System

Abstract

To provide a system which efficiently categorizes purchase data and predicts a spending.SOLUTION: The system according to an embodiment has a collection unit, a generation unit, a categorization unit, an analysis unit, and a prediction unit. The collection unit collects data. The generation unit generates a purchase dictionary on the basis of the data collected by the collection unit. The categorization unit categorizes data on the basis of the purchase dictionary generated by the generation unit. The analysis unit analyzes the data categorized by the categorization unit. The prediction unit predicts a spending on the basis of the data analyzed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] With conventional technology, categorization of purchasing data and expenditure forecasting were subjective, making efficient analysis difficult.

[0005] The system according to the embodiment aims to efficiently categorize purchase data and predict expenditures. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a generation unit, a categorization unit, an analysis unit, and a prediction unit. The collection unit collects data. The generation unit generates a purchase dictionary based on the data collected by the collection unit. The categorization unit categorizes the data based on the purchase dictionary generated by the generation unit. The analysis unit analyzes the data categorized by the categorization unit. The prediction unit predicts expenditures based on the data analyzed by the analysis unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently categorize purchase data and forecast expenditures. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The purchasing management system according to the embodiment of the present invention is a system that automatically categorizes data extracted from a purchasing management system of a buyer company and performs expenditure analysis. This purchasing management system uses a generation AI to create a purchasing dictionary and automates the categorization of data. In addition, the purchasing management system uses a generation AI to analyze data received from a buyer company, and performs detailed analysis and prediction of expenditure patterns and trends, and aims to break away from the man-month business. For example, the purchasing management system extracts data from the purchasing management system of the buyer company. This data includes information such as purchased items, amounts, and business partners. Next, a purchasing dictionary is created using a generation AI. The purchasing dictionary classifies purchased items by category and includes keywords and phrases corresponding to each category. The extracted data is automatically categorized using this purchasing dictionary. Next, the categorized data is analyzed using a generation AI. The generation AI analyzes expenditure patterns and trends and performs detailed analysis of expenditure. For example, it is possible to grasp the increase or decrease in expenditure in a specific category and the expenditure trend for each business partner. In addition, the generation AI can predict future expenditure based on past data. This eliminates the need for the traditional visual checks and time-consuming categorization that depended on individual users, enabling efficient and accurate expenditure analysis. Furthermore, by forecasting expenditures, buying companies can make more strategic purchasing plans. This will enable companies to move away from man-month business models, and is expected to lead to improved operational efficiency and cost reductions. This allows the purchasing management system to efficiently manage buying companies' purchasing data and perform expenditure analysis and forecasts.

[0029] A purchasing management system according to an embodiment includes a collection unit, a generation unit, a categorization unit, an analysis unit, and a prediction unit. The collection unit collects data from a purchasing management system of a buyer company. The collection unit extracts data including information such as purchased items, amounts, and business partners. The collection unit can use AI to efficiently collect data. The generation unit uses a generation AI to generate a purchasing dictionary based on the data collected by the collection unit. The generation unit, for example, classifies purchased items by category and generates a purchasing dictionary including keywords and phrases corresponding to each category. The generation AI can generate the purchasing dictionary using a text generation AI (for example, LLM). The categorization unit categorizes data based on the purchasing dictionary generated by the generation unit. The categorization unit, for example, automatically classifies purchased items by category. The categorization unit can efficiently categorize data using AI. The analysis unit analyzes the data categorized by the categorization unit. The analysis unit, for example, analyzes spending patterns and trends and performs a detailed analysis of spending. The analysis unit can use AI to efficiently analyze data. The prediction unit predicts expenditures based on the data analyzed by the analysis unit. The prediction unit predicts future expenditures based on, for example, past data. The prediction unit can efficiently predict expenditures using AI. As a result, the purchasing management system according to the embodiment can efficiently manage purchasing data of buyer companies and perform expenditure analysis and predictions.

[0030] The collection department collects data from the buyer company's purchasing management system. Specifically, the collection department works with the company's ERP system and purchasing management software to extract detailed data such as purchased items, amounts, business partners, purchase dates, and quantities. These data are automatically collected through APIs and database connections and stored in a central database. The collection department can use AI to make data collection more efficient. For example, natural language processing technology can be used to unify and accurately process data recorded in different formats and languages. The collection department also has the function of detecting duplicates and missing data and cleaning the data as necessary. This allows the collection department to accurately and efficiently collect purchasing data from buyer companies and provide high-quality data required for subsequent processing. Furthermore, the collection department can collect data in real time, so it can always keep track of the latest purchasing information. This allows companies to lay the foundation for making quick decisions.

[0031] The generation unit uses the generation AI to generate a purchasing dictionary based on the data collected by the collection unit. Specifically, the generation unit analyzes the collected purchasing data and classifies each purchasing item by category. The generation AI can generate the purchasing dictionary using a text generation AI (e.g., LLM). The generation AI analyzes the names and descriptions of the purchasing items and extracts related keywords and phrases. This allows the generation unit to generate a purchasing dictionary corresponding to each category and efficiently manage the purchasing items. For example, the generation unit classifies the purchasing items by category, such as food, clothing, and electronic devices, and generates a purchasing dictionary containing keywords and phrases related to each category. The generated purchasing dictionary is used in the subsequent categorization unit and analysis unit, and serves as a basis for efficiently classifying and analyzing data. Furthermore, the generation unit can regularly update the learning data of the generation AI to respond to the latest purchasing trends and market trends. This allows the generation unit to always provide a highly accurate purchasing dictionary based on the latest information and support corporate purchasing management.

[0032] The categorization unit categorizes data based on the purchasing dictionary generated by the generation unit. Specifically, the categorization unit automatically classifies collected purchasing data by category. The categorization unit can use AI to efficiently categorize data. For example, a machine learning algorithm is used to analyze the names and descriptions of purchased items and classify them into appropriate categories. This allows the categorization unit to quickly and accurately classify large amounts of purchasing data and efficiently manage data. Furthermore, the categorization unit can utilize the purchasing dictionary generated by the generation unit to classify newly collected data in real time. This allows companies to always understand the latest purchasing data and make quick decisions. In addition, the categorization unit can continuously evaluate the accuracy of the classification results and adjust the algorithm or update the purchasing dictionary as necessary. This allows the categorization unit to always provide highly accurate data classification and support companies' purchasing management.

[0033] The analysis unit analyzes the data categorized by the categorization unit. Specifically, the analysis unit analyzes spending patterns and trends and performs a detailed analysis of spending. The analysis unit can use AI to streamline data analysis. For example, a machine learning algorithm is used to analyze past purchasing data and understand spending trends in a specific period or category. In addition, an anomaly detection algorithm can be used to detect unusual spending patterns and issue early warnings. This allows the analysis unit to detect waste and fraud in a company's purchasing activities early and take measures. Furthermore, the analysis unit uses a data visualization tool to display the analysis results as graphs and charts to support company decision-making. For example, by visually displaying spending trends and anomalies, managers and purchasing personnel can quickly grasp the situation and take appropriate measures. This allows the analysis unit to streamline a company's purchasing activities and support cost reduction and risk management.

[0034] The prediction unit predicts expenditures based on the data analyzed by the analysis unit. Specifically, the prediction unit predicts future expenditures based on past data. The prediction unit can use AI to make expenditure forecasts more efficient. For example, the prediction unit uses a time series analysis algorithm to analyze past expenditure data and predict future expenditure trends. The prediction unit can also build a prediction model that takes seasonality and trends into account to make more accurate predictions. This allows the prediction unit to predict the company's future expenditures with high accuracy and support budget formulation and financial planning. Furthermore, the prediction unit can continuously revise the prediction results based on data updated in real time to respond to the latest situation. For example, if purchasing data or market trends change suddenly, the prediction unit immediately incorporates new data and updates the prediction results. The prediction unit can also detect abnormal spending patterns early and strengthen risk management. This allows the prediction unit to minimize risks in the company's purchasing activities and support efficient fund management.

[0035] The generation unit can classify purchased items by category and generate a purchasing dictionary including keywords or phrases corresponding to each category. The generation unit can, for example, classify purchased items by category and generate a purchasing dictionary including keywords or phrases corresponding to each category. The generation unit can generate the purchasing dictionary using a generation AI. The generation AI generates the purchasing dictionary using a text generation AI (e.g., LLM). The generation unit can efficiently classify purchased items and automate categorization of data. This allows the generation unit to efficiently classify purchased items and automate categorization of data.

[0036] The analysis unit can analyze spending patterns or trends and perform a detailed analysis of spending. The analysis unit can, for example, analyze spending patterns and trends and perform a detailed analysis of spending. The analysis unit can use AI to streamline data analysis. The analysis unit can grasp spending patterns and trends and perform a detailed analysis of spending. This allows the analysis unit to grasp spending patterns and trends and perform a detailed analysis of spending.

[0037] The prediction unit can predict future expenditures based on past data. The prediction unit, for example, predicts future expenditures based on past data. The prediction unit can use AI to make expenditure predictions more efficient. The prediction unit can predict future expenditures based on past data and make strategic purchasing plans. This allows the prediction unit to predict future expenditures based on past data and make strategic purchasing plans.

[0038] The collection unit can extract data from the purchasing management system of a company that uses the purchasing management system. The collection unit, for example, extracts data from the purchasing management system of a company that uses the purchasing management system. The collection unit can use AI to make data collection more efficient. The collection unit can efficiently extract data from the purchasing management system of a buyer company. This allows the collection unit to efficiently extract data from the purchasing management system of a buyer company.

[0039] The categorization unit can automatically categorize the data based on the generated purchasing dictionary. The categorization unit automatically categorizes the data based on the generated purchasing dictionary, for example. The categorization unit can use AI to streamline data categorization. The categorization unit automates data categorization, enabling efficient data management. Thereby, the categorization unit automates data categorization, enabling efficient data management.

[0040] The collection unit can analyze the purchase history of the buyer company and select the optimal data collection method. For example, the collection unit analyzes the past purchase history of the buyer company and collects data focusing on frequently purchased items. The collection unit can also preferentially collect data related to a specific season or event from the purchase history of the buyer company. Furthermore, the collection unit can also focus on collecting data from a specific supplier based on the purchase history of the buyer company. This allows the collection unit to select the optimal data collection method based on the purchase history of the buyer company, enabling efficient data collection. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the purchase history data of the buyer company to the generation AI and cause the generation AI to select the optimal data collection method.

[0041] The collection unit can perform filtering based on the current purchasing situation or field of interest of the buyer company when collecting data. For example, the collection unit grasps the current purchasing situation of the buyer company in real time and collects only related data. The collection unit can also preferentially collect data of a specific category based on the field of interest of the buyer company. Furthermore, the collection unit can filter unnecessary data according to the purchasing situation of the buyer company and perform efficient collection. This allows the collection unit to filter data based on the current purchasing situation or field of interest of the buyer company, enabling efficient data collection. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the current purchasing situation data of the buyer company to the generation AI and have the generation AI perform filtering.

[0042] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the buyer company when collecting data. For example, the collection unit preferentially collects area-specific data based on the location of the buyer company. The collection unit can also focus on collecting data from nearby suppliers in consideration of the geographical location information of the buyer company. Furthermore, the collection unit can analyze the geographical purchasing patterns of the buyer company and collect highly relevant data. This allows the collection unit to preferentially collect highly relevant data in consideration of the geographical location information of the buyer company, enabling efficient data collection. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the geographical location information data of the buyer company to the generation AI and cause the generation AI to select highly relevant data.

[0043] The collection unit can analyze the social media activities of the buyer company and collect related data when collecting data. For example, the collection unit monitors the social media activities of the buyer company and collects related purchasing data. The collection unit can also analyze trends on the buyer company's social media and collect related data preferentially. Furthermore, the collection unit can collect data related to a specific campaign or event from the social media activities of the buyer company. This allows the collection unit to analyze the social media activities of the buyer company and collect related data, thereby enabling efficient data collection. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the social media activity data of the buyer company to the generation AI and cause the generation AI to collect related data.

[0044] The generating unit can adjust the level of detail of the dictionary based on the importance of the purchased item when generating the purchasing dictionary. For example, the generating unit generates a dictionary including detailed information for a purchased item with high importance. The generating unit can also generate a simplified dictionary for a purchased item with low importance. Furthermore, the generating unit can dynamically adjust the level of detail of the dictionary according to the importance of the purchased item. This allows the generating unit to adjust the level of detail of the dictionary based on the importance of the purchased item, making it possible to generate an efficient purchasing dictionary. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit can input the importance data of the purchased item to the generating AI and cause the generating AI to adjust the level of detail of the dictionary.

[0045] The generating unit can apply different generating algorithms depending on the category of the purchased item when generating the purchasing dictionary. For example, when the purchased item is an electronic device, the generating unit applies a specific algorithm to generate the dictionary. Also, when the purchased item is food, the generating unit can apply a different algorithm to generate the dictionary. Furthermore, the generating unit can select an optimal generating algorithm depending on the category of the purchased item to generate the dictionary. This allows the generating unit to apply an optimal generating algorithm depending on the category of the purchased item, enabling efficient generation of the purchasing dictionary. A part or all of the above-mentioned processing in the generating unit may be performed using, for example, AI, or may be performed without using AI. For example, the generating unit can input category data of the purchased item to the generating AI and cause the generating AI to select the generating algorithm.

[0046] The generating unit can determine the priority of dictionaries based on the submission time of the purchased item when generating the purchased dictionary. For example, if the purchased item has been submitted recently, the generating unit preferentially reflects it in the dictionary. In addition, the generating unit can lower the priority of the dictionary if the purchased item is old. Furthermore, the generating unit can dynamically adjust the priority of dictionaries based on the submission time of the purchased item. This allows the generating unit to determine the priority of dictionaries based on the submission time of the purchased item, making it possible to generate an efficient purchased dictionary. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit can input the submission time data of the purchased item to the generating AI and cause the generating AI to execute the determination of the priority of dictionaries.

[0047] The generating unit can adjust the order of the dictionary based on the relevance of the purchased item when generating the purchasing dictionary. For example, if the purchased item is highly related to other items, the generating unit places the purchased item at the top of the dictionary. Also, if the purchased item is less related to other items, the generating unit can place the purchased item at the bottom of the dictionary. Furthermore, the generating unit can dynamically adjust the order of the dictionary based on the relevance of the purchased item. This allows the generating unit to adjust the order of the dictionary based on the relevance of the purchased item, making it possible to generate an efficient purchasing dictionary. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit can input relevance data of the purchased item to the generating AI and cause the generating AI to adjust the order of the dictionary.

[0048] The categorization unit can improve the accuracy of categorization by considering the interrelationships of data during categorization. For example, the categorization unit analyzes the interrelationships of data and classifies highly related data into the same category. The categorization unit can also apply an algorithm that improves the accuracy of categorization by considering the interrelationships of data. Furthermore, the categorization unit can dynamically adjust the categorization criteria based on the interrelationships of data. As a result, the categorization unit improves the accuracy of categorization by considering the interrelationships of data. A part or all of the above-mentioned processing in the categorization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the categorization unit can input interrelationship data of data to the generation AI and cause the generation AI to improve the accuracy of categorization.

[0049] The categorization unit can perform categorization taking into consideration attribute information of the data submitter at the time of categorization. The categorization unit classifies data into categories with high relevance based on, for example, the attribute information of the data submitter. The categorization unit can also adjust the categorization criteria taking into consideration the attribute information of the data submitter. Furthermore, the categorization unit can apply an algorithm that improves the accuracy of categorization based on the attribute information of the data submitter. As a result, the categorization unit improves the accuracy of categorization by taking into consideration the attribute information of the data submitter. A part or all of the above-mentioned processing in the categorization unit may be performed using, for example, AI, or may be performed without using AI. For example, the categorization unit can input attribute information of the data submitter to the generation AI and cause the generation AI to adjust the categorization criteria.

[0050] The categorization unit can perform categorization taking into consideration the geographical distribution of data. For example, the categorization unit analyzes the geographical distribution of data and performs categorization by region. The categorization unit can also adjust the categorization criteria taking into consideration the geographical distribution of data. Furthermore, the categorization unit can apply an algorithm that improves the accuracy of categorization based on the geographical distribution of data. This allows the categorization unit to perform efficient data categorization by taking into consideration the geographical distribution of data. A part or all of the above-mentioned processing in the categorization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the categorization unit can input geographical distribution data of data to the generation AI and cause the generation AI to adjust the categorization criteria.

[0051] The categorization unit can improve the accuracy of categorization by referring to literature related to the data during categorization. The categorization unit can adjust the criteria for categorization by referring to literature related to the data, for example. The categorization unit can also apply an algorithm that improves the accuracy of categorization based on literature related to the data. Furthermore, the categorization unit can classify highly related data into the same category by referring to literature related to the data. As a result, the categorization unit can improve the accuracy of categorization by referring to literature related to the data. A part or all of the above-mentioned processing in the categorization unit can be performed using, for example, AI, or can be performed without using AI. For example, the categorization unit can input literature data related to the data to the generation AI and cause the generation AI to improve the accuracy of categorization.

[0052] The analysis unit can optimize the current analysis by referring to past analysis data during analysis. The analysis unit corrects the current analysis result based on the past analysis data, for example. The analysis unit can also optimize the current analysis method by referring to the past analysis data. Furthermore, the analysis unit can improve the reliability of the current analysis result based on the past analysis data. As a result, the analysis unit optimizes the current analysis by referring to the past analysis data, and a highly reliable analysis result can be obtained. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the past analysis data to the generation AI and cause the generation AI to optimize the current analysis.

[0053] The analysis unit can apply different analysis methods to each data category during analysis. For example, the analysis unit applies a specific analysis method to data in the electronic device category. The analysis unit can also apply a different analysis method to data in the food category. Furthermore, the analysis unit can select and apply an optimal analysis method according to the data category. This allows the analysis unit to apply an optimal analysis method according to the data category, enabling efficient data analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data category information to the generation AI and cause the generation AI to select an analysis method.

[0054] The analysis unit can analyze the change in the analysis based on the time of data submission during the analysis. The analysis unit can analyze the change in the analysis result based on, for example, the time of data submission. The analysis unit can also adjust the analysis method in consideration of the time of data submission. Furthermore, the analysis unit can improve the reliability of the analysis result based on the time of data submission. Thereby, the analysis unit can analyze the change in the analysis based on the time of data submission, and a highly reliable analysis result can be obtained. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI, or can be performed without using AI. For example, the analysis unit can input the data submission time information to the generation AI and cause the generation AI to perform the analysis of the change in the analysis.

[0055] The analysis unit can perform the analysis by referring to the relevant market data of the data during the analysis. The analysis unit, for example, refers to the relevant market data and corrects the analysis result. The analysis unit can also optimize the analysis method based on the related market data. Furthermore, the analysis unit can also improve the reliability of the analysis result by referring to the related market data. As a result, the analysis unit can obtain a highly reliable analysis result by referring to the related market data of the data. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the relevant market data to the generation AI and cause the generation AI to execute optimization of the analysis.

[0056] The prediction unit can optimize the prediction algorithm by referring to past data at the time of prediction. The prediction unit corrects the prediction algorithm based on, for example, past data. The prediction unit can also optimize the prediction algorithm by referring to past data. Furthermore, the prediction unit can improve the reliability of the prediction algorithm based on past data. As a result, the prediction unit optimizes the prediction algorithm by referring to past data, and a highly reliable prediction result can be obtained. A part or all of the above-mentioned processing in the prediction unit may be performed, for example, using AI, or may be performed without using AI. For example, the prediction unit can input past data to the generation AI and cause the generation AI to execute optimization of the prediction algorithm.

[0057] The prediction unit can apply different prediction methods for each data category at the time of prediction. For example, the prediction unit applies a specific prediction method to data in the electronic device category. The prediction unit can also apply a different prediction method to data in the food category. Furthermore, the prediction unit can select and apply an optimal prediction method according to the data category. This allows the prediction unit to apply an optimal prediction method according to the data category, enabling efficient prediction. Some or all of the above-mentioned processing in the prediction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the prediction unit can input data category information to the generation AI and cause the generation AI to select a prediction method.

[0058] The prediction unit can make predictions taking into account the geographic location information of the data at the time of prediction. The prediction unit, for example, makes predictions for each region based on the geographic location information of the data. The prediction unit can also adjust the prediction method taking into account the geographic location information of the data. Furthermore, the prediction unit can improve the reliability of the prediction result based on the geographic location information of the data. As a result, the prediction unit can obtain a highly reliable prediction result by taking into account the geographic location information of the data. A part or all of the above-mentioned processing in the prediction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the prediction unit can input the geographic location information of the data to the generation AI and cause the generation AI to execute the prediction.

[0059] The prediction unit can improve the accuracy of prediction by referring to the literature related to the data at the time of prediction. The prediction unit can, for example, adjust the prediction method by referring to the literature related to the data. The prediction unit can also optimize the prediction method based on the literature related to the data. Furthermore, the prediction unit can improve the reliability of the prediction result by referring to the literature related to the data. As a result, the prediction unit can obtain a highly reliable prediction result by referring to the literature related to the data. A part or all of the above-mentioned processing in the prediction unit can be performed, for example, using AI or can be performed without using AI. For example, the prediction unit can input the literature related to the data to the generation AI and cause the generation AI to improve the accuracy of the prediction.

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

[0061] The purchasing management system may further include an alert unit. The alert unit may issue an alert when an abnormal spending pattern or unexpected spending occurs based on the results of the analysis unit and the forecast unit. For example, when a sudden increase in spending is observed in a particular category, the alert unit may notify the buying company. Also, when the forecast unit detects an abnormal fluctuation in future spending, the alert unit may immediately provide that information. Furthermore, the alert unit may issue a warning when the credit risk of a trading partner increases. This allows the buying company to take countermeasures quickly, enhancing risk management.

[0062] The generation unit can evaluate the environmental impact of purchased items and generate a purchasing dictionary based on the evaluation results. For example, environmentally friendly products can be marked with a specific mark. The generation unit can also identify products with a high environmental impact and classify them into a different category. Furthermore, the generation unit can adjust keywords and phrases in the purchasing dictionary based on the environmental impact assessment data. This allows the buyer company to promote environmentally conscious purchasing activities.

[0063] The prediction unit may include a dashboard unit for visually displaying the prediction results. The dashboard unit displays the prediction results as graphs or charts, allowing the user to intuitively understand them. For example, the future expenditure forecast may be displayed as a line graph. Also, the expenditure forecast by category may be shown as a pie chart. Furthermore, the dashboard unit may include a function for suggesting an action plan based on the prediction results. This allows the user to plan specific actions based on the prediction results.

[0064] The categorization unit can improve the accuracy of categorization by taking into account the interrelationships between data. For example, the categorization unit analyzes the interrelationships between data and classifies highly related data into the same category. The categorization unit can also apply an algorithm that improves the accuracy of categorization by taking into account the interrelationships between data. Furthermore, the categorization unit can dynamically adjust the categorization criteria based on the interrelationships between data. In this way, the categorization unit improves the accuracy of categorization by taking into account the interrelationships between data.

[0065] The collection department can analyze the purchasing history of the buyer company and select the optimal data collection method. For example, the collection department can analyze the past purchasing history of the buyer company and collect data focusing on frequently purchased items. The collection department can also preferentially collect data related to specific seasons or events from the purchasing history of the buyer company. Furthermore, the collection department can focus on collecting data from specific suppliers based on the purchasing history of the buyer company. This allows the collection department to select the optimal data collection method based on the purchasing history of the buyer company, enabling efficient data collection.

[0066] The collection unit can filter data based on the buyer company's current purchasing status or areas of interest when collecting data. For example, the collection unit grasps the buyer company's current purchasing status in real time and collects only related data. The collection unit can also preferentially collect data of a specific category based on the buyer company's areas of interest. Furthermore, the collection unit can filter unnecessary data according to the buyer company's purchasing status and collect data efficiently. This allows the collection unit to filter data based on the buyer company's current purchasing status and areas of interest, enabling efficient data collection.

[0067] The process flow of the first embodiment will be briefly described below.

[0068] Step 1: The collection department collects data from the buyer company's purchasing management system. The collection department extracts data including information such as purchased items, amounts, and business partners. The collection department can use AI to make data collection more efficient. Step 2: The generation unit uses a generation AI to generate a purchasing dictionary based on the data collected by the collection unit. The generation unit, for example, classifies purchased items by category and generates a purchasing dictionary including keywords and phrases corresponding to each category. The generation AI can generate the purchasing dictionary using a text generation AI (e.g., LLM). Step 3: The categorization unit categorizes the data based on the purchase dictionary generated by the generation unit. The categorization unit, for example, automatically classifies purchased items into categories. The categorization unit can use AI to streamline data categorization. Step 4: The analysis unit analyzes the data categorized by the categorization unit. For example, the analysis unit analyzes spending patterns and trends and performs a detailed analysis of spending. The analysis unit can use AI to streamline data analysis. Step 5: The prediction unit predicts expenditures based on the data analyzed by the analysis unit. The prediction unit predicts future expenditures based on, for example, past data. The prediction unit can use AI to make expenditure predictions more efficient.

[0069] (Example 2) The purchasing management system according to the embodiment of the present invention is a system that automatically categorizes data extracted from a purchasing management system of a buyer company and performs expenditure analysis. This purchasing management system uses a generation AI to create a purchasing dictionary and automates the categorization of data. In addition, the purchasing management system uses a generation AI to analyze data received from a buyer company, and performs detailed analysis and prediction of expenditure patterns and trends, and aims to break away from the man-month business. For example, the purchasing management system extracts data from the purchasing management system of the buyer company. This data includes information such as purchased items, amounts, and business partners. Next, a purchasing dictionary is created using a generation AI. The purchasing dictionary classifies purchased items by category and includes keywords and phrases corresponding to each category. The extracted data is automatically categorized using this purchasing dictionary. Next, the categorized data is analyzed using a generation AI. The generation AI analyzes expenditure patterns and trends and performs detailed analysis of expenditure. For example, it is possible to grasp the increase or decrease in expenditure in a specific category and the expenditure trend for each business partner. In addition, the generation AI can predict future expenditure based on past data. This eliminates the need for the traditional visual checks and time-consuming categorization that depended on individual users, enabling efficient and accurate expenditure analysis. Furthermore, by forecasting expenditures, buying companies can make more strategic purchasing plans. This will enable companies to move away from man-month business models, and is expected to lead to improved operational efficiency and cost reductions. This allows the purchasing management system to efficiently manage buying companies' purchasing data and perform expenditure analysis and forecasts.

[0070] A purchasing management system according to an embodiment includes a collection unit, a generation unit, a categorization unit, an analysis unit, and a prediction unit. The collection unit collects data from a purchasing management system of a buyer company. The collection unit extracts data including information such as purchased items, amounts, and business partners. The collection unit can use AI to efficiently collect data. The generation unit uses a generation AI to generate a purchasing dictionary based on the data collected by the collection unit. The generation unit, for example, classifies purchased items by category and generates a purchasing dictionary including keywords and phrases corresponding to each category. The generation AI can generate the purchasing dictionary using a text generation AI (for example, LLM). The categorization unit categorizes data based on the purchasing dictionary generated by the generation unit. The categorization unit, for example, automatically classifies purchased items by category. The categorization unit can efficiently categorize data using AI. The analysis unit analyzes the data categorized by the categorization unit. The analysis unit, for example, analyzes spending patterns and trends and performs a detailed analysis of spending. The analysis unit can use AI to efficiently analyze data. The prediction unit predicts expenditures based on the data analyzed by the analysis unit. The prediction unit predicts future expenditures based on, for example, past data. The prediction unit can efficiently predict expenditures using AI. As a result, the purchasing management system according to the embodiment can efficiently manage purchasing data of buyer companies and perform expenditure analysis and predictions.

[0071] The collection department collects data from the buyer company's purchasing management system. Specifically, the collection department works with the company's ERP system and purchasing management software to extract detailed data such as purchased items, amounts, business partners, purchase dates, and quantities. These data are automatically collected through APIs and database connections and stored in a central database. The collection department can use AI to make data collection more efficient. For example, natural language processing technology can be used to unify and accurately process data recorded in different formats and languages. The collection department also has the function of detecting duplicates and missing data and cleaning the data as necessary. This allows the collection department to accurately and efficiently collect purchasing data from buyer companies and provide high-quality data required for subsequent processing. Furthermore, the collection department can collect data in real time, so it can always keep track of the latest purchasing information. This allows companies to lay the foundation for making quick decisions.

[0072] The generation unit uses the generation AI to generate a purchasing dictionary based on the data collected by the collection unit. Specifically, the generation unit analyzes the collected purchasing data and classifies each purchasing item by category. The generation AI can generate the purchasing dictionary using a text generation AI (e.g., LLM). The generation AI analyzes the names and descriptions of the purchasing items and extracts related keywords and phrases. This allows the generation unit to generate a purchasing dictionary corresponding to each category and efficiently manage the purchasing items. For example, the generation unit classifies the purchasing items by category, such as food, clothing, and electronic devices, and generates a purchasing dictionary containing keywords and phrases related to each category. The generated purchasing dictionary is used in the subsequent categorization unit and analysis unit, and serves as a basis for efficiently classifying and analyzing data. Furthermore, the generation unit can regularly update the learning data of the generation AI to respond to the latest purchasing trends and market trends. This allows the generation unit to always provide a highly accurate purchasing dictionary based on the latest information and support corporate purchasing management.

[0073] The categorization unit categorizes data based on the purchasing dictionary generated by the generation unit. Specifically, the categorization unit automatically classifies collected purchasing data by category. The categorization unit can use AI to efficiently categorize data. For example, a machine learning algorithm is used to analyze the names and descriptions of purchased items and classify them into appropriate categories. This allows the categorization unit to quickly and accurately classify large amounts of purchasing data and efficiently manage data. Furthermore, the categorization unit can utilize the purchasing dictionary generated by the generation unit to classify newly collected data in real time. This allows companies to always understand the latest purchasing data and make quick decisions. In addition, the categorization unit can continuously evaluate the accuracy of the classification results and adjust the algorithm or update the purchasing dictionary as necessary. This allows the categorization unit to always provide highly accurate data classification and support companies' purchasing management.

[0074] The analysis unit analyzes the data categorized by the categorization unit. Specifically, the analysis unit analyzes spending patterns and trends and performs a detailed analysis of spending. The analysis unit can use AI to streamline data analysis. For example, a machine learning algorithm is used to analyze past purchasing data and understand spending trends in a specific period or category. In addition, an anomaly detection algorithm can be used to detect unusual spending patterns and issue early warnings. This allows the analysis unit to detect waste and fraud in a company's purchasing activities early and take measures. Furthermore, the analysis unit uses a data visualization tool to display the analysis results as graphs and charts to support company decision-making. For example, by visually displaying spending trends and anomalies, managers and purchasing personnel can quickly grasp the situation and take appropriate measures. This allows the analysis unit to streamline a company's purchasing activities and support cost reduction and risk management.

[0075] The prediction unit predicts expenditures based on the data analyzed by the analysis unit. Specifically, the prediction unit predicts future expenditures based on past data. The prediction unit can use AI to make expenditure forecasts more efficient. For example, the prediction unit uses a time series analysis algorithm to analyze past expenditure data and predict future expenditure trends. The prediction unit can also build a prediction model that takes seasonality and trends into account to make more accurate predictions. This allows the prediction unit to predict the company's future expenditures with high accuracy and support budget formulation and financial planning. Furthermore, the prediction unit can continuously revise the prediction results based on data updated in real time to respond to the latest situation. For example, if purchasing data or market trends change suddenly, the prediction unit immediately incorporates new data and updates the prediction results. The prediction unit can also detect abnormal spending patterns early and strengthen risk management. This allows the prediction unit to minimize risks in the company's purchasing activities and support efficient fund management.

[0076] The generation unit can classify purchased items by category and generate a purchasing dictionary including keywords or phrases corresponding to each category. The generation unit can, for example, classify purchased items by category and generate a purchasing dictionary including keywords or phrases corresponding to each category. The generation unit can generate the purchasing dictionary using a generation AI. The generation AI generates the purchasing dictionary using a text generation AI (e.g., LLM). The generation unit can efficiently classify purchased items and automate categorization of data. This allows the generation unit to efficiently classify purchased items and automate categorization of data.

[0077] The analysis unit can analyze spending patterns or trends and perform a detailed analysis of spending. The analysis unit can, for example, analyze spending patterns and trends and perform a detailed analysis of spending. The analysis unit can use AI to streamline data analysis. The analysis unit can grasp spending patterns and trends and perform a detailed analysis of spending. This allows the analysis unit to grasp spending patterns and trends and perform a detailed analysis of spending.

[0078] The prediction unit can predict future expenditures based on past data. The prediction unit, for example, predicts future expenditures based on past data. The prediction unit can use AI to make expenditure predictions more efficient. The prediction unit can predict future expenditures based on past data and make strategic purchasing plans. This allows the prediction unit to predict future expenditures based on past data and make strategic purchasing plans.

[0079] The collection unit can extract data from the purchasing management system of a company that uses the purchasing management system. The collection unit, for example, extracts data from the purchasing management system of a company that uses the purchasing management system. The collection unit can use AI to make data collection more efficient. The collection unit can efficiently extract data from the purchasing management system of a buyer company. This allows the collection unit to efficiently extract data from the purchasing management system of a buyer company.

[0080] The categorization unit can automatically categorize the data based on the generated purchasing dictionary. The categorization unit automatically categorizes the data based on the generated purchasing dictionary, for example. The categorization unit can use AI to streamline data categorization. The categorization unit automates data categorization, enabling efficient data management. Thereby, the categorization unit automates data categorization, enabling efficient data management.

[0081] The collection unit can estimate the user's emotion and adjust the timing of data collection based on the estimated user's emotion. For example, when the user is feeling stressed, the collection unit delays the timing of collection to reduce the burden on the user. In addition, when the user is relaxed, the collection unit can also advance the timing of collection to efficiently collect data. Furthermore, when the user is in a hurry, the collection unit can immediately collect data and quickly start processing. This allows the collection unit to adjust the timing of data collection according to the user's emotion and efficiently collect data. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0082] The collection unit can analyze the purchase history of the buyer company and select the optimal data collection method. For example, the collection unit analyzes the past purchase history of the buyer company and collects data focusing on frequently purchased items. The collection unit can also preferentially collect data related to a specific season or event from the purchase history of the buyer company. Furthermore, the collection unit can also focus on collecting data from a specific supplier based on the purchase history of the buyer company. This allows the collection unit to select the optimal data collection method based on the purchase history of the buyer company, enabling efficient data collection. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the purchase history data of the buyer company to the generation AI and cause the generation AI to select the optimal data collection method.

[0083] The collection unit can perform filtering based on the current purchasing situation or field of interest of the buyer company when collecting data. For example, the collection unit grasps the current purchasing situation of the buyer company in real time and collects only related data. The collection unit can also preferentially collect data of a specific category based on the field of interest of the buyer company. Furthermore, the collection unit can filter unnecessary data according to the purchasing situation of the buyer company and perform efficient collection. This allows the collection unit to filter data based on the current purchasing situation or field of interest of the buyer company, enabling efficient data collection. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the current purchasing situation data of the buyer company to the generation AI and have the generation AI perform filtering.

[0084] The collection unit can estimate the user's emotion and determine the priority of data to be collected based on the estimated user's emotion. For example, when the user is feeling stressed, the collection unit preferentially collects data with a high degree of importance. In addition, when the user is relaxed, the collection unit can also collect overall data in a balanced manner. Furthermore, when the user is in a hurry, the collection unit can instantly collect necessary data and quickly start processing. This allows the collection unit to determine the priority of data to be collected according to the user's emotion, enabling efficient data collection. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of the data.

[0085] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the buyer company when collecting data. For example, the collection unit preferentially collects area-specific data based on the location of the buyer company. The collection unit can also focus on collecting data from nearby suppliers in consideration of the geographical location information of the buyer company. Furthermore, the collection unit can analyze the geographical purchasing patterns of the buyer company and collect highly relevant data. This allows the collection unit to preferentially collect highly relevant data in consideration of the geographical location information of the buyer company, enabling efficient data collection. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the geographical location information data of the buyer company to the generation AI and cause the generation AI to select highly relevant data.

[0086] The collection unit can analyze the social media activities of the buyer company and collect related data when collecting data. For example, the collection unit monitors the social media activities of the buyer company and collects related purchasing data. The collection unit can also analyze trends on the buyer company's social media and collect related data preferentially. Furthermore, the collection unit can collect data related to a specific campaign or event from the social media activities of the buyer company. This allows the collection unit to analyze the social media activities of the buyer company and collect related data, thereby enabling efficient data collection. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the social media activity data of the buyer company to the generation AI and cause the generation AI to collect related data.

[0087] The generation unit can estimate the user's emotion and adjust the generation method of the purchase dictionary based on the estimated user's emotion. For example, when the user is relaxed, the generation unit generates a detailed purchase dictionary. In addition, when the user is in a hurry, the generation unit can also generate a simplified purchase dictionary. Furthermore, when the user is excited, the generation unit can also generate a visually easy-to-understand purchase dictionary. This allows the generation unit to adjust the generation method of the purchase dictionary according to the user's emotion, making it possible to generate an efficient purchase dictionary. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to execute adjustment of the generation method of the purchase dictionary.

[0088] The generating unit can adjust the level of detail of the dictionary based on the importance of the purchased item when generating the purchasing dictionary. For example, the generating unit generates a dictionary including detailed information for a purchased item with high importance. The generating unit can also generate a simplified dictionary for a purchased item with low importance. Furthermore, the generating unit can dynamically adjust the level of detail of the dictionary according to the importance of the purchased item. This allows the generating unit to adjust the level of detail of the dictionary based on the importance of the purchased item, making it possible to generate an efficient purchasing dictionary. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit can input the importance data of the purchased item to the generating AI and cause the generating AI to adjust the level of detail of the dictionary.

[0089] The generating unit can apply different generating algorithms depending on the category of the purchased item when generating the purchasing dictionary. For example, when the purchased item is an electronic device, the generating unit applies a specific algorithm to generate the dictionary. Also, when the purchased item is food, the generating unit can apply a different algorithm to generate the dictionary. Furthermore, the generating unit can select an optimal generating algorithm depending on the category of the purchased item to generate the dictionary. This allows the generating unit to apply an optimal generating algorithm depending on the category of the purchased item, enabling efficient generation of the purchasing dictionary. A part or all of the above-mentioned processing in the generating unit may be performed using, for example, AI, or may be performed without using AI. For example, the generating unit can input category data of the purchased item to the generating AI and cause the generating AI to select the generating algorithm.

[0090] The generation unit can estimate the user's emotion and adjust the length of the purchase dictionary based on the estimated user's emotion. For example, when the user is in a hurry, the generation unit generates a short and to the point purchase dictionary. In addition, when the user is relaxed, the generation unit can also generate a longer purchase dictionary including detailed explanations. Furthermore, when the user is excited, the generation unit can also generate a purchase dictionary with a visually stimulating effect. This allows the generation unit to adjust the length of the purchase dictionary according to the user's emotion and generate an efficient purchase dictionary. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the purchase dictionary.

[0091] The generating unit can determine the priority of dictionaries based on the submission time of the purchased item when generating the purchased dictionary. For example, if the purchased item has been submitted recently, the generating unit preferentially reflects it in the dictionary. In addition, the generating unit can lower the priority of the dictionary if the purchased item is old. Furthermore, the generating unit can dynamically adjust the priority of dictionaries based on the submission time of the purchased item. This allows the generating unit to determine the priority of dictionaries based on the submission time of the purchased item, making it possible to generate an efficient purchased dictionary. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit can input the submission time data of the purchased item to the generating AI and cause the generating AI to execute the determination of the priority of dictionaries.

[0092] The generating unit can adjust the order of the dictionary based on the relevance of the purchased item when generating the purchasing dictionary. For example, if the purchased item is highly related to other items, the generating unit places the purchased item at the top of the dictionary. Also, if the purchased item is less related to other items, the generating unit can place the purchased item at the bottom of the dictionary. Furthermore, the generating unit can dynamically adjust the order of the dictionary based on the relevance of the purchased item. This allows the generating unit to adjust the order of the dictionary based on the relevance of the purchased item, making it possible to generate an efficient purchasing dictionary. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit can input relevance data of the purchased item to the generating AI and cause the generating AI to adjust the order of the dictionary.

[0093] The categorization unit can estimate the user's emotion and adjust the categorization criteria of the data based on the estimated user's emotion. For example, when the user is relaxed, the categorization unit can apply detailed categorization criteria. Furthermore, when the user is in a hurry, the categorization unit can also apply simplified categorization criteria. Furthermore, when the user is excited, the categorization unit can apply visually easy-to-understand categorization criteria. This allows the categorization unit to adjust the categorization criteria of the data according to the user's emotion, enabling efficient data categorization. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the categorization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the categorization unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the categorization criteria.

[0094] The categorization unit can improve the accuracy of categorization by considering the interrelationships of data during categorization. For example, the categorization unit analyzes the interrelationships of data and classifies highly related data into the same category. The categorization unit can also apply an algorithm that improves the accuracy of categorization by considering the interrelationships of data. Furthermore, the categorization unit can dynamically adjust the categorization criteria based on the interrelationships of data. As a result, the categorization unit improves the accuracy of categorization by considering the interrelationships of data. A part or all of the above-mentioned processing in the categorization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the categorization unit can input interrelationship data of data to the generation AI and cause the generation AI to improve the accuracy of categorization.

[0095] The categorization unit can perform categorization taking into consideration attribute information of the data submitter at the time of categorization. The categorization unit classifies data into categories with high relevance based on, for example, the attribute information of the data submitter. The categorization unit can also adjust the categorization criteria taking into consideration the attribute information of the data submitter. Furthermore, the categorization unit can apply an algorithm that improves the accuracy of categorization based on the attribute information of the data submitter. As a result, the categorization unit improves the accuracy of categorization by taking into consideration the attribute information of the data submitter. A part or all of the above-mentioned processing in the categorization unit may be performed using, for example, AI, or may be performed without using AI. For example, the categorization unit can input attribute information of the data submitter to the generation AI and cause the generation AI to adjust the categorization criteria.

[0096] The categorization unit can estimate the user's emotion and adjust the order of displaying the categorization results based on the estimated user's emotion. For example, when the user is relaxed, the categorization unit preferentially displays detailed categorization results. In addition, when the user is in a hurry, the categorization unit can also preferentially display categorization results that focus on the main points. Furthermore, when the user is excited, the categorization unit can also preferentially display categorization results that are visually easy to understand. This allows the categorization unit to adjust the order of displaying the categorization results according to the user's emotion, enabling efficient data display. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the categorization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the categorization unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order.

[0097] The categorization unit can perform categorization taking into consideration the geographical distribution of data. For example, the categorization unit analyzes the geographical distribution of data and performs categorization by region. The categorization unit can also adjust the categorization criteria taking into consideration the geographical distribution of data. Furthermore, the categorization unit can apply an algorithm that improves the accuracy of categorization based on the geographical distribution of data. This allows the categorization unit to perform efficient data categorization by taking into consideration the geographical distribution of data. A part or all of the above-mentioned processing in the categorization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the categorization unit can input geographical distribution data of data to the generation AI and cause the generation AI to adjust the categorization criteria.

[0098] The categorization unit can improve the accuracy of categorization by referring to literature related to the data during categorization. The categorization unit can adjust the criteria for categorization by referring to literature related to the data, for example. The categorization unit can also apply an algorithm that improves the accuracy of categorization based on literature related to the data. Furthermore, the categorization unit can classify highly related data into the same category by referring to literature related to the data. As a result, the categorization unit can improve the accuracy of categorization by referring to literature related to the data. A part or all of the above-mentioned processing in the categorization unit can be performed using, for example, AI, or can be performed without using AI. For example, the categorization unit can input literature data related to the data to the generation AI and cause the generation AI to improve the accuracy of categorization.

[0099] The analysis unit can estimate the user's emotion and adjust the display method of the analysis based on the estimated user's emotion. For example, when the user is nervous, the analysis unit provides a simple and highly visible display method. In addition, when the user is relaxed, the analysis unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the analysis unit can also provide a display method that focuses on the main points. This allows the analysis unit to adjust the display method of the analysis according to the user's emotion, enabling efficient data analysis. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display method.

[0100] The analysis unit can optimize the current analysis by referring to past analysis data during analysis. The analysis unit corrects the current analysis result based on the past analysis data, for example. The analysis unit can also optimize the current analysis method by referring to the past analysis data. Furthermore, the analysis unit can improve the reliability of the current analysis result based on the past analysis data. As a result, the analysis unit optimizes the current analysis by referring to the past analysis data, and a highly reliable analysis result can be obtained. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the past analysis data to the generation AI and cause the generation AI to optimize the current analysis.

[0101] The analysis unit can apply different analysis methods to each data category during analysis. For example, the analysis unit applies a specific analysis method to data in the electronic device category. The analysis unit can also apply a different analysis method to data in the food category. Furthermore, the analysis unit can select and apply an optimal analysis method according to the data category. This allows the analysis unit to apply an optimal analysis method according to the data category, enabling efficient data analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data category information to the generation AI and cause the generation AI to select an analysis method.

[0102] The analysis unit can estimate the user's emotion and adjust the importance of the analysis based on the estimated user's emotion. For example, when the user is nervous, the analysis unit preferentially displays analysis results with a high importance. Furthermore, when the user is relaxed, the analysis unit can also display overall analysis results in a balanced manner. Furthermore, when the user is in a hurry, the analysis unit can also preferentially display analysis results that focus on the main points. This allows the analysis unit to adjust the importance of the analysis according to the user's emotion, enabling efficient data analysis. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the importance of the analysis.

[0103] The analysis unit can analyze the change in the analysis based on the time of data submission during the analysis. The analysis unit can analyze the change in the analysis result based on, for example, the time of data submission. The analysis unit can also adjust the analysis method in consideration of the time of data submission. Furthermore, the analysis unit can improve the reliability of the analysis result based on the time of data submission. Thereby, the analysis unit can analyze the change in the analysis based on the time of data submission, and a highly reliable analysis result can be obtained. A part or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI, or can be performed without using AI. For example, the analysis unit can input the data submission time information to the generation AI and cause the generation AI to perform the analysis of the change in the analysis.

[0104] The analysis unit can perform the analysis by referring to the relevant market data of the data during the analysis. The analysis unit, for example, refers to the relevant market data and corrects the analysis result. The analysis unit can also optimize the analysis method based on the related market data. Furthermore, the analysis unit can also improve the reliability of the analysis result by referring to the related market data. As a result, the analysis unit can obtain a highly reliable analysis result by referring to the related market data of the data. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the relevant market data to the generation AI and cause the generation AI to execute optimization of the analysis.

[0105] The prediction unit can estimate the user's emotion and adjust the prediction method based on the estimated user's emotion. For example, when the user is relaxed, the prediction unit applies a detailed prediction method. Furthermore, when the user is in a hurry, the prediction unit can also apply a simplified prediction method. Furthermore, when the user is excited, the prediction unit can also apply a visually easy-to-understand prediction method. This allows the prediction unit to adjust the prediction method according to the user's emotion, enabling efficient prediction. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the prediction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the prediction unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the prediction method.

[0106] The prediction unit can optimize the prediction algorithm by referring to past data at the time of prediction. The prediction unit corrects the prediction algorithm based on, for example, past data. The prediction unit can also optimize the prediction algorithm by referring to past data. Furthermore, the prediction unit can improve the reliability of the prediction algorithm based on past data. As a result, the prediction unit optimizes the prediction algorithm by referring to past data, and a highly reliable prediction result can be obtained. A part or all of the above-mentioned processing in the prediction unit may be performed, for example, using AI, or may be performed without using AI. For example, the prediction unit can input past data to the generation AI and cause the generation AI to execute optimization of the prediction algorithm.

[0107] The prediction unit can apply different prediction methods for each data category at the time of prediction. For example, the prediction unit applies a specific prediction method to data in the electronic device category. The prediction unit can also apply a different prediction method to data in the food category. Furthermore, the prediction unit can select and apply an optimal prediction method according to the data category. This allows the prediction unit to apply an optimal prediction method according to the data category, enabling efficient prediction. Some or all of the above-mentioned processing in the prediction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the prediction unit can input data category information to the generation AI and cause the generation AI to select a prediction method.

[0108] The prediction unit can estimate the user's emotion and determine the priority of prediction based on the estimated user's emotion. For example, when the user is relaxed, the prediction unit preferentially displays a detailed prediction result. In addition, when the user is in a hurry, the prediction unit can also preferentially display a prediction result that covers the main points. Furthermore, when the user is excited, the prediction unit can also preferentially display a visually easy-to-understand prediction result. This allows the prediction unit to determine the priority of prediction according to the user's emotion, enabling efficient prediction. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the prediction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the prediction unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of prediction.

[0109] The prediction unit can make predictions taking into account the geographic location information of the data at the time of prediction. The prediction unit, for example, makes predictions for each region based on the geographic location information of the data. The prediction unit can also adjust the prediction method taking into account the geographic location information of the data. Furthermore, the prediction unit can improve the reliability of the prediction result based on the geographic location information of the data. As a result, the prediction unit can obtain a highly reliable prediction result by taking into account the geographic location information of the data. A part or all of the above-mentioned processing in the prediction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the prediction unit can input the geographic location information of the data to the generation AI and cause the generation AI to execute the prediction.

[0110] The prediction unit can improve the accuracy of prediction by referring to the literature related to the data at the time of prediction. The prediction unit can, for example, adjust the prediction method by referring to the literature related to the data. The prediction unit can also optimize the prediction method based on the literature related to the data. Furthermore, the prediction unit can improve the reliability of the prediction result by referring to the literature related to the data. As a result, the prediction unit can obtain a highly reliable prediction result by referring to the literature related to the data. A part or all of the above-mentioned processing in the prediction unit can be performed, for example, using AI or can be performed without using AI. For example, the prediction unit can input the literature related to the data to the generation AI and cause the generation AI to improve the accuracy of the prediction.

[0111] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0112] The purchasing management system may further include an alert unit. The alert unit may issue an alert when an abnormal spending pattern or unexpected spending occurs based on the results of the analysis unit and the forecast unit. For example, when a sudden increase in spending is observed in a particular category, the alert unit may notify the buying company. Also, when the forecast unit detects an abnormal fluctuation in future spending, the alert unit may immediately provide that information. Furthermore, the alert unit may issue a warning when the credit risk of a trading partner increases. This allows the buying company to take countermeasures quickly, enhancing risk management.

[0113] The generation unit can evaluate the environmental impact of purchased items and generate a purchasing dictionary based on the evaluation results. For example, environmentally friendly products can be marked with a specific mark. The generation unit can also identify products with a high environmental impact and classify them into a different category. Furthermore, the generation unit can adjust keywords and phrases in the purchasing dictionary based on the environmental impact assessment data. This allows the buyer company to promote environmentally conscious purchasing activities.

[0114] The analysis unit can estimate the user's emotions and adjust the display format of the analysis results based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit can display the results in a simple, visually easy-to-understand format. If the user is relaxed, the analysis unit can provide the results in a format including detailed data and graphs. Furthermore, if the user is in a hurry, the analysis unit can display the results in a concise format that focuses on the main points. In this way, the analysis unit can provide an optimal display format according to the user's emotions and help the user understand.

[0115] The prediction unit may include a dashboard unit for visually displaying the prediction results. The dashboard unit displays the prediction results as graphs or charts, allowing the user to intuitively understand them. For example, the future expenditure forecast may be displayed as a line graph. Also, the expenditure forecast by category may be shown as a pie chart. Furthermore, the dashboard unit may include a function for suggesting an action plan based on the prediction results. This allows the user to plan specific actions based on the prediction results.

[0116] The collection unit can estimate the user's emotions and adjust the frequency of data collection based on the estimated user's emotions. For example, if the user is feeling stressed, the collection unit can reduce the frequency of data collection to reduce the burden on the user. Also, if the user is relaxed, the collection unit can increase the frequency of data collection to collect more detailed data. Furthermore, if the user is in a hurry, the collection unit can instantly collect necessary data and start processing quickly. This allows the collection unit to adjust the frequency of data collection according to the user's emotions, enabling efficient data collection.

[0117] The categorization unit can improve the accuracy of categorization by taking into account the interrelationships between data. For example, the categorization unit analyzes the interrelationships between data and classifies highly related data into the same category. The categorization unit can also apply an algorithm that improves the accuracy of categorization by taking into account the interrelationships between data. Furthermore, the categorization unit can dynamically adjust the categorization criteria based on the interrelationships between data. In this way, the categorization unit improves the accuracy of categorization by taking into account the interrelationships between data.

[0118] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user's emotions. For example, when the user is feeling stressed, data with high importance is collected with priority. When the user is relaxed, overall data can be collected in a balanced manner. Furthermore, when the user is in a hurry, necessary data can be collected immediately and processing can be started quickly. This allows the collection unit to determine the priority of data to be collected according to the user's emotions, enabling efficient data collection.

[0119] The collection department can analyze the purchasing history of the buyer company and select the optimal data collection method. For example, the collection department can analyze the past purchasing history of the buyer company and collect data focusing on frequently purchased items. The collection department can also preferentially collect data related to specific seasons or events from the purchasing history of the buyer company. Furthermore, the collection department can focus on collecting data from specific suppliers based on the purchasing history of the buyer company. This allows the collection department to select the optimal data collection method based on the purchasing history of the buyer company, enabling efficient data collection.

[0120] The collection unit can filter data based on the buyer company's current purchasing status or areas of interest when collecting data. For example, the collection unit grasps the buyer company's current purchasing status in real time and collects only related data. The collection unit can also preferentially collect data of a specific category based on the buyer company's areas of interest. Furthermore, the collection unit can filter unnecessary data according to the buyer company's purchasing status and collect data efficiently. This allows the collection unit to filter data based on the buyer company's current purchasing status and areas of interest, enabling efficient data collection.

[0121] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user's emotions. For example, when the user is feeling stressed, data with high importance is collected with priority. When the user is relaxed, overall data can be collected in a balanced manner. Furthermore, when the user is in a hurry, necessary data can be collected immediately and processing can be started quickly. This allows the collection unit to determine the priority of data to be collected according to the user's emotions, enabling efficient data collection.

[0122] The process flow of the second embodiment will be briefly described below.

[0123] Step 1: The collection department collects data from the buyer company's purchasing management system. The collection department extracts data including information such as purchased items, amounts, and business partners. The collection department can use AI to make data collection more efficient. Step 2: The generation unit uses a generation AI to generate a purchasing dictionary based on the data collected by the collection unit. The generation unit, for example, classifies purchased items by category and generates a purchasing dictionary including keywords and phrases corresponding to each category. The generation AI can generate the purchasing dictionary using a text generation AI (e.g., LLM). Step 3: The categorization unit categorizes the data based on the purchase dictionary generated by the generation unit. The categorization unit, for example, automatically classifies purchased items into categories. The categorization unit can use AI to streamline data categorization. Step 4: The analysis unit analyzes the data categorized by the categorization unit. For example, the analysis unit analyzes spending patterns and trends and performs a detailed analysis of spending. The analysis unit can use AI to streamline data analysis. Step 5: The prediction unit predicts expenditures based on the data analyzed by the analysis unit. The prediction unit predicts future expenditures based on, for example, past data. The prediction unit can use AI to make expenditure predictions more efficient.

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0125] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0126] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0127] Each of the multiple elements including the above-mentioned collection unit, generation unit, categorization unit, analysis unit, and prediction unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and collects data from a purchase management system of a buyer company. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a purchase dictionary based on the collected data. The categorization unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and categorizes data based on the generated purchase dictionary. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the categorized data. The prediction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and predicts expenditures based on the analyzed data. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0128] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0129] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0130] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0131] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0132] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0134] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0135] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0136] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0137] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0138] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0139] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0140] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0142] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0143] Each of the multiple elements including the above-mentioned collection unit, generation unit, categorization unit, analysis unit, and prediction unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and collects data from a purchase management system of a buyer company. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a purchase dictionary based on the collected data. The categorization unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and categorizes data based on the generated purchase dictionary. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the categorized data. The prediction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and predicts expenditures based on the analyzed data. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0144] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0145] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0147] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0148] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0150] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0151] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0152] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0153] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0154] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0155] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0156] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0157] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0158] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0159] Each of the multiple elements including the above-mentioned collection unit, generation unit, categorization unit, analysis unit, and prediction unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and collects data from the purchase management system of the buyer company. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a purchase dictionary based on the collected data. The categorization unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and categorizes data based on the generated purchase dictionary. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the categorized data. The prediction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and predicts expenditure based on the analyzed data. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0160] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0161] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0162] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0163] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0164] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0166] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0167] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0168] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0169] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0170] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0171] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0172] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0173] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0174] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0175] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0176] Each of the multiple elements including the above-mentioned collection unit, generation unit, categorization unit, analysis unit, and prediction unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and collects data from the purchase management system of the buyer company. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a purchase dictionary based on the collected data. The categorization unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and categorizes data based on the generated purchase dictionary. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the categorized data. The prediction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and predicts expenditure based on the analyzed data. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0177] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0178] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0179] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0180] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0181] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0182] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0184] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0185] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0186] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0187] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0188] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0189] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0190] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0191] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0192] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0193] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0194] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0195] (Appendix 1) A collection unit that collects data; a generation unit that generates a purchase dictionary based on the data collected by the collection unit; a categorizing unit that categorizes data based on the purchase dictionary generated by the generating unit; an analysis unit that analyzes the data categorized by the categorization unit; A prediction unit that predicts expenditures based on the data analyzed by the analysis unit. A system characterized by: (Appendix 2) The generation unit is Categorize purchased items into categories and generate a purchasing dictionary that contains keywords or phrases that correspond to each category 2. The system of claim 1, (Appendix 3) The analysis unit is Analyze spending patterns or trends and conduct detailed analysis of spending 2. The system of claim 1, (Appendix 4) The prediction unit is Predict future spending based on past data 2. The system of claim 1, (Appendix 5) The collecting unit includes: Extract data from a purchasing management system for companies that use a purchasing management system 2. The system of claim 1, (Appendix 6) The categorization unit includes: Automatically categorize data based on generated purchasing dictionaries 2. The system of claim 1, (Appendix 7) The collecting unit includes: Adjusting data collection timing based on inferring user emotions 2. The system of claim 1, (Appendix 8) The collecting unit includes: Analyze the purchasing history of buyer companies and select the optimal data collection method 2. The system of claim 1, (Appendix 9) The collecting unit includes: Filter data collection based on the buyer's current purchasing behavior or interests 2. The system of claim 1, (Appendix 10) The collecting unit includes: Infer user sentiment and prioritize data to be collected based on the inferred user sentiment 2. The system of claim 1, (Appendix 11) The collecting unit includes: When collecting data, prioritize collecting relevant data by considering the geographic location of buyer companies. 2. The system of claim 1, (Appendix 12) The collecting unit includes: During data collection, analyze the buyer company's social media activity and collect relevant data. 2. The system of claim 1, (Appendix 13) The generation unit is A user's emotion is estimated, and a method for generating a purchasing dictionary is adjusted based on the estimated user's emotion. 2. The system of claim 1, (Appendix 14) The generation unit is When generating a purchasing dictionary, adjust the dictionary detail level based on the importance of the purchased items. 2. The system of claim 1, (Appendix 15) The generation unit is When generating a purchasing dictionary, apply different generation algorithms depending on the category of the purchased item. 2. The system of claim 1, (Appendix 16) The generation unit is To estimate a user's emotion and adjust the length of a purchase dictionary based on the estimated user's emotion. 2. The system of claim 1, (Appendix 17) The generation unit is When generating purchasing dictionaries, determine the priority of dictionaries based on when the purchased items were submitted. 2. The system of claim 1, (Appendix 18) The generation unit is When generating purchasing dictionaries, adjust the dictionary order based on the relevance of purchased items 2. The system of claim 1, (Appendix 19) The categorization unit includes: Infer user sentiment and adjust data categorization criteria based on the inferred user sentiment 2. The system of claim 1, (Appendix 20) The categorization unit includes: When categorizing, the accuracy of categorization is improved by considering the correlation of data. 2. The system of claim 1, (Appendix 21) The categorization unit includes: When categorizing, the attribute information of the data submitter is taken into consideration. 2. The system of claim 1, (Appendix 22) The categorization unit includes: Infer user sentiment and adjust the order in which categorization results are displayed based on the estimated user sentiment 2. The system of claim 1, (Appendix 23) The categorization unit includes: When categorizing, the geographical distribution of data is taken into account. 2. The system of claim 1, (Appendix 24) The categorization unit includes: When categorizing, refer to the relevant literature of the data to improve the accuracy of categorization. 2. The system of claim 1, (Appendix 25) The analysis unit is Infer user sentiment and adjust how analytics are displayed based on the inferred user sentiment 2. The system of claim 1, (Appendix 26) The analysis unit is During analysis, refer to past analysis data to optimize the current analysis 2. The system of claim 1, (Appendix 27) The analysis unit is During analysis, apply different analytical techniques to different categories of data 2. The system of claim 1, (Appendix 28) The analysis unit is Inferring user emotions and adjusting the importance of analysis based on the estimated user emotions 2. The system of claim 1, (Appendix 29) The analysis unit is During analysis, analyze changes in analysis based on when data was submitted 2. The system of claim 1, (Appendix 30) The analysis unit is When analyzing, the analysis is performed by referring to the relevant market data of the data. 2. The system of claim 1, (Appendix 31) The prediction unit is Infer user sentiment and adjust prediction methods based on the inferred user sentiment 2. The system of claim 1, (Appendix 32) The prediction unit is When making predictions, look at past data to optimize the prediction algorithm 2. The system of claim 1, (Appendix 33) The prediction unit is When making predictions, apply different prediction methods to different categories of data 2. The system of claim 1, (Appendix 34) The prediction unit is Infer user sentiment and prioritize predictions based on the inferred user sentiment 2. The system of claim 1, (Appendix 35) The prediction unit is At the time of forecasting, the geographic location of the data is taken into account to make the prediction. 2. The system of claim 1, (Appendix 36) The prediction unit is When making predictions, refer to the relevant literature for the data to improve the accuracy of the predictions. 2. The system of claim 1, [Explanation of symbols]

[0196] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects data; a generation unit that generates a purchase dictionary based on the data collected by the collection unit; a categorizing unit that categorizes data based on the purchase dictionary generated by the generating unit; an analysis unit that analyzes the data categorized by the categorization unit; A prediction unit that predicts expenditures based on the data analyzed by the analysis unit. A system characterized by:

2. The generation unit is Categorize purchased items into categories and generate a purchasing dictionary that contains keywords or phrases that correspond to each category 2. The system of claim 1 .

3. The analysis unit is Analyze spending patterns or trends and conduct detailed analysis of spending 2. The system of claim 1 .

4. The prediction unit is Predict future spending based on past data 2. The system of claim 1 .

5. The collecting unit includes: Extract data from a purchasing management system for companies that use a purchasing management system 2. The system of claim 1 .

6. The categorization unit includes: Automatically categorize data based on generated purchasing dictionaries 2. The system of claim 1 .

7. The collecting unit includes: Adjusting data collection timing based on inferring user emotions 2. The system of claim 1 .

8. The collecting unit includes: Analyze the purchasing history of buyer companies and select the optimal data collection method 2. The system of claim 1 .

Images