system

Abstract

The system according to the embodiment aims to enable salespeople to recommend products quickly and appropriately. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, a recommendation unit, and a reference unit. The reception unit receives requests from sales representatives. The analysis unit analyzes the requests received by the reception unit and recommends appropriate products based on past proposals and customer data. The recommendation unit provides the products recommended by the analysis unit. The reference unit references success stories from other sales representatives.

Description

[Technical Field]

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

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

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

[0004] Conventional technology makes it difficult for sales representatives to quickly recommend optimal products, and there is room for improvement in the quality and efficiency of proposals.

[0005] The system according to the embodiment aims to enable salespeople to recommend products quickly and appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a recommendation unit, and a reference unit. The reception unit receives requests from sales representatives. The analysis unit analyzes the requests received by the reception unit and recommends appropriate products based on past proposals and customer data. The recommendation unit provides the products recommended by the analysis unit. The reference unit references success stories from other sales representatives. [Effects of the Invention]

[0007] The system according to the embodiment can enable salespeople to recommend products quickly and appropriately. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A product recommendation system according to an embodiment of the present invention is a system in which, when a salesperson inputs a product request in natural language, an AI analyzes the request and recommends the most suitable product based on past proposals and customer data. When a salesperson inputs a product request in natural language, the AI ​​analyzes the request and recommends the most suitable product based on past proposals and customer data. Furthermore, the system allows reference to successful proposals made by other salespeople, improving the quality and efficiency of proposals. For example, a product recommendation system inputs a request such as "I would like to propose a new product." This request is input into an AI. The product recommendation system then analyzes the input request using AI. The AI ​​analyzes the request using natural language processing technology and recommends the most suitable product based on past proposals and customer data. For example, if a similar request has been made in the past, the AI ​​recommends the most suitable product based on the proposal. Furthermore, the product recommendation system analyzes customer data and recommends products that meet the customer's needs. Furthermore, the product recommendation system allows reference to successful proposals made by other salespeople. For example, the system can refer to successful proposals made by other salespeople and make proposals based on those proposals. This allows salespeople to easily input product requirements in natural language and have AI recommend the most suitable products, improving the quality and efficiency of proposals. This allows salespeople to easily input product requirements in natural language and have AI recommend the most suitable products, improving the quality and efficiency of proposals. For example, when a salesperson inputs a product requirement in natural language, the AI ​​analyzes past proposals and customer data to recommend the most suitable products. In addition, the quality and efficiency of proposals can be improved by allowing salespeople to refer to success stories from other salespeople.

[0029] A product recommendation system according to an embodiment includes a reception unit, an analysis unit, a recommendation unit, and a reference unit. The reception unit receives requests from sales representatives. The sales representative's requests include, but are not limited to, product-related questions, complaints, and proposals. The reception unit receives requests input by the sales representatives in natural language, for example. The reception unit can also support various input methods, such as voice input and text input. For example, if the sales representative inputs a request by voice, the request can be received using voice recognition technology. The analysis unit uses AI to analyze the request received by the reception unit. The analysis can be performed using, for example, natural language processing technology, but is not limited to, for example. For example, the analysis unit can analyze past proposals using data mining technology and recommend optimal products. The analysis unit can also analyze customer data and recommend products that meet the customer's needs. For example, the analysis unit recommends optimal products based on the customer's past purchase history and customer attribute data. The recommendation unit provides the products recommended by the analysis unit. For example, the recommendation unit presents the products recommended by the analysis unit to the sales representative. The recommendation unit can also provide detailed information about the product and information about related products. For example, the recommendation unit explains the features and advantages of the recommended product. The recommendation unit also provides information about related products, allowing the sales representative to have more choices. The reference unit retrieves success stories of other sales representatives from a database and provides them to the analysis unit. The reference unit selects the best case for the current request based on, for example, data on past success stories. The reference unit can also apply different reference algorithms depending on the category of the success story. For example, the reference unit references success stories of different categories, such as cases of increased sales and cases of increased customer satisfaction. This allows the product recommendation system according to the embodiment to efficiently accept and analyze requests from sales representatives, recommend the best products, and reference success stories.

[0030] The reception unit can analyze the sales representative's past request history and select the optimal reception method. For example, the reception unit preferentially suggests reception methods (voice, text, etc.) that the sales representative has frequently used in the past. The reception unit can also select the optimal reception method for a specific time period from the sales representative's past request history. The reception unit can also analyze the sales representative's past request history and suggest the most efficient reception method. In this way, by analyzing the past request history, the optimal reception method can be provided to the sales representative. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's past request history data into the generation AI and have the generation AI select the optimal reception method.

[0031] When receiving a request, the reception unit can filter the requests based on the sales representative's current project or area of ​​interest. For example, the reception unit can preferentially receive only requests related to the project the sales representative is currently working on. The reception unit can also filter and receive highly relevant requests based on the sales representative's area of ​​interest. The reception unit can also filter and receive appropriate requests according to the progress of the sales representative's current project. In this way, by filtering requests based on the sales representative's current project or area of ​​interest, highly relevant requests can be preferentially received. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's project data into a generation AI and have the generation AI perform filtering.

[0032] When receiving a request, the reception unit can select an appropriate reception means depending on the input method of the sales representative. For example, if the sales representative inputs a request by voice, the reception unit can receive the request using voice recognition technology. Furthermore, if the sales representative inputs a request by text, the reception unit can also receive the request using text analysis technology. Furthermore, if the sales representative inputs a request by image, the reception unit can also receive the request using image recognition technology. This enables efficient request reception by selecting the optimal reception means depending on the input method of the sales representative. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's voice data into a generation AI and have the generation AI convert the voice data into text data.

[0033] When receiving a request, the reception unit can prioritize receiving highly relevant requests by taking into account the geographical location information of the sales representative. For example, if the sales representative is in a specific area, the reception unit can prioritize receiving requests related to that area. The reception unit can also prioritize receiving requests related to locations close to the sales representative's current location. If the sales representative is traveling, the reception unit can also prioritize receiving requests related to the sales representative's destination. In this way, by taking the geographical location information of the sales representative into consideration, highly relevant requests can be prioritized. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the geographical location data of the sales representative into the generation AI and cause the generation AI to select highly relevant requests.

[0034] When receiving a request, the reception unit can analyze the social media activity of the sales representative and receive related requests. For example, the reception unit can prioritize receiving requests related to products mentioned by the sales representative on social media. The reception unit can also analyze the sales representative's social media activity and receive related requests. The reception unit can also refer to the activity of the sales representative's friends on social media to receive related requests. In this way, by analyzing the sales representative's social media activity, highly relevant requests can be received preferentially. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's social media data into a generation AI and have the generation AI select related requests.

[0035] When receiving a request, the reception unit can customize the reception method by reflecting the sales representative's past feedback. The reception unit, for example, suggests the optimal reception method based on feedback provided by the sales representative in the past. The reception unit can also preferentially suggest a specific reception method based on the sales representative's past feedback. The reception unit can also analyze the sales representative's past feedback and suggest the most efficient reception method. In this way, the optimal reception method can be provided by reflecting the sales representative's past feedback. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's past feedback data into the generation AI and have the generation AI customize the reception method.

[0036] The analysis unit can adjust the level of detail of the analysis based on the importance of the request during analysis. For example, the analysis unit performs a detailed analysis on a request with a high level of importance. The analysis unit can also perform a simplified analysis on a request with a low level of importance. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the request. This enables efficient analysis by adjusting the level of detail of the analysis according to the importance of the request. 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 requirement importance data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0037] The analysis unit can apply an appropriate analysis algorithm depending on the category of the request during analysis. The analysis unit selects the optimal analysis algorithm depending on, for example, the product category. The analysis unit can also apply different analysis algorithms depending on the category of customer data. The analysis unit can also dynamically select the optimal analysis algorithm based on the category of the request. This improves the accuracy of the analysis by applying the optimal analysis algorithm depending on the category of the request. 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 request category data to the generation AI and have the generation AI select the analysis algorithm.

[0038] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the sales representative's past analysis results. The analysis unit improves the accuracy of the analysis, for example, based on the sales representative's past analysis results. The analysis unit can also refer to the sales representative's past analysis results to perform optimal analysis for similar requests. The analysis unit can also analyze the sales representative's past analysis results and optimize the analysis algorithm. In this way, the accuracy of the analysis is improved by referring to the sales representative's past analysis results. 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 the sales representative's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0039] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the request. For example, the analysis unit prioritizes analysis of requests submitted earlier. The analysis unit can also postpone analysis of requests submitted later. The analysis unit can also dynamically adjust the priority of analysis based on the submission time. This enables efficient analysis by determining the priority of analysis based on the submission time of the request. 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 request submission time data to the generation AI and have the generation AI determine the analysis priority.

[0040] The analysis unit can adjust the order of analysis based on the relevance of the requests during analysis. For example, the analysis unit prioritizes analysis of highly relevant requests. The analysis unit can also postpone analysis of less relevant requests. The analysis unit can also dynamically adjust the order of analysis based on the relevance of the requests. This enables efficient analysis by adjusting the order of analysis based on the relevance of the requests. 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 request relevance data to the generation AI and cause the generation AI to adjust the order of analysis.

[0041] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the sales representative's level of expertise. For example, if the sales representative's level of expertise is high, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the sales representative's level of expertise is low, the analysis unit can also provide analysis results that avoid technical terms. The analysis unit can also dynamically adjust the use of technical terms in the analysis according to the sales representative's level of expertise. This allows for more appropriate analysis results to be provided by adjusting the use of technical terms in the analysis according to the sales representative's level of expertise. Some or all of the above-described 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 the sales representative's level of expertise data into a generation AI and have the generation AI execute the use of technical terms.

[0042] The recommendation unit can adjust the level of detail of the recommendation based on the importance of the product when making a recommendation. For example, the recommendation unit makes a detailed recommendation for a product with a high importance. The recommendation unit can also make a simplified recommendation for a product with a low importance. The recommendation unit can also dynamically adjust the level of detail of the recommendation according to the importance of the product. This enables efficient recommendations by adjusting the level of detail of the recommendation according to the importance of the product. Some or all of the above-mentioned processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit can input product importance data to the generation AI and cause the generation AI to adjust the level of detail of the recommendation.

[0043] The recommendation unit can apply an appropriate recommendation algorithm depending on the product category when making a recommendation. The recommendation unit selects an optimal recommendation algorithm depending on, for example, the product category. The recommendation unit can also apply different recommendation algorithms depending on the category of customer data. The recommendation unit can also dynamically select an optimal recommendation algorithm based on the product category. This improves the accuracy of recommendations by applying an optimal recommendation algorithm depending on the product category. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit can input product category data to a generation AI and cause the generation AI to select a recommendation algorithm.

[0044] When making a recommendation, the recommendation unit can improve the accuracy of the recommendation by referring to the sales representative's past recommendation results. The recommendation unit improves the accuracy of the recommendation based on, for example, the sales representative's past recommendation results. The recommendation unit can also refer to the sales representative's past recommendation results to make optimal recommendations for similar requests. The recommendation unit can also analyze the sales representative's past recommendation results and optimize the recommendation algorithm. In this way, the accuracy of the recommendation is improved by referring to the sales representative's past recommendation results. Some or all of the above-mentioned processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit can input the sales representative's past recommendation result data into the generation AI and cause the generation AI to improve the accuracy of the recommendations.

[0045] When making a recommendation, the recommendation unit can determine the priority of recommendations based on the submission time of the product. For example, the recommendation unit preferentially recommends products that were submitted earlier. The recommendation unit can also recommend products that were submitted later later. The recommendation unit can also dynamically adjust the priority of recommendations based on the submission time. This enables efficient recommendations by determining the priority of recommendations based on the submission time of the product. Some or all of the above-mentioned processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit can input product submission time data into the generation AI and have the generation AI determine the recommendation priority.

[0046] The recommendation unit can adjust the order of recommendations based on the relevance of products when making a recommendation. For example, the recommendation unit prioritizes recommending highly relevant products. The recommendation unit can also recommend less relevant products later. The recommendation unit can also dynamically adjust the order of recommendations based on the relevance of products. This enables efficient recommendations by adjusting the order of recommendations based on the relevance of products. Some or all of the above-described processing in the recommendation unit may be performed using AI, for example, or may be performed without using AI. For example, the recommendation unit can input product relevance data to a generation AI and cause the generation AI to adjust the order of recommendations.

[0047] The recommendation unit can adjust the use of technical terminology in the recommendation depending on the expertise level of the salesperson when making a recommendation. For example, if the expertise level of the salesperson is high, the recommendation unit can provide a recommendation that uses a lot of technical terminology. Furthermore, if the expertise level of the salesperson is low, the recommendation unit can also provide a recommendation that avoids technical terminology. The recommendation unit can also dynamically adjust the use of technical terminology in the recommendation depending on the expertise level of the salesperson. This allows for more appropriate recommendations by adjusting the use of technical terminology in the recommendation depending on the expertise level of the salesperson. Some or all of the above-described processing in the recommendation unit may be performed using AI, for example, or may be performed without using AI. For example, the recommendation unit can input expertise level data of the salesperson to a generation AI and have the generation AI execute the use of technical terminology.

[0048] During the reference process, the reference unit can refer to data on past success cases to select an appropriate case for the current request. For example, the reference unit selects the best case for the current request based on data on past success cases. The reference unit can also preferentially select successful cases for similar requests. The reference unit can also analyze data on past success cases and select the most relevant case. In this way, by referring to data on past success cases, the best case for the current request can be provided. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input data on past success cases into a generation AI and have the generation AI select the best case.

[0049] The reference unit can apply different reference algorithms depending on the category of the success story during reference. The reference unit selects an optimal reference algorithm depending on, for example, the category of the success story. The reference unit can also apply different reference algorithms depending on the category of customer data. The reference unit can also dynamically select an optimal reference algorithm based on the category of the success story. This improves the accuracy of reference by applying the optimal reference algorithm depending on the category of the success story. Some or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input category data of the success story to the generation AI and have the generation AI select the reference algorithm.

[0050] The reference unit can improve the accuracy of the reference by referring to the sales representative's past reference results during the reference. The reference unit improves the accuracy of the reference, for example, based on the sales representative's past reference results. The reference unit can also refer to the sales representative's past reference results to perform optimal reference for similar requests. The reference unit can also analyze the sales representative's past reference results and optimize the reference algorithm. In this way, the accuracy of the reference is improved by referring to the sales representative's past reference results. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input the sales representative's past reference result data into the generation AI and have the generation AI improve the accuracy of the reference.

[0051] The reference unit can determine the reference priority based on the submission time of the success case during reference. For example, the reference unit prioritizes reference of a success case submitted earlier. The reference unit can also postpone reference of a success case submitted later. The reference unit can also dynamically adjust the reference priority based on the submission time. This enables efficient reference by determining the reference priority based on the submission time of the success case. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input data on the submission time of the success case into the generation AI and have the generation AI determine the reference priority.

[0052] The reference unit can adjust the order of reference based on the relevance of the success cases during reference. For example, the reference unit prioritizes reference to highly relevant success cases. The reference unit can also postpone reference to less relevant success cases. The reference unit can also dynamically adjust the order of reference based on the relevance of the success cases. This enables efficient reference by adjusting the order of reference based on the relevance of the success cases. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input relevance data of the success cases into the generation AI and have the generation AI adjust the order of reference.

[0053] The reference unit can adjust the use of technical terminology in the reference depending on the sales representative's level of expertise during the reference. For example, if the sales representative has a high level of expertise, the reference unit can provide success stories that use a lot of technical terminology. Furthermore, if the sales representative has a low level of expertise, the reference unit can provide success stories that avoid technical terminology. The reference unit can also dynamically adjust the use of technical terminology in the reference depending on the sales representative's level of expertise. This allows for more appropriate success stories to be provided by adjusting the use of technical terminology in the reference depending on the sales representative's level of expertise. Some or all of the above-described processing in the reference unit can be performed using, or without, AI, for example. For example, the reference unit can input the sales representative's level of expertise data into a generation AI and have the generation AI execute the use of technical terminology.

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

[0055] The reception unit can dynamically adjust the priority of requests based on the sales representative's past request history. For example, it can prioritize requests that have been frequently made in the past. It can also extract specific patterns from past request history and respond quickly if a similar pattern occurs again. Furthermore, by analyzing past request history, it can also concentrate resources on specific time periods or days of the week when many requests occur. This makes it possible to efficiently process requests by utilizing past request history.

[0056] The analysis unit can predict the success rate of proposals based on the content of past proposals made by sales representatives. For example, it analyzes the content of proposals that have been successful in the past and calculates the probability that a similar proposal will be successful again. It can also predict the success rate of proposals for specific customers by combining the content of past proposals with customer data. Furthermore, it can extract areas for improvement in proposals based on the content of past proposals and reflect them in the next proposal. This makes it possible to improve the success rate of proposals by utilizing the content of past proposals.

[0057] The recommendation unit can improve the accuracy of recommendations based on the sales representative's past recommendation history. For example, it analyzes recommendations that were successful in the past and makes recommendations again under similar conditions. It can also predict the success rate of recommendations for specific customers by combining past recommendation history with customer data. Furthermore, it can extract areas for improvement in recommendations based on past recommendation history and reflect them in the next recommendation. This makes it possible to improve recommendation accuracy by utilizing past recommendation history.

[0058] The reference section can improve the accuracy of references based on the sales representative's past reference history. For example, it analyzes past successful references and references them again under similar conditions. It can also combine past reference history with customer data to predict the success rate of references for specific customers. Furthermore, it can extract areas for improvement in references based on past reference history and reflect them in the next reference. This makes it possible to improve reference accuracy by utilizing past reference history.

[0059] The reference department can dynamically adjust the priority of references based on the sales representative's past reference results. For example, it can prioritize successful cases that have been frequently referenced in the past. It can also extract specific patterns from past reference results and respond quickly if a similar pattern occurs again. Furthermore, by analyzing past reference results, it can also concentrate resources on specific time periods or days of the week if many references occur during those times. This makes it possible to utilize past reference results to enable efficient references.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The reception unit receives a request from a sales representative. The request from a sales representative may include, but is not limited to, a question, a complaint, or a suggestion regarding a product. The reception unit receives, for example, a request input by the sales representative in natural language. The reception unit can also support various input methods, such as voice input and text input. For example, if the sales representative inputs a request by voice, the request can be received using voice recognition technology. Step 2: The analysis unit uses AI to analyze the request received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to this example. For example, the analysis unit uses data mining technology to analyze past proposals and recommend the most suitable product. The analysis unit can also analyze customer data and recommend products that meet the customer's needs. For example, the analysis unit recommends the most suitable product based on the customer's past purchase history and customer attribute data. Step 3: The recommendation unit provides the products recommended by the analysis unit. For example, the recommendation unit presents the products recommended by the analysis unit to the sales representative. The recommendation unit can also provide detailed information about the products and information about related products. For example, the recommendation unit explains the features and advantages of the recommended products. The recommendation unit also provides information about related products, allowing the sales representative to have more choices. Step 4: The reference unit retrieves success stories of other sales representatives from the database and provides them to the analysis unit. For example, the reference unit selects the case that best meets the current requirements based on data on past success stories. The reference unit can also apply different reference algorithms depending on the category of the success story. For example, the reference unit references success stories from different categories, such as cases of increased sales and cases of increased customer satisfaction.

[0062] (Example 2) A product recommendation system according to an embodiment of the present invention is a system in which, when a salesperson inputs a product request in natural language, an AI analyzes the request and recommends the most suitable product based on past proposals and customer data. When a salesperson inputs a product request in natural language, the AI ​​analyzes the request and recommends the most suitable product based on past proposals and customer data. Furthermore, the system allows reference to successful proposals made by other salespeople, improving the quality and efficiency of proposals. For example, a product recommendation system inputs a request such as "I would like to propose a new product." This request is input into an AI. The product recommendation system then analyzes the input request using AI. The AI ​​analyzes the request using natural language processing technology and recommends the most suitable product based on past proposals and customer data. For example, if a similar request has been made in the past, the AI ​​recommends the most suitable product based on the proposal. Furthermore, the product recommendation system analyzes customer data and recommends products that meet the customer's needs. Furthermore, the product recommendation system allows reference to successful proposals made by other salespeople. For example, the system can refer to successful proposals made by other salespeople and make proposals based on those proposals. This allows salespeople to easily input product requirements in natural language and have AI recommend the most suitable products, improving the quality and efficiency of proposals. This allows salespeople to easily input product requirements in natural language and have AI recommend the most suitable products, improving the quality and efficiency of proposals. For example, when a salesperson inputs a product requirement in natural language, the AI ​​analyzes past proposals and customer data to recommend the most suitable products. In addition, the quality and efficiency of proposals can be improved by allowing salespeople to refer to success stories from other salespeople.

[0063] A product recommendation system according to an embodiment includes a reception unit, an analysis unit, a recommendation unit, and a reference unit. The reception unit receives requests from sales representatives. The sales representative's requests include, but are not limited to, product-related questions, complaints, and proposals. The reception unit receives requests input by the sales representatives in natural language, for example. The reception unit can also support various input methods, such as voice input and text input. For example, if the sales representative inputs a request by voice, the request can be received using voice recognition technology. The analysis unit uses AI to analyze the request received by the reception unit. The analysis can be performed using, for example, natural language processing technology, but is not limited to, for example. For example, the analysis unit can analyze past proposals using data mining technology and recommend optimal products. The analysis unit can also analyze customer data and recommend products that meet the customer's needs. For example, the analysis unit recommends optimal products based on the customer's past purchase history and customer attribute data. The recommendation unit provides the products recommended by the analysis unit. For example, the recommendation unit presents the products recommended by the analysis unit to the sales representative. The recommendation unit can also provide detailed information about the product and information about related products. For example, the recommendation unit explains the features and advantages of the recommended product. The recommendation unit also provides information about related products, allowing the sales representative to have more choices. The reference unit retrieves success stories of other sales representatives from a database and provides them to the analysis unit. The reference unit selects the best case for the current request based on, for example, data on past success stories. The reference unit can also apply different reference algorithms depending on the category of the success story. For example, the reference unit references success stories of different categories, such as cases of increased sales and cases of increased customer satisfaction. This allows the product recommendation system according to the embodiment to efficiently accept and analyze requests from sales representatives, recommend the best products, and reference success stories.

[0064] The reception unit can estimate the salesperson's emotions and adjust the timing of request acceptance based on the estimated emotions. For example, if the salesperson is feeling stressed, the reception unit uses AI to estimate the salesperson's emotions and delay accepting the request until the salesperson is relaxed. Furthermore, if the salesperson is in a hurry, the reception unit can use AI to estimate the salesperson's emotions and immediately accept the request. Furthermore, if the salesperson is excited, the reception unit can use AI to estimate the salesperson's emotions and temporarily suspend accepting the request until the salesperson has calmed down. This allows the timing of request acceptance to be adjusted according to the salesperson's emotions, enabling the request to be accepted at a more appropriate time. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input facial expression data of the salesperson into the generation AI and have the generation AI execute emotion estimation.

[0065] The reception unit can analyze the sales representative's past request history and select the optimal reception method. For example, the reception unit preferentially suggests reception methods (voice, text, etc.) that the sales representative has frequently used in the past. The reception unit can also select the optimal reception method for a specific time period from the sales representative's past request history. The reception unit can also analyze the sales representative's past request history and suggest the most efficient reception method. In this way, by analyzing the past request history, the optimal reception method can be provided to the sales representative. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's past request history data into the generation AI and have the generation AI select the optimal reception method.

[0066] When receiving a request, the reception unit can filter the requests based on the sales representative's current project or area of ​​interest. For example, the reception unit can preferentially receive only requests related to the project the sales representative is currently working on. The reception unit can also filter and receive highly relevant requests based on the sales representative's area of ​​interest. The reception unit can also filter and receive appropriate requests according to the progress of the sales representative's current project. In this way, by filtering requests based on the sales representative's current project or area of ​​interest, highly relevant requests can be preferentially received. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's project data into a generation AI and have the generation AI perform filtering.

[0067] When receiving a request, the reception unit can select an appropriate reception means depending on the input method of the sales representative. For example, if the sales representative inputs a request by voice, the reception unit can receive the request using voice recognition technology. Furthermore, if the sales representative inputs a request by text, the reception unit can also receive the request using text analysis technology. Furthermore, if the sales representative inputs a request by image, the reception unit can also receive the request using image recognition technology. This enables efficient request reception by selecting the optimal reception means depending on the input method of the sales representative. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's voice data into a generation AI and have the generation AI convert the voice data into text data.

[0068] The reception unit can estimate the emotions of the sales representative and determine the priority of the requests to be received based on the estimated emotions. For example, when the sales representative is stressed, the reception unit uses AI to estimate the emotions and prioritize requests with high importance. Alternatively, when the sales representative is relaxed, the reception unit can use AI to estimate the emotions and prioritize requests. Alternatively, when the sales representative is in a hurry, the reception unit can use AI to estimate the emotions and prioritize requests with high importance. This allows requests to be prioritized based on the emotions of the sales representative, allowing important requests to be processed first. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit can be performed using AI, for example, or without AI. For example, the reception unit can input facial expression data of the sales representative into the generation AI and have the generation AI perform emotion estimation.

[0069] When receiving a request, the reception unit can prioritize receiving highly relevant requests by taking into account the geographical location information of the sales representative. For example, if the sales representative is in a specific area, the reception unit can prioritize receiving requests related to that area. The reception unit can also prioritize receiving requests related to locations close to the sales representative's current location. If the sales representative is traveling, the reception unit can also prioritize receiving requests related to the sales representative's destination. In this way, by taking the geographical location information of the sales representative into consideration, highly relevant requests can be prioritized. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit can input the geographical location data of the sales representative into the generation AI and cause the generation AI to select highly relevant requests.

[0070] When receiving a request, the reception unit can analyze the social media activity of the sales representative and receive related requests. For example, the reception unit can prioritize receiving requests related to products mentioned by the sales representative on social media. The reception unit can also analyze the sales representative's social media activity and receive related requests. The reception unit can also refer to the activity of the sales representative's friends on social media to receive related requests. In this way, by analyzing the sales representative's social media activity, highly relevant requests can be received preferentially. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's social media data into a generation AI and have the generation AI select related requests.

[0071] When receiving a request, the reception unit can customize the reception method by reflecting the sales representative's past feedback. The reception unit, for example, suggests the optimal reception method based on feedback provided by the sales representative in the past. The reception unit can also preferentially suggest a specific reception method based on the sales representative's past feedback. The reception unit can also analyze the sales representative's past feedback and suggest the most efficient reception method. In this way, the optimal reception method can be provided by reflecting the sales representative's past feedback. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the sales representative's past feedback data into the generation AI and have the generation AI customize the reception method.

[0072] The analysis unit can estimate the salesperson's emotions and adjust the way the analysis is presented based on the estimated emotions. For example, if the salesperson is stressed, the analysis unit provides simple, highly visible analysis results. Furthermore, if the salesperson is relaxed, the analysis unit can provide detailed analysis results. Furthermore, if the salesperson is in a hurry, the analysis unit can provide analysis results that focus on the main points. By adjusting the way the analysis is presented based on the salesperson's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input facial expression data of the salesperson into the generation AI and have the generation AI perform emotion estimation.

[0073] The analysis unit can adjust the level of detail of the analysis based on the importance of the request during analysis. For example, the analysis unit performs a detailed analysis on a request with a high level of importance. The analysis unit can also perform a simplified analysis on a request with a low level of importance. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the request. This enables efficient analysis by adjusting the level of detail of the analysis according to the importance of the request. 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 requirement importance data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0074] The analysis unit can apply an appropriate analysis algorithm depending on the category of the request during analysis. The analysis unit selects the optimal analysis algorithm depending on, for example, the product category. The analysis unit can also apply different analysis algorithms depending on the category of customer data. The analysis unit can also dynamically select the optimal analysis algorithm based on the category of the request. This improves the accuracy of the analysis by applying the optimal analysis algorithm depending on the category of the request. 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 request category data to the generation AI and have the generation AI select the analysis algorithm.

[0075] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the sales representative's past analysis results. The analysis unit improves the accuracy of the analysis, for example, based on the sales representative's past analysis results. The analysis unit can also refer to the sales representative's past analysis results to perform optimal analysis for similar requests. The analysis unit can also analyze the sales representative's past analysis results and optimize the analysis algorithm. In this way, the accuracy of the analysis is improved by referring to the sales representative's past analysis results. 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 the sales representative's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0076] The analysis unit can estimate the salesperson's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the salesperson is in a hurry, the analysis unit can provide a short and concise analysis result. Furthermore, if the salesperson is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the salesperson is excited, the analysis unit can provide an analysis result with visually stimulating effects. By adjusting the length of the analysis according to the salesperson's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input facial expression data of the salesperson into the generation AI and have the generation AI perform emotion estimation.

[0077] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the request. For example, the analysis unit prioritizes analysis of requests submitted earlier. The analysis unit can also postpone analysis of requests submitted later. The analysis unit can also dynamically adjust the priority of analysis based on the submission time. This enables efficient analysis by determining the priority of analysis based on the submission time of the request. 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 request submission time data to the generation AI and have the generation AI determine the analysis priority.

[0078] The analysis unit can adjust the order of analysis based on the relevance of the requests during analysis. For example, the analysis unit prioritizes analysis of highly relevant requests. The analysis unit can also postpone analysis of less relevant requests. The analysis unit can also dynamically adjust the order of analysis based on the relevance of the requests. This enables efficient analysis by adjusting the order of analysis based on the relevance of the requests. 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 request relevance data to the generation AI and cause the generation AI to adjust the order of analysis.

[0079] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the sales representative's level of expertise. For example, if the sales representative's level of expertise is high, the analysis unit can provide analysis results that use a lot of technical terms. Furthermore, if the sales representative's level of expertise is low, the analysis unit can also provide analysis results that avoid technical terms. The analysis unit can also dynamically adjust the use of technical terms in the analysis according to the sales representative's level of expertise. This allows for more appropriate analysis results to be provided by adjusting the use of technical terms in the analysis according to the sales representative's level of expertise. Some or all of the above-described 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 the sales representative's level of expertise data into a generation AI and have the generation AI execute the use of technical terms.

[0080] The recommendation unit can estimate the salesperson's emotions and adjust the recommendation method based on the estimated emotions. For example, if the salesperson is stressed, the recommendation unit can provide a simple, highly visible recommendation method. Furthermore, if the salesperson is relaxed, the recommendation unit can provide a detailed recommendation method. Furthermore, if the salesperson is in a hurry, the recommendation unit can provide a recommendation method that focuses on the main points. This allows for more appropriate recommendations by adjusting the recommendation method according to the salesperson's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the recommendation unit can be performed using, for example, AI, or without AI. For example, the recommendation unit can input facial expression data of the salesperson into the generation AI and have the generation AI perform emotion estimation.

[0081] The recommendation unit can adjust the level of detail of the recommendation based on the importance of the product when making a recommendation. For example, the recommendation unit makes a detailed recommendation for a product with a high importance. The recommendation unit can also make a simplified recommendation for a product with a low importance. The recommendation unit can also dynamically adjust the level of detail of the recommendation according to the importance of the product. This enables efficient recommendations by adjusting the level of detail of the recommendation according to the importance of the product. Some or all of the above-mentioned processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit can input product importance data to the generation AI and cause the generation AI to adjust the level of detail of the recommendation.

[0082] The recommendation unit can apply an appropriate recommendation algorithm depending on the product category when making a recommendation. The recommendation unit selects an optimal recommendation algorithm depending on, for example, the product category. The recommendation unit can also apply different recommendation algorithms depending on the category of customer data. The recommendation unit can also dynamically select an optimal recommendation algorithm based on the product category. This improves the accuracy of recommendations by applying an optimal recommendation algorithm depending on the product category. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit can input product category data to a generation AI and cause the generation AI to select a recommendation algorithm.

[0083] When making a recommendation, the recommendation unit can improve the accuracy of the recommendation by referring to the sales representative's past recommendation results. The recommendation unit improves the accuracy of the recommendation based on, for example, the sales representative's past recommendation results. The recommendation unit can also refer to the sales representative's past recommendation results to make optimal recommendations for similar requests. The recommendation unit can also analyze the sales representative's past recommendation results and optimize the recommendation algorithm. In this way, the accuracy of the recommendation is improved by referring to the sales representative's past recommendation results. Some or all of the above-mentioned processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit can input the sales representative's past recommendation result data into the generation AI and cause the generation AI to improve the accuracy of the recommendations.

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

[0085] When making a recommendation, the recommendation unit can determine the priority of recommendations based on the submission time of the product. For example, the recommendation unit preferentially recommends products that were submitted earlier. The recommendation unit can also recommend products that were submitted later later. The recommendation unit can also dynamically adjust the priority of recommendations based on the submission time. This enables efficient recommendations by determining the priority of recommendations based on the submission time of the product. Some or all of the above-mentioned processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit can input product submission time data into the generation AI and have the generation AI determine the recommendation priority.

[0086] The recommendation unit can adjust the order of recommendations based on the relevance of products when making a recommendation. For example, the recommendation unit prioritizes recommending highly relevant products. The recommendation unit can also recommend less relevant products later. The recommendation unit can also dynamically adjust the order of recommendations based on the relevance of products. This enables efficient recommendations by adjusting the order of recommendations based on the relevance of products. Some or all of the above-described processing in the recommendation unit may be performed using AI, for example, or may be performed without using AI. For example, the recommendation unit can input product relevance data to a generation AI and cause the generation AI to adjust the order of recommendations.

[0087] The recommendation unit can adjust the use of technical terminology in the recommendation depending on the expertise level of the salesperson when making a recommendation. For example, if the expertise level of the salesperson is high, the recommendation unit can provide a recommendation that uses a lot of technical terminology. Furthermore, if the expertise level of the salesperson is low, the recommendation unit can also provide a recommendation that avoids technical terminology. The recommendation unit can also dynamically adjust the use of technical terminology in the recommendation depending on the expertise level of the salesperson. This allows for more appropriate recommendations by adjusting the use of technical terminology in the recommendation depending on the expertise level of the salesperson. Some or all of the above-described processing in the recommendation unit may be performed using AI, for example, or may be performed without using AI. For example, the recommendation unit can input expertise level data of the salesperson to a generation AI and have the generation AI execute the use of technical terminology.

[0088] The reference unit can estimate the salesperson's emotions and select success stories to reference based on the estimated emotions. For example, if the salesperson is stressed, the reference unit can provide simple, highly visible success stories. Furthermore, if the salesperson is relaxed, the reference unit can provide detailed success stories. Furthermore, if the salesperson is in a hurry, the reference unit can provide success stories that focus on the key points. By selecting success stories based on the salesperson's emotions, more appropriate success stories can be provided. The emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reference unit can be performed using, for example, AI, or without AI. For example, the reference unit can input facial expression data of the salesperson into the generation AI and have the generation AI perform emotion estimation.

[0089] During the reference process, the reference unit can refer to data on past success cases to select an appropriate case for the current request. For example, the reference unit selects the best case for the current request based on data on past success cases. The reference unit can also preferentially select successful cases for similar requests. The reference unit can also analyze data on past success cases and select the most relevant case. In this way, by referring to data on past success cases, the best case for the current request can be provided. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input data on past success cases into a generation AI and have the generation AI select the best case.

[0090] The reference unit can apply different reference algorithms depending on the category of the success story during reference. The reference unit selects an optimal reference algorithm depending on, for example, the category of the success story. The reference unit can also apply different reference algorithms depending on the category of customer data. The reference unit can also dynamically select an optimal reference algorithm based on the category of the success story. This improves the accuracy of reference by applying the optimal reference algorithm depending on the category of the success story. Some or all of the above-mentioned processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input category data of the success story to the generation AI and have the generation AI select the reference algorithm.

[0091] The reference unit can improve the accuracy of the reference by referring to the sales representative's past reference results during the reference. The reference unit improves the accuracy of the reference, for example, based on the sales representative's past reference results. The reference unit can also refer to the sales representative's past reference results to perform optimal reference for similar requests. The reference unit can also analyze the sales representative's past reference results and optimize the reference algorithm. In this way, the accuracy of the reference is improved by referring to the sales representative's past reference results. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input the sales representative's past reference result data into the generation AI and have the generation AI improve the accuracy of the reference.

[0092] The reference unit can estimate the salesperson's emotions and determine the priority of success stories to reference based on the estimated emotions. For example, if the salesperson is stressed, the reference unit can prioritize reference to success stories with high importance. Also, if the salesperson is relaxed, the reference unit can also reference success stories with normal priority. Also, if the salesperson is in a hurry, the reference unit can prioritize reference to urgent success stories. This allows important success stories to be provided preferentially by determining the priority of success stories according to the salesperson's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reference unit can be performed using AI, for example, or without AI. For example, the reference unit can input facial expression data of the salesperson into the generation AI and have the generation AI perform emotion estimation.

[0093] The reference unit can determine the reference priority based on the submission time of the success case during reference. For example, the reference unit prioritizes reference of a success case submitted earlier. The reference unit can also postpone reference of a success case submitted later. The reference unit can also dynamically adjust the reference priority based on the submission time. This enables efficient reference by determining the reference priority based on the submission time of the success case. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input data on the submission time of the success case into the generation AI and have the generation AI determine the reference priority.

[0094] The reference unit can adjust the order of reference based on the relevance of the success cases during reference. For example, the reference unit prioritizes reference to highly relevant success cases. The reference unit can also postpone reference to less relevant success cases. The reference unit can also dynamically adjust the order of reference based on the relevance of the success cases. This enables efficient reference by adjusting the order of reference based on the relevance of the success cases. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input relevance data of the success cases into the generation AI and have the generation AI adjust the order of reference.

[0095] The reference unit can adjust the use of technical terminology in the reference depending on the sales representative's level of expertise during the reference. For example, if the sales representative has a high level of expertise, the reference unit can provide success stories that use a lot of technical terminology. Furthermore, if the sales representative has a low level of expertise, the reference unit can provide success stories that avoid technical terminology. The reference unit can also dynamically adjust the use of technical terminology in the reference depending on the sales representative's level of expertise. This allows for more appropriate success stories to be provided by adjusting the use of technical terminology in the reference depending on the sales representative's level of expertise. Some or all of the above-described processing in the reference unit can be performed using, or without, AI, for example. For example, the reference unit can input the sales representative's level of expertise data into a generation AI and have the generation AI execute the use of technical terminology. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, recommendation unit, and reference unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives natural language input from a sales representative. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the request using AI. The recommendation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and recommends optimal products based on the analysis results. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and refers to success stories of other sales representatives. The reception unit can, for example, estimate the sales representative's emotions and adjust the timing of receiving the request based on the estimated emotions. === Hard Collateral 1-2 === Each of the multiple elements including the above-described reception unit, analysis unit, recommendation unit, and reference unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives natural language input from a sales representative. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the request using AI. The recommendation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and recommends optimal products based on the analysis results. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and refers to success stories of other sales representatives. The reception unit can, for example, estimate the sales representative's emotions and adjust the timing of receiving the request based on the estimated emotions. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, recommendation unit, and reference unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314 and receives natural language input from a sales representative. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the request using AI. The recommendation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and recommends optimal products based on the analysis results. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and refers to success stories of other sales representatives. The reception unit can, for example, estimate the sales representative's emotions and adjust the timing of receiving the request based on the estimated emotions. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, recommendation unit, and reference unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives natural language input from a sales representative. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the request using AI. The recommendation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and recommends the optimal product based on the analysis results. The reference unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and refers to success stories of other sales representatives. The reception unit can, for example, estimate the sales representative's emotions and adjust the timing of receiving the request based on the estimated emotions.

[0096] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0097] The reception unit can dynamically adjust the priority of requests based on the sales representative's past request history. For example, it can prioritize requests that have been frequently made in the past. It can also extract specific patterns from past request history and respond quickly if a similar pattern occurs again. Furthermore, by analyzing past request history, it can also concentrate resources on specific time periods or days of the week when many requests occur. This makes it possible to efficiently process requests by utilizing past request history.

[0098] The reception unit can estimate the emotions of the sales representative and automatically classify the content of the request based on the estimated emotions. For example, if the sales representative is feeling stressed, the request can be classified as urgent. If the sales representative is relaxed, the request can be classified as normal. Furthermore, if the sales representative is excited, the request can be classified as requiring special attention. This allows the content of the request to be appropriately classified according to the emotions of the sales representative, enabling a quick and appropriate response.

[0099] The analysis unit can predict the success rate of proposals based on the content of past proposals made by sales representatives. For example, it analyzes the content of proposals that have been successful in the past and calculates the probability that a similar proposal will be successful again. It can also predict the success rate of proposals for specific customers by combining the content of past proposals with customer data. Furthermore, it can extract areas for improvement in proposals based on the content of past proposals and reflect them in the next proposal. This makes it possible to improve the success rate of proposals by utilizing the content of past proposals.

[0100] The analysis unit can estimate the emotions of the sales representative and adjust the way in which the analysis results are presented based on the estimated emotions. For example, if the sales representative is feeling stressed, simple and highly visible analysis results can be provided. If the sales representative is relaxed, detailed analysis results can be provided. Furthermore, if the sales representative is in a hurry, analysis results that focus on the main points can be provided. This makes it possible to adjust the way in which the analysis results are presented according to the sales representative's emotions and provide more appropriate information.

[0101] The recommendation unit can improve the accuracy of recommendations based on the sales representative's past recommendation history. For example, it analyzes recommendations that were successful in the past and makes recommendations again under similar conditions. It can also predict the success rate of recommendations for specific customers by combining past recommendation history with customer data. Furthermore, it can extract areas for improvement in recommendations based on past recommendation history and reflect them in the next recommendation. This makes it possible to improve recommendation accuracy by utilizing past recommendation history.

[0102] The recommendation unit can estimate the emotions of the salesperson and adjust the timing of recommendations based on the estimated emotions. For example, if the salesperson is feeling stressed, the recommendation can be delayed until the salesperson is relaxed. Also, if the salesperson is in a hurry, the recommendation can be made immediately. Furthermore, if the salesperson is excited, the recommendation can be temporarily suspended until the salesperson has calmed down. In this way, the timing of recommendations can be adjusted according to the emotions of the salesperson, and recommendations can be made at more appropriate times.

[0103] The reference section can improve the accuracy of references based on the sales representative's past reference history. For example, it analyzes past successful references and references them again under similar conditions. It can also combine past reference history with customer data to predict the success rate of references for specific customers. Furthermore, it can extract areas for improvement in references based on past reference history and reflect them in the next reference. This makes it possible to improve reference accuracy by utilizing past reference history.

[0104] The reference unit can estimate the emotions of the sales representative and adjust the level of detail of the success stories to be referenced based on the estimated emotions. For example, if the sales representative is feeling stressed, simple, highly visible success stories can be provided. If the sales representative is relaxed, detailed success stories can be provided. Furthermore, if the sales representative is in a hurry, success stories that focus on the main points can be provided. This allows the level of detail of success stories to be adjusted according to the emotions of the sales representative, making it possible to provide more appropriate information.

[0105] The reference department can dynamically adjust the priority of references based on the sales representative's past reference results. For example, it can prioritize successful cases that have been frequently referenced in the past. It can also extract specific patterns from past reference results and respond quickly if a similar pattern occurs again. Furthermore, by analyzing past reference results, it can also concentrate resources on specific time periods or days of the week if many references occur during those times. This makes it possible to utilize past reference results to enable efficient references.

[0106] The reference unit can estimate the emotions of the sales representative and select success stories to reference based on the estimated emotions. For example, if the sales representative is feeling stressed, a simple, highly visible success story can be provided. If the sales representative is relaxed, a detailed success story can be provided. Furthermore, if the sales representative is in a hurry, a success story that focuses on the main points can be provided. In this way, by selecting success stories according to the emotions of the sales representative, more appropriate success stories can be provided.

[0107] The processing flow of the second embodiment will be briefly explained below.

[0108] Step 1: The reception unit receives a request from a sales representative. The request from a sales representative may include, but is not limited to, a question, a complaint, or a suggestion regarding a product. The reception unit receives, for example, a request input by the sales representative in natural language. The reception unit can also support various input methods, such as voice input and text input. For example, if the sales representative inputs a request by voice, the request can be received using voice recognition technology. Step 2: The analysis unit uses AI to analyze the request received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to this example. For example, the analysis unit uses data mining technology to analyze past proposals and recommend the most suitable product. The analysis unit can also analyze customer data and recommend products that meet the customer's needs. For example, the analysis unit recommends the most suitable product based on the customer's past purchase history and customer attribute data. Step 3: The recommendation unit provides the products recommended by the analysis unit. For example, the recommendation unit presents the products recommended by the analysis unit to the sales representative. The recommendation unit can also provide detailed information about the products and information about related products. For example, the recommendation unit explains the features and advantages of the recommended products. The recommendation unit also provides information about related products, allowing the sales representative to have more choices. Step 4: The reference unit retrieves success stories of other sales representatives from the database and provides them to the analysis unit. For example, the reference unit selects the case that best meets the current requirements based on data on past success stories. The reference unit can also apply different reference algorithms depending on the category of the success story. For example, the reference unit references success stories from different categories, such as cases of increased sales and cases of increased customer satisfaction.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0111] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0112] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0113] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0114] 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.

[0115] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0116] 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.

[0117] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0119] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0120] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0121] 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.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0123] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0124] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0127] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0129] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0130] 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.

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

[0132] The 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.

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

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

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

[0136] Fig. 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.

[0137] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0139] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

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

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0143] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0145] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0146] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0148] The 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.

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

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

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

[0152] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0153] 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.

[0154] 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.

[0155] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0156] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0157] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0158] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0159] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0160] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0161] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0162] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0164] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0165] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0166] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0169] 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.

[0170] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0171] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0172] 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.

[0173] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0174] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0175] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0177] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0178] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0179] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0180] [Explanation of symbols]

[0181] 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 reception unit that receives requests from sales representatives; an analysis unit that analyzes the request received by the reception unit and recommends appropriate products based on past proposal contents and customer data; a recommendation unit that provides the products recommended by the analysis unit; A reference section for referring to success stories of other sales representatives. A system characterized by:

2. The reception unit Estimate the sentiment of salespeople and adjust the timing of requests based on the estimated sentiment 2. The system of claim 1.

3. The reception unit Analyze sales representatives' past request history and select the appropriate reception method 2. The system of claim 1.

4. The reception unit Filter requests based on the sales rep's current projects and areas of interest when they are received 2. The system of claim 1.

5. The reception unit When accepting a request, select the appropriate acceptance method depending on the sales representative's input method 2. The system of claim 1.

6. The reception unit Estimate the sentiment of salespeople and prioritize incoming requests based on the estimated sentiment 2. The system of claim 1.

7. The reception unit When accepting requests, consider the geographic location of the salesperson to prioritize the most relevant requests.

2. The system of claim 1.

8. The reception unit Upon receiving a request, analyze the social media activity of the sales representative and receive relevant requests.

2. The system of claim 1.

Images