest image data. For example, the collection unit can acquire update information on patent documents in real time and collect the latest image data. The collection unit can also reset the priority of the image data to be collected based on the update information. The collection unit can also expand the range of image data to be collected based on the update information. This makes it possible to collect the latest image data based on update information on patent documents. Some or all of the above processing in the collection unit may be performed using AI, for example, or without using AI. For example, the collection unit inputs update information on patent documents into a generating AI, and the generating AI collects the latest image data. This makes it possible to collect the latest image data efficiently.

[0041] The collection unit can efficiently collect image data by classifying it based on the language and region of the patent document during collection. For example, the collection unit can prioritize the collection of English image data for English patent documents. The collection unit can also prioritize the collection of Japanese image data for Japanese patent documents. The collection unit can also classify patent documents by region and efficiently collect image data. This enables the classification and efficient collection of image data based on the language and region of the patent document. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit inputs the language and region of the patent document into a generating AI, and the generating AI classifies the image data. This allows for efficient collection of image data.

[0042] The data collection unit can expand the range of image data to be collected by referring to relevant technical information in the patent document during the collection process. For example, for patent documents in the medical field, the data collection unit can also collect image data in relevant technical fields. For patent documents in the automotive field, the data collection unit can also collect 3D models in relevant technical fields. For patent documents in the IT field, the data collection unit can also collect image data of relevant software. This makes it possible to expand the range of image data by referring to relevant technical information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit inputs relevant technical information from the patent document into a generating AI, and the generating AI expands the range of image data. This makes the collection of image data more efficient.

[0043] The analysis unit can optimize its analysis algorithm during analysis, taking into account the resolution and quality of the image data of the patent document. For example, the analysis unit performs a detailed analysis on high-resolution image data. For low-resolution image data, the analysis unit can analyze only the important parts. The analysis unit can also optimize its analysis algorithm according to the quality of the image data. This makes it possible to optimize the analysis algorithm according to the resolution and quality of the image data. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit inputs the resolution and quality of the image data to a generating AI, and the generating AI optimizes the analysis algorithm. This makes the optimization of the analysis algorithm efficient.

[0044] The analysis unit can extract structural and design features of image data from patent documents during analysis and perform a detailed analysis. For example, the analysis unit can analyze the structure of the image data and extract design features. The analysis unit can also analyze the design of the image data and evaluate its similarity. The analysis unit can also extract features of the image data and perform a detailed analysis. This enables a detailed analysis that extracts structural and design features of the image data. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit inputs the structural and design features of the image data into a generating AI, and the generating AI extracts the features. This allows for efficient detailed analysis.

[0045] The analysis unit can perform analysis while considering the color and shape characteristics of the image data of the patent document. For example, the analysis unit can analyze the color of the image data and extract design features. The analysis unit can also analyze the shape of the image data and evaluate similarity. The analysis unit can also perform detailed analysis while considering the color and shape characteristics of the image data. This makes it possible to perform analysis while considering the color and shape characteristics of the image data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit inputs the color and shape characteristics of the image data into a generating AI, and the generating AI extracts the features. This allows for efficient detailed analysis.

[0046] The analysis unit can improve the accuracy of its analysis by referring to relevant technical documents related to the image data of the patent document during the analysis. For example, the analysis unit can improve the accuracy of its analysis by referring to relevant technical documents. The analysis unit can also perform image data analysis based on the information in the technical documents. The analysis unit can also improve the reliability of its analysis results by referring to relevant technical documents. This makes it possible to improve the accuracy of analysis by referring to relevant technical documents. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit inputs information from relevant technical documents into a generating AI, and the generating AI improves the accuracy of the analysis. This efficiently improves the accuracy of the analysis.

[0047] The evaluation unit can evaluate the similarity of image data of patent documents using multiple evaluation criteria during the evaluation process and perform a comprehensive evaluation. The evaluation unit can evaluate image data using multiple evaluation criteria, such as structure, design, color, and shape. The evaluation unit can also evaluate similarity by comprehensively considering multiple evaluation criteria. The evaluation unit can also perform a comprehensive evaluation by adjusting the weighting of each evaluation criterion. This makes it possible to perform a comprehensive similarity evaluation using multiple evaluation criteria. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit inputs multiple evaluation criteria for image data into a generating AI, and the generating AI performs a comprehensive evaluation. This makes the comprehensive evaluation more efficient.

[0048] The evaluation unit can improve the accuracy of its evaluation by referring to past evaluation results of image data of patent documents during the evaluation process. For example, the evaluation unit can improve the accuracy of its evaluation by referring to past evaluation results. The evaluation unit can also adjust the evaluation criteria based on past evaluation results. The evaluation unit can also improve the reliability of its evaluation results by referring to past evaluation results. As a result, the accuracy of the evaluation is improved by referring to past evaluation results. Some or all of the above-described processes in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit inputs past evaluation results into a generating AI, and the generating AI improves the accuracy of the evaluation. As a result, the accuracy of the evaluation is efficiently improved.

[0049] The evaluation unit can perform evaluations based on the region and language of the image data of the patent documents during the evaluation process. For example, the evaluation unit can classify and evaluate patent documents by region. The evaluation unit can also classify and evaluate patent documents by language. The evaluation unit can also adjust the evaluation criteria based on region and language. This enables evaluations based on region and language. Some or all of the above-described processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs information on the region and language of the patent documents into a generating AI, and the generating AI performs the evaluation. This allows for efficient evaluation.

[0050] The evaluation unit can improve the accuracy of its evaluation by referring to relevant market data for the image data of the patent document during the evaluation process. The evaluation unit can, for example, refer to relevant market data to improve the accuracy of its evaluation. The evaluation unit can also adjust the evaluation criteria based on the market data information. The evaluation unit can also improve the reliability of the evaluation results by referring to relevant market data. As a result, the accuracy of the evaluation is improved by referring to relevant market data. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs information from relevant market data into a generating AI, and the generating AI improves the accuracy of the evaluation. As a result, the accuracy of the evaluation is efficiently improved.

[0051] The service provider can customize the evaluation results of patent documents according to the user's area of ​​interest when providing them. For example, the service provider can customize and provide the evaluation results according to the user's area of ​​interest. The service provider can also adjust the display order of the evaluation results based on the user's area of ​​interest. The service provider can also adjust the level of detail of the evaluation results according to the user's area of ​​interest. This makes it possible to customize the evaluation results according to the user's area of ​​interest. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider inputs information on the user's area of ​​interest into a generating AI, and the generating AI customizes the evaluation results. This makes it possible to customize the evaluation results efficiently.

[0052] The provisioning unit can update the evaluation results of patent documents in real time at the time of provision, providing the latest information. For example, the provisioning unit can update the evaluation results in real time and provide the latest information. The provisioning unit can also adjust the display order of the evaluation results based on the updated information. The provisioning unit can also update the evaluation results in real time and notify the user. This enables real-time updating of evaluation results. Some or all of the above processing in the provisioning unit may be performed using AI, for example, or without using AI. For example, the provisioning unit inputs updated evaluation result information to a generating AI, and the generating AI updates the evaluation results in real time. This enables efficient updating of evaluation results.

[0053] The service provider can display the evaluation results of the patent document optimized for the user's device at the time of provision. For example, if the user is using a smartphone, the service provider provides a display method that matches the screen size. If the user is using a tablet, the service provider can also provide a display method optimized for a larger screen. If the user is using a smartwatch, the service provider can also provide a concise and highly visible display method. This makes it possible to display evaluation results optimized for the user's device. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider inputs the user's device information into a generating AI, and the generating AI provides an optimized display method. This makes the optimization of the display method efficient.

[0054] The provisioning unit can provide evaluation results of patent documents linked to related technical documents at the time of provision. For example, the provisioning unit can provide evaluation results linked to related technical documents. The provisioning unit can also provide evaluation results based on information from related technical documents. The provisioning unit can also provide users with evaluation results linked to related technical documents. This makes it possible to provide links between evaluation results and related technical documents. Some or all of the above processing in the provisioning unit may be performed using AI, for example, or without using AI. For example, the provisioning unit inputs information on evaluation results and related technical documents into a generating AI, and the generating AI generates links. This makes link provision efficient.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The collection unit can prioritize the collection of highly relevant image data by referring to the user's past search history when collecting image data from patent documents. For example, if the user has previously searched for many patent documents in the medical field, the collection unit will prioritize the collection of image data in the medical field. Furthermore, if the user has shown interest in a specific technical field, the collection unit can prioritize the collection of image data in that field. In addition, the collection unit can automatically suggest highly relevant patent documents based on the user's search history. This enables efficient image data collection tailored to the user's interests.

[0057] The collection unit can prioritize the collection of the most recent image data when collecting image data from patent documents, taking into account the publication date and update date of the patent documents. For example, the collection unit can prioritize the collection of patent documents with the most recent publication date. It can also prioritize the collection of patent documents with the most recent update date. Furthermore, the collection unit can set the priority order of the image data to be collected based on the publication date and update date of the patent documents. This enables efficient collection of image data based on the latest information.

[0058] The analysis unit can optimize its analysis algorithm according to the field and category of the patent document when analyzing image data within the patent document. For example, for patent documents in the medical field, an algorithm specialized in medical image analysis can be used. For patent documents in the automotive field, an algorithm specialized in the shape analysis of automotive parts can be used. Furthermore, for patent documents in the IT field, an algorithm specialized in software-related image analysis can be used. This enables optimal analysis according to the field and category of the patent document.

[0059] The evaluation unit can adjust the evaluation criteria based on the country or region of publication of the patent documents when evaluating the similarity of image data of patent documents. For example, if the patent documents are published in different countries, the evaluation criteria based on the patent law of that country will be used. It is also possible to classify patent documents by region and adjust the evaluation criteria accordingly. Furthermore, the reliability of the evaluation results can be improved based on the country or region of publication of the patent documents. This enables appropriate similarity evaluation according to the country or region of publication of the patent documents.

[0060] The service provider can provide evaluation results to users in a display format optimized for their device. For example, if a user is using a smartphone, it can provide a display format that matches the screen size. If a user is using a tablet, it can also provide a display format optimized for the larger screen. Furthermore, if a user is using a smartwatch, it can provide a concise and highly visible display format. This enables the display of evaluation results optimized for the user's device.

[0061] The data collection unit can expand the range of image data collected by referring to information on the relevant technical field when collecting image data within patent documents. For example, for patent documents in the medical field, it can also collect image data in the relevant technical field. For patent documents in the automotive field, it can also collect 3D models in the relevant technical field. Furthermore, for patent documents in the IT field, it can also collect image data of the relevant software. This makes it possible to expand the range of image data by referring to information on the relevant technical field.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The collection unit collects image data from the patent document. Image data from the patent document includes drawings, photographs, scanned images, etc. The collection unit digitizes and collects handwritten drawings using scanning technology. It can also directly collect image data submitted in digital format. Furthermore, it can read printed image data using OCR technology. Step 2: The analysis unit uses a generative AI to analyze the image data collected by the collection unit. The analysis is performed based on image recognition technology and pattern matching technology. The generative AI uses deep learning models and generative opposite networks (GANs) to extract features from the image data and analyze patterns. Step 3: The evaluation unit evaluates similarity based on the data analyzed by the analysis unit. Similarity is evaluated by methods such as comparing image features and calculating similarity scores. The evaluation unit evaluates similarity by vectorizing the image features and calculating the distance between the vectors. Step 4: The delivery unit provides the evaluation results obtained by the evaluation unit. This is done through report formats, dashboard displays, and notification systems. For example, the evaluation results are generated as a PDF report and provided to the user.

[0064] (Example of form 2) The patent document search AI agent according to an embodiment of the present invention is a system that automatically collects image data within patent documents, analyzes it using a generating AI, and evaluates its similarity to existing designs and structures. This system automatically scans image data within patent documents and evaluates its similarity to other existing designs and structures, thereby efficiently confirming the novelty required for patents and quickly identifying similar designs. For example, the patent document search AI agent collects image data within patent documents. For example, the patent document search AI agent can scan handwritten drawings or photographs and convert them into digital data, or it can directly input data in digital format. This data is converted into a format that is easy for the generating AI to analyze. Next, the patent document search AI agent analyzes the image data within patent documents using the generating AI. The input to the generating AI is the image data within the patent documents themselves, and the generating AI performs analysis based on its content. For example, the generating AI receives a prompt such as "Please extract the features of this image," and extracts and analyzes the features of the image. Next, the patent document search AI agent evaluates the similarity between the data analyzed by the generating AI and a pre-prepared existing patent database. Image recognition technology and pattern matching technology are used to evaluate similarity. For example, a generating AI compares image features and calculates a similarity score. Next, a patent document search AI agent evaluates the novelty of the patent document based on the similarity score. For example, a lower similarity score indicates higher novelty. The final evaluation result is fed back to the user. This allows the user to quickly and accurately verify the novelty of the patent document. The patent document search AI agent also analyzes 3D CAD data through the generating AI and automatically compares it with existing patent databases. For example, for a new design of an automobile part, it automatically searches for existing similar parts and evaluates the possibility of it being a new application. This automates the patent document search process, significantly reducing search time and costs. The highly accurate similarity evaluation by AI reduces human oversight and variability due to subjective judgment. As a result, the novelty of patents is confirmed more reliably, and risk management is strengthened.Furthermore, rapid feedback makes the design process and strategic patent acquisition more effective. This allows the patent document search AI agent to efficiently verify the novelty of patent documents and quickly identify similar designs.

[0065] The patent document search AI agent according to this embodiment comprises a collection unit, an analysis unit, an evaluation unit, and a provision unit. The collection unit collects image data within patent documents. Image data within patent documents includes, but is not limited to, drawings, photographs, scanned images, etc. The collection unit can, for example, digitize and collect handwritten drawings using scanning technology. The collection unit can also directly collect image data submitted in digital format. Furthermore, the collection unit can read printed image data using OCR technology. For example, the collection unit scans handwritten drawings with a high-resolution scanner and converts them into text information using OCR technology. Digital image data can be directly collected if submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The analysis unit analyzes the image data collected by the collection unit using a generative AI. The analysis is performed based on, for example, image recognition technology or pattern matching technology, but is not limited to such examples. For example, the generative AI analyzes the image data using a deep learning model. The analysis unit can also extract features of the image data using a generative-opposed network (GAN). Furthermore, the analysis unit can also analyze patterns in image data using generative AI. For example, deep learning models have learned from large amounts of image data and possess advanced image recognition capabilities. Generative counter-networks (GANs) extract image features by generating and identifying image data. Generative AI analyzes patterns in image data and extracts features for evaluating similarity. The evaluation unit evaluates similarity based on the data analyzed by the analysis unit. Similarity is evaluated by methods such as comparing image features or calculating a similarity score, but is not limited to these examples. For example, the evaluation unit calculates a similarity score by comparing image features. The evaluation unit can also evaluate similarity using pattern matching technology. The evaluation unit can also evaluate the similarity of image data using generative AI. For example, the evaluation unit evaluates similarity by vectorizing image features and calculating the distance between vectors. Pattern matching technology compares patterns in image data and evaluates similarity.The generating AI evaluates similarity based on the features of the image data. Some or all of the processing described above in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can evaluate similarity using an AI model that takes data analyzed by the analysis unit as input and outputs similarity. The providing unit provides the evaluation results obtained by the evaluation unit. The provision is performed by methods such as report format or dashboard display, but is not limited to such examples. For example, the providing unit provides the evaluation results in report format. The providing unit can also display the evaluation results on a dashboard. The providing unit can also provide the evaluation results through a notification system. For example, the providing unit generates the evaluation results as a PDF report and provides it to the user. The dashboard display visually displays the evaluation results so that the user can easily understand them. The notification system notifies the user of the evaluation results in real time. As a result, the patent document search AI agent according to the embodiment can efficiently confirm the novelty of patent documents and quickly identify similar designs. Some or all of the processing described above in the providing unit may be performed using AI, for example, or without AI. For example, the provisioning unit can use an AI model that takes the evaluation results obtained by the evaluation unit as input and generates a report to provide the evaluation results. For example, the outputting unit can display the evaluation results to the user through a web application or a mobile application. If feedback in paper format is desired, the results can be printed using a printer. Sending the results via email provides quick feedback by directly sending the results to the user. Some or all of the above processing in the outputting unit may be performed using AI, for example, or without using AI.

[0066] The collection unit collects image data from patent documents. Image data from patent documents includes, but is not limited to, drawings, photographs, and scanned images. For example, the collection unit digitizes and collects handwritten drawings using scanning technology. It can also directly collect image data submitted in digital format. Furthermore, the collection unit can read printed image data using OCR technology. For example, the collection unit scans handwritten drawings with a high-resolution scanner and converts them into text information using OCR technology. Digital image data submitted in specific file formats can be collected directly. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The collection unit centrally manages this data and has established infrastructure for efficient collection. For example, the collection unit uses cloud storage to store large amounts of image data and allows for quick access as needed. The collection unit also implements algorithms to eliminate data duplication and maintain data integrity. This allows the collection unit to efficiently collect image data from patent documents and provide it to the analysis unit. Furthermore, the collection unit can flexibly adjust the frequency and method of data collection. For example, it is possible to set the system to automatically collect data whenever a new patent document is published, or to collect data periodically at specific intervals. This allows the data collection unit to always maintain the latest information and quickly provide the data required by the analysis and evaluation units. The data collection unit can select the optimal collection method according to the type and format of the patent document, enabling efficient and accurate data collection.

[0067] The analysis unit analyzes image data collected by the collection unit using generative AI. The analysis is performed based on, for example, image recognition technology and pattern matching technology, but is not limited to these examples. For example, the generative AI analyzes image data using a deep learning model. The analysis unit can also extract features of image data using a generative opposite network (GAN). The analysis unit can also analyze patterns in image data using generative AI. For example, a deep learning model has been trained on a large amount of image data and has advanced image recognition capabilities. A generative opposite network (GAN) extracts image features by generating and identifying image data. The generative AI analyzes patterns in image data and extracts features for evaluating similarity. The analysis unit combines these technologies to perform a detailed analysis of the image data. For example, a deep learning model can automatically identify and classify specific patterns and features from image data. A generative opposite network (GAN) achieves more accurate feature extraction by repeatedly generating and identifying image data. The analysis unit utilizes these technologies to perform a detailed analysis of image data within patent documents and generates data to provide to the evaluation unit. Furthermore, before providing the analysis results to the evaluation unit, the analysis unit performs a verification process to confirm the integrity and consistency of the data. This allows the analysis unit to provide accurate and reliable data to the evaluation unit. The analysis unit can select the optimal analysis method according to the type and content of the patent document, enabling efficient and accurate data analysis.

[0068] The evaluation unit evaluates similarity based on the data analyzed by the analysis unit. Similarity is evaluated by methods such as comparing image features or calculating a similarity score, but is not limited to these examples. For example, the evaluation unit calculates a similarity score by comparing image features. The evaluation unit can also evaluate similarity using pattern matching technology. The evaluation unit can also evaluate the similarity of image data using generative AI. For example, the evaluation unit evaluates similarity by vectorizing image features and calculating the distance between vectors. Pattern matching technology compares patterns in image data and evaluates similarity. Generative AI evaluates similarity based on the features of image data. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can evaluate similarity using an AI model that takes data analyzed by the analysis unit as input and outputs similarity. The evaluation unit combines these technologies to evaluate the similarity of image data in patent documents with high accuracy. For example, in the comparison of image features, specific features are extracted, vectorized, and compared to calculate a similarity score. Pattern matching technology compares patterns in image data and evaluates similarity. Generative AI evaluates similarity based on the features of the image data. The evaluation unit utilizes these technologies to evaluate the similarity of image data within patent documents with high accuracy and generates data to be provided to the provider. Furthermore, the evaluation unit can verify and re-evaluate the evaluation process to ensure the reliability of the evaluation results. This allows the evaluation unit to provide accurate and reliable evaluation results to the provider. The evaluation unit can select the optimal evaluation method according to the type and content of the patent document, and evaluate the data efficiently and accurately.

[0069] The provisioning unit provides the evaluation results obtained by the evaluation unit. The provision is carried out, for example, in the form of a report or a dashboard display, but is not limited to such examples. For example, the provisioning unit provides the evaluation results in report format. The provisioning unit can also display the evaluation results on a dashboard. Furthermore, the provisioning unit can provide the evaluation results through a notification system. For example, the provisioning unit generates the evaluation results as a PDF report and provides it to the user. The dashboard display visually displays the evaluation results, making them easily understandable to the user. The notification system notifies the user of the evaluation results in real time. This allows the patent document search AI agent according to the embodiment to efficiently verify the novelty of patent documents and quickly identify similar designs. Some or all of the processing described above in the provisioning unit may be performed using, for example, AI, or not using AI. For example, the provisioning unit can provide the evaluation results using an AI model that takes the evaluation results obtained by the evaluation unit as input and generates a report. The provisioning unit combines these techniques to efficiently provide the evaluation results. For example, in report format, the evaluation results are described in detail, making them easily understandable to the user. The dashboard display visually shows evaluation results, allowing users to understand them intuitively. The notification system notifies users of evaluation results in real time, providing prompt feedback. The service provider utilizes these technologies to efficiently deliver evaluation results, enabling users to obtain information quickly and accurately. Furthermore, the service provider can collect user feedback and use it to improve delivery methods and enhance the accuracy of evaluation results. This allows the service provider to provide users with accurate and reliable evaluation results, improving the efficiency of novelty verification and similarity identification of patent documents. The service provider can select the optimal delivery method according to the type and content of the patent document, enabling efficient and accurate delivery of evaluation results.

[0070] The analysis unit can analyze 3D CAD data through a generative AI. For example, the analysis unit inputs 3D CAD data into the generative AI, which then analyzes the data. For example, the generative AI uses a deep learning model to analyze the 3D CAD data. The analysis unit can also extract features from the 3D CAD data using a Generative Parallel Network (GAN). For example, the generative AI analyzes the shape and structure of the 3D CAD data and extracts features. This enables the analysis of the 3D CAD data. For example, the generative AI vectorizes the shape of the 3D CAD data and calculates the distance between the vectors to evaluate similarity. The deep learning model has learned from a large amount of 3D data and possesses advanced shape recognition capabilities. The Generative Parallel Network (GAN) extracts shape features by generating and identifying 3D data. Some or all of the above-described processes in the analysis unit may be performed using AI, or without AI. For example, the analysis unit inputs 3D CAD data into the generative AI, which then analyzes the data. This allows for efficient analysis of 3D CAD data.

[0071] The evaluation unit can automatically compare data with existing patent databases. For example, the evaluation unit compares data analyzed by the analysis unit with existing patent databases. For example, the evaluation unit evaluates the similarity between image data in the patent database and the analyzed image data. The evaluation unit can also evaluate the similarity between 3D CAD data in the patent database and the analyzed 3D CAD data. For example, the evaluation unit compares image features in the patent database and calculates a similarity score. This enables automatic comparison with existing patent databases. For example, the evaluation unit evaluates similarity by vectorizing the image data in the patent database and calculating the distance between the vectors. Some or all of the above processing in the evaluation unit may be performed using AI, or not using AI. For example, the evaluation unit inputs image data from the patent database into a generating AI, and the generating AI evaluates the similarity. This allows for efficient comparison with patent databases.

[0072] The service provider can provide feedback on the evaluation results. For example, the service provider can provide feedback on the evaluation results to the user. For example, the service provider can provide the evaluation results in report format. The service provider can also display the evaluation results on a dashboard. For example, the service provider can generate the evaluation results as a PDF report and provide it to the user. This enables feedback on the evaluation results. For example, the service provider can notify the user of the evaluation results in real time through a notification system. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider inputs the evaluation results into a generating AI, and the generating AI generates a report. This enables efficient feedback on the evaluation results.

[0073] The collection unit can automatically scan image data within patent documents. For example, the collection unit can read image data within patent documents using a scanner and save it as digital data. The collection unit can also convert image data into text data using OCR technology. For example, the collection unit can read handwritten drawings using a scanner and convert them into text information using OCR technology. The collection unit can also directly collect image data submitted in digital format. This enables the automatic scanning of image data within patent documents. Some or all of the above-described processes in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit inputs image data acquired by the scanner into a generating AI, which then analyzes the data. This allows for efficient automatic scanning of image data.

[0074] The evaluation unit can verify the novelty required for a patent. For example, the evaluation unit evaluates the novelty of a patent based on data analyzed by the analysis unit. For example, the evaluation unit compares the analyzed data with existing patents in the patent database to verify novelty. The evaluation unit can also set criteria for evaluating the novelty of a patent. For example, the evaluation unit evaluates novelty based on the number of similar patents and similarity scores in the patent database. This makes it possible to verify the novelty required for a patent. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs the analyzed data into a generating AI, and the generating AI evaluates the novelty. This makes the verification of novelty more efficient.

[0075] The data collection unit can estimate the user's emotions and adjust the timing of image data collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can delay the collection timing and wait until the user is relaxed. If the user is concentrating, the data collection unit can also speed up the collection timing to collect data efficiently. If the user is tired, the data collection unit can adjust the collection timing to reduce the user's burden. This makes it possible to adjust the collection timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, or not using AI. For example, the data collection unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotions. This allows for efficient adjustment of the collection timing.

[0076] The collection unit can set priorities for the image data to be collected according to the type and field of the patent document. For example, the collection unit prioritizes the collection of image data for patent documents in the medical field. The collection unit can also prioritize the collection of 3D models for patent documents in the automotive field. The collection unit can also prioritize the collection of software-related image data for patent documents in the IT field. This makes it possible to set priorities according to the type and field of the patent document. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit inputs the type and field of the patent document into a generating AI, and the generating AI sets the priorities. This allows for efficient collection of image data.

[0077] The collection unit can acquire update information on patent documents in real time during collection and collect the latest image data. For example, the collection unit can acquire update information on patent documents in real time and collect the latest image data. The collection unit can also reset the priority of the image data to be collected based on the update information. The collection unit can also expand the range of image data to be collected based on the update information. This makes it possible to collect the latest image data based on update information on patent documents. Some or all of the above processing in the collection unit may be performed using AI, for example, or without using AI. For example, the collection unit inputs update information on patent documents into a generating AI, and the generating AI collects the latest image data. This makes it possible to collect the latest image data efficiently.

[0078] The data collection unit can estimate the user's emotions and filter the collected image data based on the estimated emotions. For example, if the user is relaxed, the data collection unit can collect detailed image data. If the user is in a hurry, the data collection unit can also collect only important image data. If the user is excited, the data collection unit can also collect visually stimulating image data. This enables filtering of image data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, or not using AI. For example, the data collection unit inputs the user's facial expression data into a generative AI, which then estimates the emotions. This allows for efficient filtering of image data.

[0079] The collection unit can efficiently collect image data by classifying it based on the language and region of the patent document during collection. For example, the collection unit can prioritize the collection of English image data for English patent documents. The collection unit can also prioritize the collection of Japanese image data for Japanese patent documents. The collection unit can also classify patent documents by region and efficiently collect image data. This enables the classification and efficient collection of image data based on the language and region of the patent document. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit inputs the language and region of the patent document into a generating AI, and the generating AI classifies the image data. This allows for efficient collection of image data.

[0080] The data collection unit can expand the range of image data to be collected by referring to relevant technical information in the patent document during the collection process. For example, for patent documents in the medical field, the data collection unit can also collect image data in relevant technical fields. For patent documents in the automotive field, the data collection unit can also collect 3D models in relevant technical fields. For patent documents in the IT field, the data collection unit can also collect image data of relevant software. This makes it possible to expand the range of image data by referring to relevant technical information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit inputs relevant technical information from the patent document into a generating AI, and the generating AI expands the range of image data. This makes the collection of image data more efficient.

[0081] The analysis unit can estimate the user's emotions and adjust the level of detail of the analysis based on the estimated emotions. For example, if the user is relaxed, the analysis unit will perform a detailed analysis. If the user is in a hurry, the analysis unit can also analyze only the important parts. If the user is excited, the analysis unit can also provide visually stimulating analysis results. This allows for adjustment of the level of detail of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotions. This allows for efficient adjustment of the level of detail of the analysis.

[0082] The analysis unit can optimize its analysis algorithm during analysis, taking into account the resolution and quality of the image data of the patent document. For example, the analysis unit performs a detailed analysis on high-resolution image data. For low-resolution image data, the analysis unit can analyze only the important parts. The analysis unit can also optimize its analysis algorithm according to the quality of the image data. This makes it possible to optimize the analysis algorithm according to the resolution and quality of the image data. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit inputs the resolution and quality of the image data to a generating AI, and the generating AI optimizes the analysis algorithm. This makes the optimization of the analysis algorithm efficient.

[0083] The analysis unit can extract structural and design features of image data from patent documents during analysis and perform a detailed analysis. For example, the analysis unit can analyze the structure of the image data and extract design features. The analysis unit can also analyze the design of the image data and evaluate its similarity. The analysis unit can also extract features of the image data and perform a detailed analysis. This enables a detailed analysis that extracts structural and design features of the image data. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit inputs the structural and design features of the image data into a generating AI, and the generating AI extracts the features. This allows for efficient detailed analysis.

[0084] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is tense, the analysis unit provides a simple and highly visible display method. If the user is relaxed, the analysis unit can also provide a display method that includes detailed information. If the user is in a hurry, the analysis unit can also provide a display method that gets straight to the point. This makes it possible to adjust the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is 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 processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotions. This allows for efficient adjustment of the display method.

[0085] The analysis unit can perform analysis while considering the color and shape characteristics of the image data of the patent document. For example, the analysis unit can analyze the color of the image data and extract design features. The analysis unit can also analyze the shape of the image data and evaluate similarity. The analysis unit can also perform detailed analysis while considering the color and shape characteristics of the image data. This makes it possible to perform analysis while considering the color and shape characteristics of the image data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit inputs the color and shape characteristics of the image data into a generating AI, and the generating AI extracts the features. This allows for efficient detailed analysis.

[0086] The analysis unit can improve the accuracy of its analysis by referring to relevant technical documents related to the image data of the patent document during the analysis. For example, the analysis unit can improve the accuracy of its analysis by referring to relevant technical documents. The analysis unit can also perform image data analysis based on the information in the technical documents. The analysis unit can also improve the reliability of its analysis results by referring to relevant technical documents. This makes it possible to improve the accuracy of analysis by referring to relevant technical documents. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit inputs information from relevant technical documents into a generating AI, and the generating AI improves the accuracy of the analysis. This efficiently improves the accuracy of the analysis.

[0087] The evaluation unit can estimate the user's emotions and adjust the similarity evaluation criteria based on the estimated user emotions. For example, if the user is relaxed, the evaluation unit can perform a detailed similarity evaluation. If the user is in a hurry, the evaluation unit can evaluate only the important parts. If the user is excited, the evaluation unit can provide visually stimulating evaluation results. This makes it possible to adjust the similarity evaluation criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI or not using AI. For example, the evaluation unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotions. This allows for efficient adjustment of the similarity evaluation criteria.

[0088] The evaluation unit can evaluate the similarity of image data of patent documents using multiple evaluation criteria during the evaluation process and perform a comprehensive evaluation. The evaluation unit can evaluate image data using multiple evaluation criteria, such as structure, design, color, and shape. The evaluation unit can also evaluate similarity by comprehensively considering multiple evaluation criteria. The evaluation unit can also perform a comprehensive evaluation by adjusting the weighting of each evaluation criterion. This makes it possible to perform a comprehensive similarity evaluation using multiple evaluation criteria. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit inputs multiple evaluation criteria for image data into a generating AI, and the generating AI performs a comprehensive evaluation. This makes the comprehensive evaluation more efficient.

[0089] The evaluation unit can improve the accuracy of its evaluation by referring to past evaluation results of image data of patent documents during the evaluation process. For example, the evaluation unit can improve the accuracy of its evaluation by referring to past evaluation results. The evaluation unit can also adjust the evaluation criteria based on past evaluation results. The evaluation unit can also improve the reliability of its evaluation results by referring to past evaluation results. As a result, the accuracy of the evaluation is improved by referring to past evaluation results. Some or all of the above-described processes in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit inputs past evaluation results into a generating AI, and the generating AI improves the accuracy of the evaluation. As a result, the accuracy of the evaluation is efficiently improved.

[0090] The evaluation unit can estimate the user's emotions and adjust the display order of the evaluation results based on the estimated emotions. For example, if the user is nervous, the evaluation unit will display important evaluation results first. If the user is relaxed, the evaluation unit may also display detailed evaluation results. If the user is in a hurry, the evaluation unit may also display concise evaluation results. This makes it possible to adjust the display order of evaluation results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI, or not using AI. For example, the evaluation unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotions. This allows for efficient adjustment of the display order.

[0091] The evaluation unit can perform evaluations based on the region and language of the image data of the patent documents during the evaluation process. For example, the evaluation unit can classify and evaluate patent documents by region. The evaluation unit can also classify and evaluate patent documents by language. The evaluation unit can also adjust the evaluation criteria based on region and language. This enables evaluations based on region and language. Some or all of the above-described processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs information on the region and language of the patent documents into a generating AI, and the generating AI performs the evaluation. This allows for efficient evaluation.

[0092] The evaluation unit can improve the accuracy of its evaluation by referring to relevant market data for the image data of the patent document during the evaluation process. The evaluation unit can, for example, refer to relevant market data to improve the accuracy of its evaluation. The evaluation unit can also adjust the evaluation criteria based on the market data information. The evaluation unit can also improve the reliability of the evaluation results by referring to relevant market data. As a result, the accuracy of the evaluation is improved by referring to relevant market data. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs information from relevant market data into a generating AI, and the generating AI improves the accuracy of the evaluation. As a result, the accuracy of the evaluation is efficiently improved.

[0093] The service provider can estimate the user's emotions and adjust the method of providing evaluation results based on the estimated emotions. For example, if the user is nervous, the service provider can provide a simple and highly visible method of providing results. If the user is relaxed, the service provider can also provide a method of providing results that includes detailed information. If the user is in a hurry, the service provider can also provide a method that gets straight to the point. This makes it possible to adjust the method of providing evaluation results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not using AI. For example, the service provider inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotions. This allows for efficient adjustment of the method of providing results.

[0094] The service provider can customize the evaluation results of patent documents according to the user's area of ​​interest when providing them. For example, the service provider can customize and provide the evaluation results according to the user's area of ​​interest. The service provider can also adjust the display order of the evaluation results based on the user's area of ​​interest. The service provider can also adjust the level of detail of the evaluation results according to the user's area of ​​interest. This makes it possible to customize the evaluation results according to the user's area of ​​interest. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider inputs information on the user's area of ​​interest into a generating AI, and the generating AI customizes the evaluation results. This makes it possible to customize the evaluation results efficiently.

[0095] The provisioning unit can update the evaluation results of patent documents in real time at the time of provision, providing the latest information. For example, the provisioning unit can update the evaluation results in real time and provide the latest information. The provisioning unit can also adjust the display order of the evaluation results based on the updated information. The provisioning unit can also update the evaluation results in real time and notify the user. This enables real-time updating of evaluation results. Some or all of the above processing in the provisioning unit may be performed using AI, for example, or without using AI. For example, the provisioning unit inputs updated evaluation result information to a generating AI, and the generating AI updates the evaluation results in real time. This enables efficient updating of evaluation results.

[0096] The service provider can estimate the user's emotions and adjust the notification method of the evaluation results based on the estimated emotions. For example, if the user is nervous, the service provider can provide a simple and highly visible notification method. If the user is relaxed, the service provider can also provide a notification method that includes detailed information. If the user is in a hurry, the service provider can also provide a notification method that gets straight to the point. This makes it possible to adjust the notification method of the evaluation results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not using AI. For example, the service provider inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotions. This allows for efficient adjustment of the notification method.

[0097] The service provider can display the evaluation results of the patent document optimized for the user's device at the time of provision. For example, if the user is using a smartphone, the service provider provides a display method that matches the screen size. If the user is using a tablet, the service provider can also provide a display method optimized for a larger screen. If the user is using a smartwatch, the service provider can also provide a concise and highly visible display method. This makes it possible to display evaluation results optimized for the user's device. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider inputs the user's device information into a generating AI, and the generating AI provides an optimized display method. This makes the optimization of the display method efficient.

[0098] The provisioning unit can provide evaluation results of patent documents linked to related technical documents at the time of provision. For example, the provisioning unit can provide evaluation results linked to related technical documents. The provisioning unit can also provide evaluation results based on information from related technical documents. The provisioning unit can also provide users with evaluation results linked to related technical documents. This makes it possible to provide links between evaluation results and related technical documents. Some or all of the above processing in the provisioning unit may be performed using AI, for example, or without using AI. For example, the provisioning unit inputs information on evaluation results and related technical documents into a generating AI, and the generating AI generates links. This makes link provision efficient.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The collection unit can prioritize the collection of highly relevant image data by referring to the user's past search history when collecting image data from patent documents. For example, if the user has previously searched for many patent documents in the medical field, the collection unit will prioritize the collection of image data in the medical field. Furthermore, if the user has shown interest in a specific technical field, the collection unit can prioritize the collection of image data in that field. In addition, the collection unit can automatically suggest highly relevant patent documents based on the user's search history. This enables efficient image data collection tailored to the user's interests.

[0101] The analysis unit can estimate the user's emotions when analyzing image data within patent documents and adjust the depth of the analysis based on the estimated user emotions. For example, if the user is relaxed, a detailed analysis can be performed. If the user is in a hurry, only the important parts can be analyzed. If the user is excited, visually stimulating analysis results can be provided. This makes it possible to adjust the depth of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without using AI.

[0102] The evaluation unit can estimate the user's emotions when evaluating the similarity of image data in patent documents and adjust the evaluation criteria based on the estimated user emotions. For example, if the user is relaxed, a detailed similarity evaluation can be performed. If the user is in a hurry, only the important parts can be evaluated. If the user is excited, visually stimulating evaluation results can be provided. This makes it possible to adjust the similarity evaluation criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI.

[0103] The delivery unit can estimate the user's emotions when providing feedback on evaluation results to the user and adjust the delivery method based on the estimated emotions. For example, if the user is nervous, a simple and highly visible delivery method can be provided. If the user is relaxed, a delivery method including detailed information can be provided. If the user is in a hurry, a delivery method that gets straight to the point can be provided. This makes it possible to adjust the delivery method of evaluation results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without using AI.

[0104] The collection unit can prioritize the collection of the most recent image data when collecting image data from patent documents, taking into account the publication date and update date of the patent documents. For example, the collection unit can prioritize the collection of patent documents with the most recent publication date. It can also prioritize the collection of patent documents with the most recent update date. Furthermore, the collection unit can set the priority order of the image data to be collected based on the publication date and update date of the patent documents. This enables efficient collection of image data based on the latest information.

[0105] The analysis unit can optimize its analysis algorithm according to the field and category of the patent document when analyzing image data within the patent document. For example, for patent documents in the medical field, an algorithm specialized in medical image analysis can be used. For patent documents in the automotive field, an algorithm specialized in the shape analysis of automotive parts can be used. Furthermore, for patent documents in the IT field, an algorithm specialized in software-related image analysis can be used. This enables optimal analysis according to the field and category of the patent document.

[0106] The evaluation unit can adjust the evaluation criteria based on the country or region of publication of the patent documents when evaluating the similarity of image data of patent documents. For example, if the patent documents are published in different countries, the evaluation criteria based on the patent law of that country will be used. It is also possible to classify patent documents by region and adjust the evaluation criteria accordingly. Furthermore, the reliability of the evaluation results can be improved based on the country or region of publication of the patent documents. This enables appropriate similarity evaluation according to the country or region of publication of the patent documents.

[0107] The service provider can provide evaluation results to users in a display format optimized for their device. For example, if a user is using a smartphone, it can provide a display format that matches the screen size. If a user is using a tablet, it can also provide a display format optimized for the larger screen. Furthermore, if a user is using a smartwatch, it can provide a concise and highly visible display format. This enables the display of evaluation results optimized for the user's device.

[0108] The data collection unit can expand the range of image data collected by referring to information on the relevant technical field when collecting image data within patent documents. For example, for patent documents in the medical field, it can also collect image data in the relevant technical field. For patent documents in the automotive field, it can also collect 3D models in the relevant technical field. Furthermore, for patent documents in the IT field, it can also collect image data of the relevant software. This makes it possible to expand the range of image data by referring to information on the relevant technical field.

[0109] The analysis unit can estimate the user's emotions when analyzing image data within the patent document and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is tense, a simple and highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. If the user is in a hurry, a display method that gets straight to the point can be provided. This makes it possible to adjust the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is 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 processing in the analysis unit may be performed using AI, for example, or without using AI.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The collection unit collects image data from the patent document. Image data from the patent document includes drawings, photographs, scanned images, etc. The collection unit digitizes and collects handwritten drawings using scanning technology. It can also directly collect image data submitted in digital format. Furthermore, it can read printed image data using OCR technology. Step 2: The analysis unit uses a generative AI to analyze the image data collected by the collection unit. The analysis is performed based on image recognition technology and pattern matching technology. The generative AI uses deep learning models and generative opposite networks (GANs) to extract features from the image data and analyze patterns. Step 3: The evaluation unit evaluates similarity based on the data analyzed by the analysis unit. Similarity is evaluated by methods such as comparing image features and calculating similarity scores. The evaluation unit evaluates similarity by vectorizing the image features and calculating the distance between the vectors. Step 4: The delivery unit provides the evaluation results obtained by the evaluation unit. This is done through report formats, dashboard displays, and notification systems. For example, the evaluation results are generated as a PDF report and provided to the user.

[0112] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0114] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0115] Each of the multiple elements described above, including the collection unit, analysis unit, evaluation unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects image data from the patent document using the camera 42 or scanner of the smart device 14. The analysis unit is implemented in the specific processing unit 290 of the data processing device 12 and analyzes the image data using a generation AI. The evaluation unit is implemented in the specific processing unit 290 of the data processing device 12 and evaluates the similarity based on the analyzed data. The provision unit is implemented in the control unit 46A of the smart device 14 and provides the evaluation results to the user. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0120] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0122] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0123] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0124] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0125] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0126] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0130] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] Each of the multiple elements described above, including the collection unit, analysis unit, evaluation unit, and provision unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects image data from the patent document using the camera 42 or scanner of the smart glasses 214. The analysis unit is implemented, for example, in the identification processing unit 290 of the data processing device 12, and analyzes the image data using a generation AI. The evaluation unit is implemented, for example, in the identification processing unit 290 of the data processing device 12, and evaluates the similarity based on the analyzed data. The provision unit is implemented, for example, in the control unit 46A of the smart glasses 214, and provides the evaluation results to the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0134] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0135] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0136] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0138] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0139] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0140] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0141] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0142] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0144] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0147] Each of the multiple elements described above, including the collection unit, analysis unit, evaluation unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects image data from the patent document using the camera 42 and scanner of the headset terminal 314. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the image data using a generation AI. The evaluation unit is implemented in the specific processing unit 290 of the data processing unit 12 and evaluates the similarity based on the analyzed data. The provision unit is implemented in the control unit 46A of the headset terminal 314 and provides the evaluation results to the user. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0151] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0152] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0154] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0155] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0156] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0157] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0158] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0159] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0161] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0162] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0164] Each of the multiple elements described above, including the collection unit, analysis unit, evaluation unit, and provision unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects image data from the patent document using the camera 42 and scanner of the robot 414. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and analyzes the image data using a generation AI. The evaluation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and evaluates the similarity based on the analyzed data. The provision unit is implemented, for example, by the control unit 46A of the robot 414, and provides the evaluation results to the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0165] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0166] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0167] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0168] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0169] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0170] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0171] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0172] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0173] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0174] 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.

[0175] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0176] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0177] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0178] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0179] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0180] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0181] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0182] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0183] (Note 1) A collection unit that collects image data from patent documents, An analysis unit analyzes the image data collected by the aforementioned collection unit, An evaluation unit that evaluates similarity based on the data analyzed by the analysis unit, The system includes a providing unit that provides evaluation results obtained by the evaluation unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, 3D CAD data is generated and analyzed using AI. The system described in Appendix 1, characterized by the features described herein. (Note 3) The evaluation unit described above, Automatically compares with existing patent databases. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, Provide feedback on the evaluation results. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is Automatically scans image data within patent documents. The system described in Appendix 1, characterized by the features described herein. (Note 6) The evaluation unit described above, Confirm the novelty required for a patent. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of image data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Prioritize the image data to be collected according to the type and field of the patent document. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is During data collection, the system acquires updated patent information in real time and collects the latest image data. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates the user's emotions and filters the collected image data based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is During collection, image data is classified based on the language and region of the patent documents to ensure efficient collection. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is During data collection, the scope of image data to be collected is expanded by referring to relevant technical information in patent documents. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts the level of detail in the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, the analysis algorithm is optimized considering the resolution and quality of the image data in the patent documents. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During the analysis, the structural and design features of the image data from the patent document are extracted, and a detailed analysis is performed. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During the analysis, the color and shape characteristics of the image data in the patent document are taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the accuracy of the analysis is improved by referring to related technical documents for the image data in the patent documents. The system described in Appendix 1, characterized by the features described herein. (Note 19) The evaluation unit described above, The system estimates user sentiment and adjusts the similarity evaluation criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The evaluation unit described above, During the evaluation, the similarity of image data from patent documents is assessed using multiple evaluation criteria, and an overall evaluation is performed. The system described in Appendix 1, characterized by the features described herein. (Note 21) The evaluation unit described above, During evaluation, the accuracy of the evaluation is improved by referring to past evaluation results of image data from patent documents. The system described in Appendix 1, characterized by the features described herein. (Note 22) The evaluation unit described above, The system estimates the user's emotions and adjusts the display order of evaluation results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The evaluation unit described above, During the evaluation, the evaluation is based on the region and language of the image data in the patent document. The system described in Appendix 1, characterized by the features described herein. (Note 24) The evaluation unit described above, During evaluation, we improve the accuracy of the evaluation by referring to relevant market data for the image data of the patent documents. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, We estimate the user's emotions and adjust the way evaluation results are provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing the patent information, the evaluation results will be customized according to the user's area of ​​interest. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing information, the evaluation results of patent documents will be updated in real time to provide the latest information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, The system estimates the user's emotions and adjusts the notification method for evaluation results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When provided, the evaluation results of the patent documents are optimized and displayed for the user's device. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing the information, the evaluation results of the patent documents will be linked to the relevant technical documents. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0184] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection unit that collects image data from patent documents, An analysis unit analyzes the image data collected by the aforementioned collection unit, An evaluation unit that evaluates similarity based on the data analyzed by the analysis unit, The system includes a providing unit that provides evaluation results obtained by the evaluation unit. A system characterized by the following features.

2. The aforementioned analysis unit, 3D CAD data is generated and analyzed using AI. The system according to feature 1.

3. The evaluation unit, Automatically compares with existing patent databases. The system according to feature 1.

4. The aforementioned supply unit is, Provide feedback on the evaluation results. The system according to feature 1.

5. The aforementioned collection unit is Automatically scans image data within patent documents. The system according to feature 1.

6. The evaluation unit, Confirm the novelty required for a patent. The system according to feature 1.

7. The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of image data collection based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is Prioritize the image data to be collected according to the type and field of the patent document. The system according to feature 1.

9. The aforementioned collection unit is During data collection, the system acquires updated patent information in real time and collects the latest image data. The system according to feature 1.

10. The aforementioned collection unit is It estimates the user's emotions and filters the collected image data based on the estimated user emotions. The system according to feature 1.

Images