System

Abstract

To provide a system according to an embodiment that quickly analyzes a customer's reaction and takes appropriate measures.SOLUTION: A system according to an embodiment comprises a collection unit, a determination unit, and a notification unit. The collection unit collects reaction information indicating a customer's reaction to a promotion post. The determination unit determines at least one of the customer's needs and emotion on the basis of the reaction information collected by the collection unit. The notification unit performs notification to a person who has posted the promotion post when a result of the determination made by the determination unit satisfies a predetermined condition.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] With conventional technology, it is difficult to quickly and accurately grasp customer needs and feelings in marketing using SNS, which may result in delayed appropriate responses.

[0005] The system according to the embodiment aims to quickly analyze the customer's reaction and take appropriate action. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a determination unit, and a notification unit. The collection unit collects reaction information indicating customer reactions to a promotional post. The determination unit determines at least one of the customer's needs and emotions based on the reaction information collected by the collection unit. The notification unit notifies the poster of the promotional post when a result of the determination by the determination unit satisfies a predetermined condition. Effect of the Invention

[0007] The system according to the embodiment can quickly analyze the customer's reaction and take appropriate action. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A marketing support system according to an embodiment of the present invention is a system that quickly grasps customer needs and emotions and realizes effective promotion. This marketing support system collects reaction information indicating customer reactions to promotion posts, and judges customer needs and emotions (positive or negative) based on the collected reaction information. If the judgment result meets a predetermined condition, the poster of the promotion post is notified. For example, if the negative emotion value is high, the risk of a social media flame war can be detected early and a prompt response can be made. First, the marketing support system collects reaction information indicating customer reactions to the promotion post. At this time, the system collects the customer's comments and evaluations, and the number of impressions such as PV, likes, and retweets. This allows the customer's reactions to be understood in detail. Next, the marketing support system judges customer needs and emotions based on the collected reaction information. The AI ​​analyzes the customer's comments and judges positive or negative emotions. For example, if the customer's comments are positive, such as "This product is great!", they are judged as positive emotions. On the other hand, if the customer's comments are negative, such as "This product is not good at all," they are judged as negative emotions. Furthermore, if the judgment result satisfies a predetermined condition, the marketing support system notifies the poster of the promotional post. For example, if the negative emotion value exceeds a threshold, the risk of a social media flame war can be detected early and a prompt response can be made. This allows companies to quickly grasp customer reactions and take appropriate measures. This mechanism allows companies to quickly grasp customer needs and emotions and realize effective promotions. For example, a promotional post that receives many positive reactions can be further strengthened to increase its effectiveness. On the other hand, if there are many negative reactions, the promotion content can be reviewed and improvements can be proposed. This allows companies to carry out effective marketing that meets the needs of customers. This allows the marketing support system to quickly grasp customer needs and emotions and realize effective promotions.

[0029] The marketing support system according to the embodiment includes a collection unit, a determination unit, and a notification unit. The collection unit collects reaction information indicating a customer's reaction to a promotion post. The reaction information includes, for example, the customer's comment content, the content of the evaluation, and the number of impressions such as PV, likes, and retweets, but is not limited to such examples. The collection unit collects this information, for example, from an SNS platform through an API. The collection unit can also collect published comments and evaluations using web scraping technology. For example, the collection unit uses the API of the SNS platform to collect posts related to specific hashtags and keywords. The collection unit can also automatically collect published comments and evaluations using web scraping technology. Furthermore, the collection unit collects reaction information in real time, enabling rapid analysis. For example, the collection unit uses the streaming API of the SNS platform to collect comments and evaluations posted in real time. The determination unit determines at least one of the customer's needs and emotions based on the reaction information collected by the collection unit. The determination unit analyzes the customer's comment content and determines positive emotions and negative emotions, for example, using natural language processing technology. For example, the determination unit uses a text generation AI (e.g., LLM) to analyze the content of the customer's comments and calculate an emotion score. The determination unit can also use a machine learning model to determine the needs of the customer. For example, the determination unit uses a machine learning model that inputs the content of the customer's comments and outputs the customer's needs to determine the needs of the customer. The determination unit can also monitor changes in customer emotions in real time based on collected reaction information. For example, the determination unit analyzes comments and ratings collected in real time to immediately grasp changes in customer emotions. The notification unit notifies the poster of the promotional post when the determination result by the determination unit satisfies a predetermined condition. For example, when the negative emotion value exceeds a threshold, the notification unit detects the risk of a social media flame war early and notifies the poster to prompt a prompt response.For example, when the negative emotion value is high, the notification unit issues a warning to the poster of the promotional post via email or push notification. The notification unit can also send a notification suggesting strengthening the promotion when the positive emotion value is high. For example, when the positive emotion value is high, the notification unit sends a notification suggesting further strengthening of the promotion to the poster of the promotional post. In this way, the marketing support system according to the embodiment can quickly grasp the needs and emotions of customers and realize effective promotion.

[0030] The collection unit collects reaction information indicating customer reactions to the promotional post. The reaction information includes, for example, the contents of customer comments, the contents of evaluations, and the number of impressions such as PV, likes, and retweets, but is not limited to such examples. The collection unit collects this information, for example, from an SNS platform through an API. Specifically, the API of the SNS platform is used to collect posts related to specific hashtags and keywords. This makes it possible to collect customer reactions to the promotional post over a wide range. The collection unit can also collect published comments and evaluations using web scraping technology. By using web scraping technology, it is possible to collect reaction information from websites and blogs other than the SNS platform. For example, the collection unit can automatically collect customer evaluations and comments from the comment section of a specific website or a review site. Furthermore, the collection unit collects reaction information in real time, enabling rapid analysis. For example, the collection unit uses the streaming API of the SNS platform to collect comments and evaluations posted in real time. This makes it possible to immediately grasp customer reactions to the promotional post and respond quickly. The collection unit can centrally manage these data and link with other systems and departments as necessary. For example, the collected data is stored in a cloud server and made accessible to the judgment unit and notification unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the collection unit to collect data efficiently and effectively, improving the performance of the entire system.

[0031] The determination unit determines at least one of the customer's needs and emotions based on the reaction information collected by the collection unit. The determination unit, for example, uses natural language processing technology to analyze the content of the customer's comments and determine positive or negative emotions. Specifically, the determination unit uses a text generation AI (for example, LLM) to analyze the content of the customer's comments and calculate an emotion score. The text generation AI is trained with a large amount of text data in advance, receives the content of the customer's comments as input, and outputs an emotion score based on the content. For example, a high emotion score is assigned to a positive comment, and a low emotion score is assigned to a negative comment. The determination unit can also determine the customer's needs using a machine learning model. For example, the determination unit determines the customer's needs using a machine learning model that receives the content of the customer's comments as input and outputs the customer's needs. The machine learning model has learned the correspondence between the customer's comments and their needs in advance, and can determine the needs with high accuracy even for new comments. Furthermore, the determination unit can monitor changes in the customer's emotions in real time based on the collected reaction information. For example, the determination unit analyzes comments and evaluations collected in real time to immediately grasp changes in the customer's emotions. This allows the system to quickly grasp customer reactions to promotional posts and take appropriate measures. Based on these analysis results, the determination unit can evaluate the effectiveness of the promotion and provide important information for planning the next steps.

[0032] The notification unit notifies the poster of the promotional post when the determination result by the determination unit satisfies a predetermined condition. Specifically, when the negative emotion value exceeds a threshold, the notification unit detects the risk of a social networking site becoming a hot topic early and notifies the poster to promptly respond. For example, when the negative emotion value is high, the notification unit issues a warning to the poster of the promotional post through email or push notification. This allows the poster to take countermeasures quickly and minimizes the risk of a social networking site becoming a hot topic. The notification unit can also notify the poster of the promotional post by suggesting strengthening the promotion when the positive emotion value is high. For example, when the positive emotion value is high, the notification unit notifies the poster of the promotional post by suggesting further strengthening the promotion. This allows the poster to develop an effective promotion strategy and further attract the interest of customers. The notification unit can use multiple communication means to quickly and reliably notify the poster of the promotional post. For example, not only email and push notification but also SMS and voice calls can be used in combination to reliably deliver important information. Furthermore, the notification unit can collect customer feedback and continuously improve the accuracy and effectiveness of the notification content. For example, based on feedback from customers who have received the notification, the notification section can review the content and timing of the notification to provide more effective notifications. This allows the notification section to provide customers with action instructions quickly and reliably, maximizing the effectiveness of promotions.

[0033] The collection unit can collect information indicating the contents of the customer's comments and the contents of the evaluations on the promotional post as reaction information. The collection unit collects the contents of the customer's comments and the contents of the evaluations from, for example, an SNS platform through an API. For example, the collection unit collects comments and evaluations related to a specific hashtag or keyword. The collection unit can also automatically collect published comments and evaluations using web scraping technology. For example, the collection unit collects comments and evaluations related to a specific hashtag or keyword using an API of the SNS platform. The collection unit can also automatically collect published comments and evaluations using web scraping technology. Furthermore, the collection unit collects comments and evaluations in real time, enabling rapid analysis. For example, the collection unit collects comments and evaluations posted in real time using a streaming API of the SNS platform. This makes it possible to grasp the contents of the customer's comments and the contents of the evaluations in detail. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input comment and rating data obtained using the API of a social media platform into the generation AI and have the generation AI analyze the content of the comments and ratings.

[0034] The determination unit can determine at least one of the customer's needs and emotions based on the reaction information collected by the collection unit and the promotion category by the promotion post. For example, the determination unit uses natural language processing technology to analyze the content of the customer's comments and determine the customer's needs and emotions based on the promotion category. The determination unit can also use a machine learning model to determine the customer's needs and emotions based on the promotion category. For example, the determination unit uses a machine learning model that inputs the customer's comment content and the promotion category and outputs the customer's needs and emotions to determine the customer's needs and emotions. Furthermore, the determination unit can monitor changes in the customer's emotions in real time based on the collected reaction information and the promotion category. For example, the determination unit analyzes comments and evaluations collected in real time and immediately grasps changes in the customer's emotions based on the promotion category. This makes it possible to determine the customer's needs and emotions based on the promotion category. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input data for determining the customer's needs and emotions based on the promotion category to the generation AI, and the generation AI can perform analysis.

[0035] The determination unit can determine at least one of the needs and emotions of the customer based on the reaction information collected by the collection unit and the attributes of the customer who responded to the promotion post. For example, the determination unit uses natural language processing technology to analyze the content of the customer's comments and determine the customer's needs and emotions based on the customer's attributes. The determination unit can also use a machine learning model to determine the customer's needs and emotions based on the customer's attributes. For example, the determination unit uses a machine learning model that inputs the content of the customer's comments and the customer's attributes and outputs the customer's needs and emotions to determine the customer's needs and emotions. Furthermore, the determination unit can monitor changes in the customer's emotions in real time based on the collected reaction information and the customer's attributes. For example, the determination unit analyzes comments and evaluations collected in real time and immediately grasps changes in the customer's emotions based on the customer's attributes. This makes it possible to determine the needs and emotions based on the customer's attributes. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input data for determining the customer's needs and emotions based on the customer's attributes to the generation AI, and the generation AI can perform analysis.

[0036] The system may include an estimation unit that predicts the effect of the promotional post based on the determination result by the determination unit. For example, the estimation unit can predict the effect of the promotional post using a machine learning model. For example, the estimation unit predicts the effect using a machine learning model that takes the determination result by the determination unit as an input and outputs the effect of the promotional post. The estimation unit can also predict the effect based on data of past promotional posts. For example, the estimation unit predicts the effect using a machine learning model that has learned data of past promotional posts. Furthermore, the estimation unit can predict the effect of the promotional post in real time. For example, the estimation unit instantly predicts the effect of the promotional post based on reaction information collected in real time. This makes it possible to estimate the effect of the promotional post. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input data for predicting the effect of the promotional post to a generation AI, and the generation AI can perform analysis.

[0037] The system may include a suggestion unit that suggests improvements to the promotional post based on the determination result by the determination unit. For example, the suggestion unit may suggest improvements to the promotional post using a machine learning model. For example, the suggestion unit may suggest improvements using a machine learning model that takes the determination result by the determination unit as an input and outputs improvements to the promotional post. The suggestion unit may also suggest improvements based on data of past promotional posts. For example, the suggestion unit may suggest improvements using a machine learning model that has learned data of past promotional posts. Furthermore, the suggestion unit may also suggest improvements to the promotional post in real time. For example, the suggestion unit may instantly suggest improvements to the promotional post based on reaction information collected in real time. This allows the improvement of the promotional post to be suggested. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input data for suggesting improvements to the promotional post to a generation AI, and the generation AI may perform analysis.

[0038] The collection unit can analyze the customer's past reaction history at the time of collection and select an appropriate collection method. For example, the collection unit analyzes the customer's comment content and evaluation content based on the past reaction history and selects the optimal collection method. The collection unit can also analyze the past reaction history using a machine learning model and select the optimal collection method. For example, the collection unit selects the collection method using a machine learning model that inputs the past reaction history and outputs the optimal collection method. Furthermore, the collection unit can analyze the past reaction history in real time and dynamically adjust the collection method. For example, the collection unit analyzes the comments and evaluations collected in real time and immediately adjusts the collection method based on the past reaction history. This makes it possible to select the optimal collection method based on the customer's past reaction history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input data for analyzing the past reaction history to the generation AI and perform analysis by the generation AI.

[0039] The collection unit can perform filtering based on the customer's current field of interest and activity status at the time of collection. For example, the collection unit preferentially collects related comments and evaluations based on the customer's current field of interest. The collection unit can also filter related comments and evaluations based on the customer's activity status. For example, the collection unit performs filtering using a machine learning model that inputs the customer's current field of interest and outputs related comments and evaluations. Furthermore, the collection unit can grasp the customer's field of interest and activity status in real time and dynamically adjust filtering. For example, the collection unit analyzes comments and evaluations collected in real time and immediately adjusts filtering based on the customer's field of interest and activity status. This makes it possible to filter reaction information based on the customer's current field of interest and activity status. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data for analyzing the customer's field of interest and activity status to the generation AI, and the generation AI can perform analysis.

[0040] The collection unit can collect highly relevant reaction information preferentially based on the geographical location information of the customer at the time of collection. For example, the collection unit preferentially collects comments and evaluations related to a specific region based on the geographical location information of the customer. The collection unit can also collect reaction information reflecting a trend specific to the region based on the geographical location information of the customer. For example, the collection unit collects reaction information using a machine learning model that inputs the geographical location information of the customer and outputs highly relevant comments and evaluations. Furthermore, the collection unit can grasp the geographical location information of the customer in real time and dynamically adjust the collection of reaction information. For example, the collection unit analyzes the comments and evaluations collected in real time and immediately adjusts the collection of reaction information based on the geographical location information of the customer. This makes it possible to preferentially collect highly relevant reaction information based on the geographical location information of the customer. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input data for analyzing the geographical location information of the customer to the generation AI and perform analysis by the generation AI.

[0041] The collection unit can analyze the social media activity of the customer at the time of collection and collect related reaction information. For example, the collection unit collects comments and ratings related to a specific hashtag or keyword based on the social media activity of the customer. The collection unit can also collect related comments and ratings based on the accounts followed by the customer. For example, the collection unit collects reaction information using a machine learning model that inputs the social media activity of the customer and outputs related comments and ratings. Furthermore, the collection unit can grasp the social media activity of the customer in real time and dynamically adjust the collection of reaction information. For example, the collection unit analyzes the comments and ratings collected in real time and immediately adjusts the collection of reaction information based on the social media activity of the customer. This makes it possible to collect related reaction information based on the social media activity of the customer. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input data for analyzing the social media activity of the customer to the generation AI and perform analysis by the generation AI.

[0042] The judgment unit can adjust the level of detail of the judgment based on the importance of the reaction information at the time of judgment. For example, the judgment unit provides a detailed judgment result based on the importance of the reaction information. The judgment unit can also adjust the level of detail of the judgment based on the importance of the reaction information using a machine learning model. For example, the judgment unit adjusts the level of detail of the judgment using a machine learning model that inputs the importance of the reaction information and outputs a detailed judgment result. Furthermore, the judgment unit can grasp the importance of the reaction information in real time and dynamically adjust the level of detail of the judgment. For example, the judgment unit analyzes comments and evaluations collected in real time and immediately adjusts the level of detail of the judgment based on the importance of the reaction information. This makes it possible to adjust the level of detail of the judgment based on the importance of the reaction information. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input data for analyzing the importance of the reaction information to the generation AI and perform analysis by the generation AI.

[0043] The judgment unit can apply different judgment algorithms depending on the category of reaction information at the time of judgment. For example, the judgment unit applies a judgment algorithm that emphasizes a specific keyword to product reviews. The judgment unit can also apply a judgment algorithm that emphasizes customer satisfaction to service evaluations. For example, the judgment unit applies a judgment algorithm using a machine learning model that inputs the category of reaction information and selects an appropriate judgment algorithm. Furthermore, the judgment unit can grasp the category of reaction information in real time and dynamically adjust the judgment algorithm. For example, the judgment unit analyzes comments and evaluations collected in real time and immediately adjusts the judgment algorithm based on the category of reaction information. This makes it possible to apply different judgment algorithms depending on the category of reaction information. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input data for selecting an appropriate judgment algorithm depending on the category of reaction information to the generation AI, and the generation AI can perform analysis.

[0044] The judgment unit can determine the priority of judgment based on the time of submission of reaction information at the time of judgment. For example, the judgment unit gives priority to the latest reaction information. The judgment unit can also determine the priority of judgment based on the time of submission of reaction information using a machine learning model. For example, the judgment unit determines the priority of judgment using a machine learning model that inputs the time of submission of reaction information and outputs the priority. Furthermore, the judgment unit can grasp the time of submission of reaction information in real time and dynamically adjust the priority of judgment. For example, the judgment unit analyzes comments and evaluations collected in real time and immediately adjusts the priority of judgment based on the time of submission of reaction information. This makes it possible to determine the priority of judgment based on the time of submission of reaction information. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input data for analyzing the time of submission of reaction information to the generation AI, and the generation AI can perform analysis.

[0045] The judgment unit can adjust the order of judgment based on the relevance of the reaction information at the time of judgment. For example, the judgment unit gives priority to judgment on reaction information with high relevance. The judgment unit can also adjust the order of judgment based on the relevance of the reaction information using a machine learning model. For example, the judgment unit adjusts the order of judgment using a machine learning model that inputs the relevance of the reaction information and outputs the order. Furthermore, the judgment unit can grasp the relevance of the reaction information in real time and dynamically adjust the order of judgment. For example, the judgment unit analyzes comments and evaluations collected in real time and immediately adjusts the order of judgment based on the relevance of the reaction information. This makes it possible to adjust the order of judgment based on the relevance of the reaction information. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input data for analyzing the relevance of the reaction information to the generation AI and perform analysis by the generation AI.

[0046] The notification unit can select the optimal notification method by analyzing the past reaction history of the customer at the time of notification. For example, the notification unit selects the notification method that the customer preferred based on the past reaction history. The notification unit can also analyze the past reaction history using a machine learning model and select the optimal notification method. For example, the notification unit selects the notification method using a machine learning model that inputs the past reaction history and outputs the optimal notification method. Furthermore, the notification unit can analyze the past reaction history in real time and dynamically adjust the notification method. For example, the notification unit analyzes comments and evaluations collected in real time and immediately adjusts the notification method based on the past reaction history. This makes it possible to select the optimal notification method based on the past reaction history of the customer. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input data for analyzing the past reaction history to the generation AI and perform analysis by the generation AI.

[0047] The notification unit can customize the notification means based on the customer's current activity status at the time of notification. For example, when the customer is in a meeting, the notification unit selects a quiet notification method (e.g., vibration). In addition, when the customer is on the move, the notification unit can also preferentially select voice notification. For example, the notification unit customizes the notification means using a machine learning model that inputs the customer's current activity status and outputs the optimal notification means. Furthermore, the notification unit can grasp the customer's activity status in real time and dynamically adjust the notification means. For example, the notification unit analyzes comments and ratings collected in real time and instantly adjusts the notification means based on the customer's activity status. This makes it possible to customize the optimal notification means based on the customer's current activity status. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input data for analyzing the customer's activity status to the generation AI, and the generation AI can perform the analysis.

[0048] The notification unit can select the optimal notification method by considering the geographical location information of the customer at the time of notification. For example, the notification unit selects a notification method related to a specific region based on the geographical location information of the customer. The notification unit can also select a notification method that reflects a trend specific to the region based on the geographical location information of the customer. For example, the notification unit selects a notification method using a machine learning model that inputs the geographical location information of the customer and outputs the optimal notification method. Furthermore, the notification unit can grasp the geographical location information of the customer in real time and dynamically adjust the notification method. For example, the notification unit analyzes comments and ratings collected in real time and immediately adjusts the notification method based on the geographical location information of the customer. This makes it possible to select the optimal notification method based on the geographical location information of the customer. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input data for analyzing the geographical location information of the customer to the generation AI and perform analysis by the generation AI.

[0049] The notification unit can analyze the social media activity of the customer at the time of notification and suggest a notification means. For example, the notification unit can suggest a notification means related to a specific hashtag or keyword based on the social media activity of the customer. The notification unit can also suggest a related notification means based on the accounts followed by the customer. For example, the notification unit can suggest a notification means using a machine learning model that inputs the social media activity of the customer and outputs an optimal notification means. Furthermore, the notification unit can grasp the social media activity of the customer in real time and dynamically adjust the notification means. For example, the notification unit can analyze comments and ratings collected in real time and instantly adjust the notification means based on the social media activity of the customer. This makes it possible to suggest an optimal notification means based on the social media activity of the customer. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can input data for analyzing the social media activity of the customer to the generation AI and perform analysis by the generation AI.

[0050] The estimation unit can optimize the estimation algorithm by referring to past promotion effect data at the time of estimation. For example, the estimation unit selects the most effective estimation algorithm based on the past promotion effect data. The estimation unit can also analyze the past promotion effect data using a machine learning model and optimize the estimation algorithm. For example, the estimation unit optimizes the estimation algorithm using a machine learning model that inputs past promotion effect data and outputs an optimal estimation algorithm. Furthermore, the estimation unit can dynamically adjust the estimation algorithm by referring to past promotion effect data in real time. For example, the estimation unit analyzes comments and evaluations collected in real time and instantly adjusts the estimation algorithm based on the past promotion effect data. This allows the estimation algorithm to be optimized based on the past promotion effect data. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input data for analyzing the past promotion effect data to the generation AI and perform analysis by the generation AI.

[0051] The estimation unit can apply different estimation methods for each promotion category at the time of estimation. For example, the estimation unit applies an estimation method that emphasizes sales data to product promotions. The estimation unit can also apply an estimation method that emphasizes customer satisfaction data to service promotions. For example, the estimation unit applies the estimation method using a machine learning model that inputs the promotion category and selects an appropriate estimation method. Furthermore, the estimation unit can grasp the promotion category in real time and dynamically adjust the estimation method. For example, the estimation unit analyzes comments and evaluations collected in real time and immediately adjusts the estimation method based on the promotion category. This makes it possible to apply an optimal estimation method according to the promotion category. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input data for selecting an appropriate estimation method according to the promotion category to the generation AI, and the generation AI can perform analysis.

[0052] The estimation unit can weight the estimation based on the implementation time of the promotion at the time of estimation. For example, if the implementation time of the promotion is a busy season, the estimation unit can weight the estimation highly. Also, if the implementation time of the promotion is a slow season, the estimation unit can weight the estimation lightly. For example, the estimation unit weights the estimation using a machine learning model that inputs the implementation time of the promotion and outputs a weighting. Furthermore, the estimation unit can grasp the implementation time of the promotion in real time and dynamically adjust the weighting of the estimation. For example, the estimation unit analyzes comments and evaluations collected in real time and immediately adjusts the weighting of the estimation based on the implementation time of the promotion. This makes it possible to weight the estimation based on the implementation time of the promotion. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input data for analyzing the implementation time of the promotion to the generation AI and perform analysis by the generation AI.

[0053] The estimation unit can improve the accuracy of the estimation by referring to the related market data of the promotion at the time of estimation. For example, the estimation unit improves the estimation accuracy of the promotion effect based on the related market data. The estimation unit can also analyze the related market data using a machine learning model and optimize the estimation algorithm. For example, the estimation unit optimizes the estimation algorithm using a machine learning model that uses the related market data as an input and improves the estimation accuracy. Furthermore, the estimation unit can also dynamically adjust the estimation algorithm by referring to the related market data in real time. For example, the estimation unit analyzes comments and evaluations collected in real time and immediately adjusts the estimation algorithm based on the related market data. This makes it possible to improve the accuracy of the estimation based on the related market data of the promotion. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input data for analyzing the related market data to the generation AI and perform analysis by the generation AI.

[0054] The suggestion unit can optimize the proposed algorithm by referring to past promotion improvement data at the time of proposal. For example, the suggestion unit selects the most effective proposed algorithm based on the past promotion improvement data. The suggestion unit can also analyze the past promotion improvement data using a machine learning model and optimize the proposed algorithm. For example, the suggestion unit optimizes the proposed algorithm using a machine learning model that inputs past promotion improvement data and outputs an optimal proposed algorithm. Furthermore, the suggestion unit can dynamically adjust the proposed algorithm by referring to the past promotion improvement data in real time. For example, the suggestion unit analyzes comments and evaluations collected in real time and instantly adjusts the proposed algorithm based on the past promotion improvement data. This allows the proposed algorithm to be optimized based on the past promotion improvement data. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input data for analyzing the past promotion improvement data to the generation AI and perform analysis by the generation AI.

[0055] The suggestion unit can apply different proposal methods for each promotion category at the time of proposal. For example, the suggestion unit applies a proposal method that emphasizes sales data to product promotion. The suggestion unit can also apply a proposal method that emphasizes customer satisfaction data to service promotion. For example, the suggestion unit applies the proposal method using a machine learning model that inputs the promotion category and selects an appropriate proposal method. Furthermore, the suggestion unit can grasp the promotion category in real time and dynamically adjust the proposal method. For example, the suggestion unit analyzes comments and evaluations collected in real time and immediately adjusts the proposal method based on the promotion category. This makes it possible to apply the optimal proposal method according to the promotion category. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input data for selecting an appropriate proposal method according to the promotion category to the generation AI, and the generation AI can perform analysis.

[0056] The suggestion unit can weight the proposal based on the implementation time of the promotion at the time of proposal. For example, if the implementation time of the promotion is a busy season, the suggestion unit can weight the proposal highly. Also, if the implementation time of the promotion is a slow season, the suggestion unit can weight the proposal low. For example, the suggestion unit weights the proposal using a machine learning model that inputs the implementation time of the promotion and outputs a weighting. Furthermore, the suggestion unit can grasp the implementation time of the promotion in real time and dynamically adjust the weighting of the proposal. For example, the suggestion unit analyzes comments and evaluations collected in real time and immediately adjusts the weighting of the proposal based on the implementation time of the promotion. In this way, the proposal can be weighted based on the implementation time of the promotion. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input data for analyzing the implementation time of the promotion to the generation AI, and the generation AI can perform the analysis.

[0057] The proposal unit can improve the accuracy of the proposal by referring to the relevant market data of the promotion at the time of proposal. For example, the proposal unit improves the proposal accuracy of the promotion improvement based on the relevant market data. The proposal unit can also analyze the relevant market data using a machine learning model and optimize the proposal algorithm. For example, the proposal unit optimizes the proposal algorithm using a machine learning model that uses the relevant market data as an input and improves the proposal accuracy. Furthermore, the proposal unit can dynamically adjust the proposal algorithm by referring to the relevant market data in real time. For example, the proposal unit analyzes comments and evaluations collected in real time and instantly adjusts the proposal algorithm based on the relevant market data. This makes it possible to improve the accuracy of the proposal based on the relevant market data of the promotion. A part or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI or may be performed without using AI. For example, the proposal unit can input data for analyzing the relevant market data to the generation AI and perform analysis by the generation AI.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The marketing support system may further include a purchase history analysis unit that analyzes the purchase history of the customer. The purchase history analysis unit collects and analyzes the customer's past purchase history to grasp the customer's purchasing trends and preferences. For example, the purchase history analysis unit may analyze the types and frequency of products that the customer has purchased in the past, and identify what products the customer is interested in. The purchase history analysis unit may also predict the product that the customer is likely to purchase next, based on the customer's purchase history. Furthermore, the purchase history analysis unit may combine the customer's purchase history with reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotions based on the customer's purchase history.

[0060] The marketing support system may further include a behavior history analysis unit that analyzes the behavior history of the customer. The behavior history analysis unit collects and analyzes behavior data such as the customer's website browsing history and app usage history. For example, the behavior history analysis unit analyzes which pages the customer viewed and which functions the customer used, and identifies the customer's interests and concerns. The behavior history analysis unit may also predict what action the customer is likely to take next based on the customer's behavior data. Furthermore, the behavior history analysis unit may combine the customer's behavior data with the reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotion based on the customer's behavior history.

[0061] The marketing support system may further include a social media analysis unit that analyzes the social media activities of the customer. The social media analysis unit collects and analyzes activity data of the customer on social media. For example, the social media analysis unit may analyze what kind of posts the customer has made and what accounts the customer follows, and identify the customer's interests and concerns. The social media analysis unit may also predict what kind of post the customer is likely to make next, based on the customer's social media activities. Furthermore, the social media analysis unit may combine the customer's social media activities with reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotions based on the customer's social media activities.

[0062] The marketing support system may further include a location information analysis unit that analyzes the geographical location information of the customer. The location information analysis unit collects and analyzes the customer's current location and past movement history. For example, the location information analysis unit may analyze which area the customer lives in and which area the customer frequently visits, and identify the customer's living area and range of movement. The location information analysis unit may also predict which area the customer is likely to visit next, based on the customer's location information. Furthermore, the location information analysis unit may combine the customer's location information and reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotions based on the customer's geographical location information.

[0063] The marketing support system can further include a purchasing willingness prediction unit that predicts a customer's purchasing willingness. The purchasing willingness prediction unit predicts a customer's purchasing willingness based on the customer's reaction information and behavioral data. For example, the purchasing willingness prediction unit analyzes the content of the customer's comments and ratings to determine the level of purchasing willingness of the customer. The purchasing willingness prediction unit can also predict the product that the customer is likely to purchase next based on the customer's behavioral data. Furthermore, the purchasing willingness prediction unit can combine the customer's purchasing willingness and reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotions based on the customer's purchasing willingness.

[0064] The process flow of the first embodiment will be briefly described below.

[0065] Step 1: The collection unit collects reaction information indicating customer reactions to the promotional post. The reaction information includes, for example, the contents of customer comments, the contents of ratings, and the number of impressions such as page views, likes, and retweets. The collection unit collects this information from the SNS platform through an API. It can also use web scraping technology to collect publicly available comments and ratings. Furthermore, the collection unit collects reaction information in real time, enabling rapid analysis. Step 2: The determination unit determines at least one of the customer's needs and emotions based on the reaction information collected by the collection unit. The determination unit uses natural language processing technology and machine learning models to analyze the content of the customer's comments and determine positive or negative emotions. It can also determine the customer's needs. Furthermore, the determination unit can monitor changes in the customer's emotions in real time based on the collected reaction information. Step 3: The notification unit notifies the poster of the promotional post when the result of the determination by the determination unit satisfies a predetermined condition. For example, when the negative emotion value exceeds a threshold, the notification unit can detect the risk of a social media outrage early on and send a notification encouraging a quick response. In addition, when the positive emotion value is high, the notification unit can also send a notification suggesting strengthening the promotion.

[0066] (Example 2) A marketing support system according to an embodiment of the present invention is a system that quickly grasps customer needs and emotions and realizes effective promotion. This marketing support system collects reaction information indicating customer reactions to promotion posts, and judges customer needs and emotions (positive or negative) based on the collected reaction information. If the judgment result meets a predetermined condition, the poster of the promotion post is notified. For example, if the negative emotion value is high, the risk of a social media flame war can be detected early and a prompt response can be made. First, the marketing support system collects reaction information indicating customer reactions to the promotion post. At this time, the system collects the customer's comments and evaluations, and the number of impressions such as PV, likes, and retweets. This allows the customer's reactions to be understood in detail. Next, the marketing support system judges customer needs and emotions based on the collected reaction information. The AI ​​analyzes the customer's comments and judges positive or negative emotions. For example, if the customer's comments are positive, such as "This product is great!", they are judged as positive emotions. On the other hand, if the customer's comments are negative, such as "This product is not good at all," they are judged as negative emotions. Furthermore, if the judgment result satisfies a predetermined condition, the marketing support system notifies the poster of the promotional post. For example, if the negative emotion value exceeds a threshold, the risk of a social media flame war can be detected early and a prompt response can be made. This allows companies to quickly grasp customer reactions and take appropriate measures. This mechanism allows companies to quickly grasp customer needs and emotions and realize effective promotions. For example, a promotional post that receives many positive reactions can be further strengthened to increase its effectiveness. On the other hand, if there are many negative reactions, the promotion content can be reviewed and improvements can be proposed. This allows companies to carry out effective marketing that meets the needs of customers. This allows the marketing support system to quickly grasp customer needs and emotions and realize effective promotions.

[0067] The marketing support system according to the embodiment includes a collection unit, a determination unit, and a notification unit. The collection unit collects reaction information indicating a customer's reaction to a promotion post. The reaction information includes, for example, the customer's comment content, the content of the evaluation, and the number of impressions such as PV, likes, and retweets, but is not limited to such examples. The collection unit collects this information, for example, from an SNS platform through an API. The collection unit can also collect published comments and evaluations using web scraping technology. For example, the collection unit uses the API of the SNS platform to collect posts related to specific hashtags and keywords. The collection unit can also automatically collect published comments and evaluations using web scraping technology. Furthermore, the collection unit collects reaction information in real time, enabling rapid analysis. For example, the collection unit uses the streaming API of the SNS platform to collect comments and evaluations posted in real time. The determination unit determines at least one of the customer's needs and emotions based on the reaction information collected by the collection unit. The determination unit analyzes the customer's comment content and determines positive emotions and negative emotions, for example, using natural language processing technology. For example, the determination unit uses a text generation AI (e.g., LLM) to analyze the content of the customer's comments and calculate an emotion score. The determination unit can also use a machine learning model to determine the needs of the customer. For example, the determination unit uses a machine learning model that inputs the content of the customer's comments and outputs the customer's needs to determine the needs of the customer. The determination unit can also monitor changes in customer emotions in real time based on collected reaction information. For example, the determination unit analyzes comments and ratings collected in real time to immediately grasp changes in customer emotions. The notification unit notifies the poster of the promotional post when the determination result by the determination unit satisfies a predetermined condition. For example, when the negative emotion value exceeds a threshold, the notification unit detects the risk of a social media flame war early and notifies the poster to prompt a prompt response.For example, when the negative emotion value is high, the notification unit issues a warning to the poster of the promotional post via email or push notification. The notification unit can also send a notification suggesting strengthening the promotion when the positive emotion value is high. For example, when the positive emotion value is high, the notification unit sends a notification suggesting further strengthening of the promotion to the poster of the promotional post. In this way, the marketing support system according to the embodiment can quickly grasp the needs and emotions of customers and realize effective promotion.

[0068] The collection unit collects reaction information indicating customer reactions to the promotional post. The reaction information includes, for example, the contents of customer comments, the contents of evaluations, and the number of impressions such as PV, likes, and retweets, but is not limited to such examples. The collection unit collects this information, for example, from an SNS platform through an API. Specifically, the API of the SNS platform is used to collect posts related to specific hashtags and keywords. This makes it possible to collect customer reactions to the promotional post over a wide range. The collection unit can also collect published comments and evaluations using web scraping technology. By using web scraping technology, it is possible to collect reaction information from websites and blogs other than the SNS platform. For example, the collection unit can automatically collect customer evaluations and comments from the comment section of a specific website or a review site. Furthermore, the collection unit collects reaction information in real time, enabling rapid analysis. For example, the collection unit uses the streaming API of the SNS platform to collect comments and evaluations posted in real time. This makes it possible to immediately grasp customer reactions to the promotional post and respond quickly. The collection unit can centrally manage these data and link with other systems and departments as necessary. For example, the collected data is stored in a cloud server and made accessible to the judgment unit and notification unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the collection unit to collect data efficiently and effectively, improving the performance of the entire system.

[0069] The determination unit determines at least one of the customer's needs and emotions based on the reaction information collected by the collection unit. The determination unit, for example, uses natural language processing technology to analyze the content of the customer's comments and determine positive or negative emotions. Specifically, the determination unit uses a text generation AI (for example, LLM) to analyze the content of the customer's comments and calculate an emotion score. The text generation AI is trained with a large amount of text data in advance, receives the content of the customer's comments as input, and outputs an emotion score based on the content. For example, a high emotion score is assigned to a positive comment, and a low emotion score is assigned to a negative comment. The determination unit can also determine the customer's needs using a machine learning model. For example, the determination unit determines the customer's needs using a machine learning model that receives the content of the customer's comments as input and outputs the customer's needs. The machine learning model has learned the correspondence between the customer's comments and their needs in advance, and can determine the needs with high accuracy even for new comments. Furthermore, the determination unit can monitor changes in the customer's emotions in real time based on the collected reaction information. For example, the determination unit analyzes comments and evaluations collected in real time to immediately grasp changes in the customer's emotions. This allows the system to quickly grasp customer reactions to promotional posts and take appropriate measures. Based on these analysis results, the determination unit can evaluate the effectiveness of the promotion and provide important information for planning the next steps.

[0070] The notification unit notifies the poster of the promotional post when the determination result by the determination unit satisfies a predetermined condition. Specifically, when the negative emotion value exceeds a threshold, the notification unit detects the risk of a social networking site becoming a hot topic early and notifies the poster to promptly respond. For example, when the negative emotion value is high, the notification unit issues a warning to the poster of the promotional post through email or push notification. This allows the poster to take countermeasures quickly and minimizes the risk of a social networking site becoming a hot topic. The notification unit can also notify the poster of the promotional post by suggesting strengthening the promotion when the positive emotion value is high. For example, when the positive emotion value is high, the notification unit notifies the poster of the promotional post by suggesting further strengthening the promotion. This allows the poster to develop an effective promotion strategy and further attract the interest of customers. The notification unit can use multiple communication means to quickly and reliably notify the poster of the promotional post. For example, not only email and push notification but also SMS and voice calls can be used in combination to reliably deliver important information. Furthermore, the notification unit can collect customer feedback and continuously improve the accuracy and effectiveness of the notification content. For example, based on feedback from customers who have received the notification, the notification section can review the content and timing of the notification to provide more effective notifications. This allows the notification section to provide customers with action instructions quickly and reliably, maximizing the effectiveness of promotions.

[0071] The determination unit determines the negative emotion value of the customer, and the notification unit can issue a notification when the negative emotion value exceeds a threshold. The determination unit, for example, uses natural language processing technology to analyze the content of the customer's comment and determine the negative emotion value. For example, the determination unit uses a text generation AI (for example, LLM) to analyze the content of the customer's comment and calculate a negative emotion score. The determination unit can also use a machine learning model to determine the negative emotion value of the customer. For example, the determination unit inputs the content of the customer's comment and uses a machine learning model that outputs a negative emotion value to determine the negative emotion value. Furthermore, the determination unit can monitor changes in the customer's negative emotion in real time based on the collected reaction information. For example, the determination unit analyzes comments and evaluations collected in real time to immediately grasp changes in the customer's negative emotion. When the negative emotion value exceeds a threshold, the notification unit detects the risk of a social media flame war early and issues a notification to encourage a prompt response. For example, when the negative emotion value is high, the notification unit issues a warning to the poster of the promotional post via email or push notification. In addition, the notification unit can also provide a notification proposing specific countermeasures when the negative emotion value is high. For example, the notification unit provides a notification proposing a quick countermeasure to the poster of the promotional post when the negative emotion value is high. This allows for a quick response when the negative emotion value is high. The emotion estimation is realized 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.

[0072] The collection unit can collect information indicating the contents of the customer's comments and the contents of the evaluations on the promotional post as reaction information. The collection unit collects the contents of the customer's comments and the contents of the evaluations from, for example, an SNS platform through an API. For example, the collection unit collects comments and evaluations related to a specific hashtag or keyword. The collection unit can also automatically collect published comments and evaluations using web scraping technology. For example, the collection unit collects comments and evaluations related to a specific hashtag or keyword using an API of the SNS platform. The collection unit can also automatically collect published comments and evaluations using web scraping technology. Furthermore, the collection unit collects comments and evaluations in real time, enabling rapid analysis. For example, the collection unit collects comments and evaluations posted in real time using a streaming API of the SNS platform. This makes it possible to grasp the contents of the customer's comments and the contents of the evaluations in detail. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input comment and rating data obtained using the API of a social media platform into the generation AI and have the generation AI analyze the content of the comments and ratings.

[0073] The determination unit can determine at least one of the customer's needs and emotions based on the reaction information collected by the collection unit and the promotion category by the promotion post. For example, the determination unit uses natural language processing technology to analyze the content of the customer's comments and determine the customer's needs and emotions based on the promotion category. The determination unit can also use a machine learning model to determine the customer's needs and emotions based on the promotion category. For example, the determination unit uses a machine learning model that inputs the customer's comment content and the promotion category and outputs the customer's needs and emotions to determine the customer's needs and emotions. Furthermore, the determination unit can monitor changes in the customer's emotions in real time based on the collected reaction information and the promotion category. For example, the determination unit analyzes comments and evaluations collected in real time and immediately grasps changes in the customer's emotions based on the promotion category. This makes it possible to determine the customer's needs and emotions based on the promotion category. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input data for determining the customer's needs and emotions based on the promotion category to the generation AI, and the generation AI can perform analysis.

[0074] The determination unit can determine at least one of the needs and emotions of the customer based on the reaction information collected by the collection unit and the attributes of the customer who responded to the promotion post. For example, the determination unit uses natural language processing technology to analyze the content of the customer's comments and determine the customer's needs and emotions based on the customer's attributes. The determination unit can also use a machine learning model to determine the customer's needs and emotions based on the customer's attributes. For example, the determination unit uses a machine learning model that inputs the content of the customer's comments and the customer's attributes and outputs the customer's needs and emotions to determine the customer's needs and emotions. Furthermore, the determination unit can monitor changes in the customer's emotions in real time based on the collected reaction information and the customer's attributes. For example, the determination unit analyzes comments and evaluations collected in real time and immediately grasps changes in the customer's emotions based on the customer's attributes. This makes it possible to determine the needs and emotions based on the customer's attributes. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input data for determining the customer's needs and emotions based on the customer's attributes to the generation AI, and the generation AI can perform analysis.

[0075] The system may include an estimation unit that predicts the effect of the promotional post based on the determination result by the determination unit. For example, the estimation unit can predict the effect of the promotional post using a machine learning model. For example, the estimation unit predicts the effect using a machine learning model that takes the determination result by the determination unit as an input and outputs the effect of the promotional post. The estimation unit can also predict the effect based on data of past promotional posts. For example, the estimation unit predicts the effect using a machine learning model that has learned data of past promotional posts. Furthermore, the estimation unit can predict the effect of the promotional post in real time. For example, the estimation unit instantly predicts the effect of the promotional post based on reaction information collected in real time. This makes it possible to estimate the effect of the promotional post. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input data for predicting the effect of the promotional post to a generation AI, and the generation AI can perform analysis.

[0076] The system may include a suggestion unit that suggests improvements to the promotional post based on the determination result by the determination unit. For example, the suggestion unit may suggest improvements to the promotional post using a machine learning model. For example, the suggestion unit may suggest improvements using a machine learning model that takes the determination result by the determination unit as an input and outputs improvements to the promotional post. The suggestion unit may also suggest improvements based on data of past promotional posts. For example, the suggestion unit may suggest improvements using a machine learning model that has learned data of past promotional posts. Furthermore, the suggestion unit may also suggest improvements to the promotional post in real time. For example, the suggestion unit may instantly suggest improvements to the promotional post based on reaction information collected in real time. This allows the improvement of the promotional post to be suggested. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input data for suggesting improvements to the promotional post to a generation AI, and the generation AI may perform analysis.

[0077] The collection unit can predict the customer's emotions and adjust the timing of collecting the reaction information based on the predicted customer's emotions. For example, the collection unit can analyze the content of the customer's comments using a text generation AI (for example, LLM) and calculate an emotion score. The collection unit can also estimate the customer's emotions using a machine learning model. For example, the collection unit estimates emotions using a machine learning model that inputs the content of the customer's comments and outputs an emotion score. Furthermore, the collection unit can estimate the customer's emotions in real time and adjust the collection timing. For example, the collection unit analyzes comments and evaluations collected in real time, immediately grasps changes in the customer's emotions, and adjusts the collection timing. This makes it possible to adjust the collection timing of the reaction information according to the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection department can input data for estimating customer emotions into the generation AI, which can then perform analysis.

[0078] The collection unit can analyze the customer's past reaction history at the time of collection and select an appropriate collection method. For example, the collection unit analyzes the customer's comment content and evaluation content based on the past reaction history and selects the optimal collection method. The collection unit can also analyze the past reaction history using a machine learning model and select the optimal collection method. For example, the collection unit selects the collection method using a machine learning model that inputs the past reaction history and outputs the optimal collection method. Furthermore, the collection unit can analyze the past reaction history in real time and dynamically adjust the collection method. For example, the collection unit analyzes the comments and evaluations collected in real time and immediately adjusts the collection method based on the past reaction history. This makes it possible to select the optimal collection method based on the customer's past reaction history. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input data for analyzing the past reaction history to the generation AI and perform analysis by the generation AI.

[0079] The collection unit can perform filtering based on the customer's current field of interest and activity status at the time of collection. For example, the collection unit preferentially collects related comments and evaluations based on the customer's current field of interest. The collection unit can also filter related comments and evaluations based on the customer's activity status. For example, the collection unit performs filtering using a machine learning model that inputs the customer's current field of interest and outputs related comments and evaluations. Furthermore, the collection unit can grasp the customer's field of interest and activity status in real time and dynamically adjust filtering. For example, the collection unit analyzes comments and evaluations collected in real time and immediately adjusts filtering based on the customer's field of interest and activity status. This makes it possible to filter reaction information based on the customer's current field of interest and activity status. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data for analyzing the customer's field of interest and activity status to the generation AI, and the generation AI can perform analysis.

[0080] The collection unit can predict the customer's emotions and determine the priority of the reaction information to be collected based on the predicted customer's emotions. For example, the collection unit can analyze the content of the customer's comments using a text generation AI (for example, LLM) and calculate an emotion score. The collection unit can also estimate the customer's emotions using a machine learning model. For example, the collection unit estimates emotions using a machine learning model that inputs the content of the customer's comments and outputs an emotion score. Furthermore, the collection unit can estimate the customer's emotions in real time and determine the priority of the reaction information to be collected. For example, the collection unit analyzes comments and evaluations collected in real time, immediately grasps changes in the customer's emotions, and determines the priority of the reaction information to be collected. This makes it possible to determine the priority of the reaction information based on the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection department can input data for estimating customer emotions into the generation AI, which can then perform analysis.

[0081] The collection unit can collect highly relevant reaction information preferentially based on the geographical location information of the customer at the time of collection. For example, the collection unit preferentially collects comments and evaluations related to a specific region based on the geographical location information of the customer. The collection unit can also collect reaction information reflecting a trend specific to the region based on the geographical location information of the customer. For example, the collection unit collects reaction information using a machine learning model that inputs the geographical location information of the customer and outputs highly relevant comments and evaluations. Furthermore, the collection unit can grasp the geographical location information of the customer in real time and dynamically adjust the collection of reaction information. For example, the collection unit analyzes the comments and evaluations collected in real time and immediately adjusts the collection of reaction information based on the geographical location information of the customer. This makes it possible to preferentially collect highly relevant reaction information based on the geographical location information of the customer. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input data for analyzing the geographical location information of the customer to the generation AI and perform analysis by the generation AI.

[0082] The collection unit can analyze the social media activity of the customer at the time of collection and collect related reaction information. For example, the collection unit collects comments and ratings related to a specific hashtag or keyword based on the social media activity of the customer. The collection unit can also collect related comments and ratings based on the accounts followed by the customer. For example, the collection unit collects reaction information using a machine learning model that inputs the social media activity of the customer and outputs related comments and ratings. Furthermore, the collection unit can grasp the social media activity of the customer in real time and dynamically adjust the collection of reaction information. For example, the collection unit analyzes the comments and ratings collected in real time and immediately adjusts the collection of reaction information based on the social media activity of the customer. This makes it possible to collect related reaction information based on the social media activity of the customer. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input data for analyzing the social media activity of the customer to the generation AI and perform analysis by the generation AI.

[0083] The judgment unit can predict the customer's emotion and adjust the expression method of the judgment based on the predicted customer's emotion. For example, the judgment unit uses a text generation AI (for example, LLM) to analyze the content of the customer's comment and calculate an emotion score. The judgment unit can also estimate the customer's emotion using a machine learning model. For example, the judgment unit uses a machine learning model that inputs the content of the customer's comment and outputs an emotion score to estimate the emotion. The judgment unit can also estimate the customer's emotion in real time and adjust the expression method of the judgment. For example, the judgment unit analyzes comments and evaluations collected in real time, immediately grasps changes in the customer's emotion, and adjusts the expression method of the judgment. This makes it possible to adjust the expression method of the judgment based on the customer's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the judgment unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the judgment unit can input data for estimating a customer's emotions into the generation AI, which can then perform analysis.

[0084] The judgment unit can adjust the level of detail of the judgment based on the importance of the reaction information at the time of judgment. For example, the judgment unit provides a detailed judgment result based on the importance of the reaction information. The judgment unit can also adjust the level of detail of the judgment based on the importance of the reaction information using a machine learning model. For example, the judgment unit adjusts the level of detail of the judgment using a machine learning model that inputs the importance of the reaction information and outputs a detailed judgment result. Furthermore, the judgment unit can grasp the importance of the reaction information in real time and dynamically adjust the level of detail of the judgment. For example, the judgment unit analyzes comments and evaluations collected in real time and immediately adjusts the level of detail of the judgment based on the importance of the reaction information. This makes it possible to adjust the level of detail of the judgment based on the importance of the reaction information. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input data for analyzing the importance of the reaction information to the generation AI and perform analysis by the generation AI.

[0085] The judgment unit can apply different judgment algorithms depending on the category of reaction information at the time of judgment. For example, the judgment unit applies a judgment algorithm that emphasizes a specific keyword to product reviews. The judgment unit can also apply a judgment algorithm that emphasizes customer satisfaction to service evaluations. For example, the judgment unit applies a judgment algorithm using a machine learning model that inputs the category of reaction information and selects an appropriate judgment algorithm. Furthermore, the judgment unit can grasp the category of reaction information in real time and dynamically adjust the judgment algorithm. For example, the judgment unit analyzes comments and evaluations collected in real time and immediately adjusts the judgment algorithm based on the category of reaction information. This makes it possible to apply different judgment algorithms depending on the category of reaction information. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input data for selecting an appropriate judgment algorithm depending on the category of reaction information to the generation AI, and the generation AI can perform analysis.

[0086] The judgment unit can predict the customer's emotions and adjust the length of the judgment based on the predicted customer's emotions. For example, the judgment unit uses a text generation AI (for example, LLM) to analyze the contents of the customer's comments and calculate an emotion score. The judgment unit can also estimate the customer's emotions using a machine learning model. For example, the judgment unit uses a machine learning model that inputs the contents of the customer's comments and outputs an emotion score to estimate the emotion. The judgment unit can also estimate the customer's emotions in real time and adjust the length of the judgment. For example, the judgment unit analyzes comments and evaluations collected in real time, immediately grasps changes in the customer's emotions, and adjusts the length of the judgment. This makes it possible to adjust the length of the judgment based on the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the judgment unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the judgment unit can input data for estimating a customer's emotions into the generation AI, which can then perform analysis.

[0087] The judgment unit can determine the priority of judgment based on the time of submission of reaction information at the time of judgment. For example, the judgment unit gives priority to the latest reaction information. The judgment unit can also determine the priority of judgment based on the time of submission of reaction information using a machine learning model. For example, the judgment unit determines the priority of judgment using a machine learning model that inputs the time of submission of reaction information and outputs the priority. Furthermore, the judgment unit can grasp the time of submission of reaction information in real time and dynamically adjust the priority of judgment. For example, the judgment unit analyzes comments and evaluations collected in real time and immediately adjusts the priority of judgment based on the time of submission of reaction information. This makes it possible to determine the priority of judgment based on the time of submission of reaction information. Part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input data for analyzing the time of submission of reaction information to the generation AI, and the generation AI can perform analysis.

[0088] The judgment unit can adjust the order of judgment based on the relevance of the reaction information at the time of judgment. For example, the judgment unit gives priority to judgment on reaction information with high relevance. The judgment unit can also adjust the order of judgment based on the relevance of the reaction information using a machine learning model. For example, the judgment unit adjusts the order of judgment using a machine learning model that inputs the relevance of the reaction information and outputs the order. Furthermore, the judgment unit can grasp the relevance of the reaction information in real time and dynamically adjust the order of judgment. For example, the judgment unit analyzes comments and evaluations collected in real time and immediately adjusts the order of judgment based on the relevance of the reaction information. This makes it possible to adjust the order of judgment based on the relevance of the reaction information. A part or all of the above-mentioned processing in the judgment unit may be performed, for example, using AI, or may be performed without using AI. For example, the judgment unit can input data for analyzing the relevance of the reaction information to the generation AI and perform analysis by the generation AI.

[0089] The notification unit can predict the customer's emotions and adjust the notification method based on the predicted customer's emotions. For example, the notification unit can analyze the content of the customer's comments using a text generation AI (for example, LLM) and calculate an emotion score. The notification unit can also estimate the customer's emotions using a machine learning model. For example, the notification unit estimates emotions using a machine learning model that inputs the content of the customer's comments and outputs an emotion score. Furthermore, the notification unit can estimate the customer's emotions in real time and adjust the notification method. For example, the notification unit analyzes comments and ratings collected in real time, immediately grasps changes in the customer's emotions, and adjusts the notification method. This makes it possible to adjust the notification method based on the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input data for estimating a customer's emotions into the generation AI, which can then perform analysis.

[0090] The notification unit can select the optimal notification method by analyzing the past reaction history of the customer at the time of notification. For example, the notification unit selects the notification method that the customer preferred based on the past reaction history. The notification unit can also analyze the past reaction history using a machine learning model and select the optimal notification method. For example, the notification unit selects the notification method using a machine learning model that inputs the past reaction history and outputs the optimal notification method. Furthermore, the notification unit can analyze the past reaction history in real time and dynamically adjust the notification method. For example, the notification unit analyzes comments and evaluations collected in real time and immediately adjusts the notification method based on the past reaction history. This makes it possible to select the optimal notification method based on the past reaction history of the customer. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input data for analyzing the past reaction history to the generation AI and perform analysis by the generation AI.

[0091] The notification unit can customize the notification means based on the customer's current activity status at the time of notification. For example, when the customer is in a meeting, the notification unit selects a quiet notification method (e.g., vibration). In addition, when the customer is on the move, the notification unit can also preferentially select voice notification. For example, the notification unit customizes the notification means using a machine learning model that inputs the customer's current activity status and outputs the optimal notification means. Furthermore, the notification unit can grasp the customer's activity status in real time and dynamically adjust the notification means. For example, the notification unit analyzes comments and ratings collected in real time and instantly adjusts the notification means based on the customer's activity status. This makes it possible to customize the optimal notification means based on the customer's current activity status. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input data for analyzing the customer's activity status to the generation AI, and the generation AI can perform the analysis.

[0092] The notification unit can predict the customer's emotions and determine the priority of notifications based on the predicted customer's emotions. For example, the notification unit can analyze the content of the customer's comments using a text generation AI (for example, LLM) and calculate an emotion score. The notification unit can also estimate the customer's emotions using a machine learning model. For example, the notification unit estimates emotions using a machine learning model that inputs the content of the customer's comments and outputs an emotion score. Furthermore, the notification unit can estimate the customer's emotions in real time and determine the priority of notifications. For example, the notification unit analyzes comments and ratings collected in real time, immediately grasps changes in the customer's emotions, and determines the priority of notifications. This makes it possible to determine the priority of notifications based on the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input data for estimating a customer's emotions into the generation AI, which can then perform analysis.

[0093] The notification unit can select the optimal notification method by considering the geographical location information of the customer at the time of notification. For example, the notification unit selects a notification method related to a specific region based on the geographical location information of the customer. The notification unit can also select a notification method that reflects a trend specific to the region based on the geographical location information of the customer. For example, the notification unit selects a notification method using a machine learning model that inputs the geographical location information of the customer and outputs the optimal notification method. Furthermore, the notification unit can grasp the geographical location information of the customer in real time and dynamically adjust the notification method. For example, the notification unit analyzes comments and ratings collected in real time and immediately adjusts the notification method based on the geographical location information of the customer. This makes it possible to select the optimal notification method based on the geographical location information of the customer. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input data for analyzing the geographical location information of the customer to the generation AI and perform analysis by the generation AI.

[0094] The notification unit can analyze the social media activity of the customer at the time of notification and suggest a notification means. For example, the notification unit can suggest a notification means related to a specific hashtag or keyword based on the social media activity of the customer. The notification unit can also suggest a related notification means based on the accounts followed by the customer. For example, the notification unit can suggest a notification means using a machine learning model that inputs the social media activity of the customer and outputs an optimal notification means. Furthermore, the notification unit can grasp the social media activity of the customer in real time and dynamically adjust the notification means. For example, the notification unit can analyze comments and ratings collected in real time and instantly adjust the notification means based on the social media activity of the customer. This makes it possible to suggest an optimal notification means based on the social media activity of the customer. A part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can input data for analyzing the social media activity of the customer to the generation AI and perform analysis by the generation AI.

[0095] The estimation unit can predict the customer's emotions and adjust the estimation method of the promotion effect based on the predicted customer's emotions. For example, the estimation unit can analyze the content of the customer's comments using a text generation AI (for example, LLM) and calculate an emotion score. The estimation unit can also estimate the customer's emotions using a machine learning model. For example, the estimation unit estimates emotions using a machine learning model that inputs the content of the customer's comments and outputs an emotion score. Furthermore, the estimation unit can estimate the customer's emotions in real time and adjust the estimation method of the promotion effect. For example, the estimation unit analyzes comments and evaluations collected in real time, immediately grasps changes in the customer's emotions, and adjusts the estimation method of the promotion effect. This makes it possible to adjust the estimation method of the promotion effect based on the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input data for estimating a customer's emotions into the generation AI, and have the generation AI perform analysis.

[0096] The estimation unit can optimize the estimation algorithm by referring to past promotion effect data at the time of estimation. For example, the estimation unit selects the most effective estimation algorithm based on the past promotion effect data. The estimation unit can also analyze the past promotion effect data using a machine learning model and optimize the estimation algorithm. For example, the estimation unit optimizes the estimation algorithm using a machine learning model that inputs past promotion effect data and outputs an optimal estimation algorithm. Furthermore, the estimation unit can dynamically adjust the estimation algorithm by referring to past promotion effect data in real time. For example, the estimation unit analyzes comments and evaluations collected in real time and instantly adjusts the estimation algorithm based on the past promotion effect data. This allows the estimation algorithm to be optimized based on the past promotion effect data. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input data for analyzing the past promotion effect data to the generation AI and perform analysis by the generation AI.

[0097] The estimation unit can apply different estimation methods for each promotion category at the time of estimation. For example, the estimation unit applies an estimation method that emphasizes sales data to product promotions. The estimation unit can also apply an estimation method that emphasizes customer satisfaction data to service promotions. For example, the estimation unit applies the estimation method using a machine learning model that inputs the promotion category and selects an appropriate estimation method. Furthermore, the estimation unit can grasp the promotion category in real time and dynamically adjust the estimation method. For example, the estimation unit analyzes comments and evaluations collected in real time and immediately adjusts the estimation method based on the promotion category. This makes it possible to apply an optimal estimation method according to the promotion category. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input data for selecting an appropriate estimation method according to the promotion category to the generation AI, and the generation AI can perform analysis.

[0098] The estimation unit can predict the customer's emotions and determine the priority of estimation based on the predicted customer's emotions. For example, the estimation unit can analyze the content of the customer's comments using a text generation AI (for example, LLM) and calculate an emotion score. The estimation unit can also estimate the customer's emotions using a machine learning model. For example, the estimation unit estimates emotions using a machine learning model that inputs the content of the customer's comments and outputs an emotion score. Furthermore, the estimation unit can estimate the customer's emotions in real time and determine the priority of estimation. For example, the estimation unit analyzes comments and evaluations collected in real time, immediately grasps changes in the customer's emotions, and determines the priority of estimation. This makes it possible to determine the priority of estimation based on the customer's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input data for estimating a customer's emotions into the generation AI, and have the generation AI perform analysis.

[0099] The estimation unit can weight the estimation based on the implementation time of the promotion at the time of estimation. For example, if the implementation time of the promotion is a busy season, the estimation unit can weight the estimation highly. Also, if the implementation time of the promotion is a slow season, the estimation unit can weight the estimation lightly. For example, the estimation unit weights the estimation using a machine learning model that inputs the implementation time of the promotion and outputs a weighting. Furthermore, the estimation unit can grasp the implementation time of the promotion in real time and dynamically adjust the weighting of the estimation. For example, the estimation unit analyzes comments and evaluations collected in real time and immediately adjusts the weighting of the estimation based on the implementation time of the promotion. This makes it possible to weight the estimation based on the implementation time of the promotion. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit can input data for analyzing the implementation time of the promotion to the generation AI and perform analysis by the generation AI.

[0100] The estimation unit can improve the accuracy of the estimation by referring to the related market data of the promotion at the time of estimation. For example, the estimation unit improves the estimation accuracy of the promotion effect based on the related market data. The estimation unit can also analyze the related market data using a machine learning model and optimize the estimation algorithm. For example, the estimation unit optimizes the estimation algorithm using a machine learning model that uses the related market data as an input and improves the estimation accuracy. Furthermore, the estimation unit can also dynamically adjust the estimation algorithm by referring to the related market data in real time. For example, the estimation unit analyzes comments and evaluations collected in real time and immediately adjusts the estimation algorithm based on the related market data. This makes it possible to improve the accuracy of the estimation based on the related market data of the promotion. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input data for analyzing the related market data to the generation AI and perform analysis by the generation AI.

[0101] The suggestion unit can predict the customer's emotions and adjust the method of proposing improvements based on the predicted customer's emotions. For example, the suggestion unit can use a text generation AI (for example, LLM) to analyze the content of the customer's comments and calculate an emotion score. The suggestion unit can also estimate the customer's emotions using a machine learning model. For example, the suggestion unit estimates emotions using a machine learning model that inputs the content of the customer's comments and outputs an emotion score. Furthermore, the suggestion unit can estimate the customer's emotions in real time and adjust the method of proposing improvements. For example, the suggestion unit analyzes comments and evaluations collected in real time, immediately grasps changes in the customer's emotions, and adjusts the method of proposing improvements. This makes it possible to adjust the method of proposing improvements based on the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input data for estimating a customer's emotions into the generation AI, and have the generation AI perform analysis.

[0102] The suggestion unit can optimize the proposed algorithm by referring to past promotion improvement data at the time of proposal. For example, the suggestion unit selects the most effective proposed algorithm based on the past promotion improvement data. The suggestion unit can also analyze the past promotion improvement data using a machine learning model and optimize the proposed algorithm. For example, the suggestion unit optimizes the proposed algorithm using a machine learning model that inputs past promotion improvement data and outputs an optimal proposed algorithm. Furthermore, the suggestion unit can dynamically adjust the proposed algorithm by referring to the past promotion improvement data in real time. For example, the suggestion unit analyzes comments and evaluations collected in real time and instantly adjusts the proposed algorithm based on the past promotion improvement data. This allows the proposed algorithm to be optimized based on the past promotion improvement data. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input data for analyzing the past promotion improvement data to the generation AI and perform analysis by the generation AI.

[0103] The suggestion unit can apply different proposal methods for each promotion category at the time of proposal. For example, the suggestion unit applies a proposal method that emphasizes sales data to product promotion. The suggestion unit can also apply a proposal method that emphasizes customer satisfaction data to service promotion. For example, the suggestion unit applies the proposal method using a machine learning model that inputs the promotion category and selects an appropriate proposal method. Furthermore, the suggestion unit can grasp the promotion category in real time and dynamically adjust the proposal method. For example, the suggestion unit analyzes comments and evaluations collected in real time and immediately adjusts the proposal method based on the promotion category. This makes it possible to apply the optimal proposal method according to the promotion category. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input data for selecting an appropriate proposal method according to the promotion category to the generation AI, and the generation AI can perform analysis.

[0104] The suggestion unit can predict the customer's emotions and determine the priority of suggestions based on the predicted customer's emotions. For example, the suggestion unit can use a text generation AI (e.g., LLM) to analyze the content of the customer's comments and calculate an emotion score. The suggestion unit can also estimate the customer's emotions using a machine learning model. For example, the suggestion unit estimates emotions using a machine learning model that inputs the content of the customer's comments and outputs an emotion score. Furthermore, the suggestion unit can estimate the customer's emotions in real time and determine the priority of suggestions. For example, the suggestion unit analyzes comments and evaluations collected in real time, immediately grasps changes in the customer's emotions, and determines the priority of suggestions. This makes it possible to determine the priority of suggestions based on the customer's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input data for estimating a customer's emotions into the generation AI, and have the generation AI perform analysis.

[0105] The suggestion unit can weight the proposal based on the implementation time of the promotion at the time of proposal. For example, if the implementation time of the promotion is a busy season, the suggestion unit can weight the proposal highly. Also, if the implementation time of the promotion is a slow season, the suggestion unit can weight the proposal low. For example, the suggestion unit weights the proposal using a machine learning model that inputs the implementation time of the promotion and outputs a weighting. Furthermore, the suggestion unit can grasp the implementation time of the promotion in real time and dynamically adjust the weighting of the proposal. For example, the suggestion unit analyzes comments and evaluations collected in real time and immediately adjusts the weighting of the proposal based on the implementation time of the promotion. In this way, the proposal can be weighted based on the implementation time of the promotion. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input data for analyzing the implementation time of the promotion to the generation AI, and the generation AI can perform the analysis.

[0106] The proposal unit can improve the accuracy of the proposal by referring to the relevant market data of the promotion at the time of proposal. For example, the proposal unit improves the proposal accuracy of the promotion improvement based on the relevant market data. The proposal unit can also analyze the relevant market data using a machine learning model and optimize the proposal algorithm. For example, the proposal unit optimizes the proposal algorithm using a machine learning model that uses the relevant market data as an input and improves the proposal accuracy. Furthermore, the proposal unit can dynamically adjust the proposal algorithm by referring to the relevant market data in real time. For example, the proposal unit analyzes comments and evaluations collected in real time and instantly adjusts the proposal algorithm based on the relevant market data. This makes it possible to improve the accuracy of the proposal based on the relevant market data of the promotion. A part or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI or may be performed without using AI. For example, the proposal unit can input data for analyzing the relevant market data to the generation AI and perform analysis by the generation AI.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] The marketing support system may further include a purchase history analysis unit that analyzes the purchase history of the customer. The purchase history analysis unit collects and analyzes the customer's past purchase history to grasp the customer's purchasing trends and preferences. For example, the purchase history analysis unit may analyze the types and frequency of products that the customer has purchased in the past, and identify what products the customer is interested in. The purchase history analysis unit may also predict the product that the customer is likely to purchase next, based on the customer's purchase history. Furthermore, the purchase history analysis unit may combine the customer's purchase history with reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotions based on the customer's purchase history.

[0109] The marketing support system may further include a behavior history analysis unit that analyzes the behavior history of the customer. The behavior history analysis unit collects and analyzes behavior data such as the customer's website browsing history and app usage history. For example, the behavior history analysis unit analyzes which pages the customer viewed and which functions the customer used, and identifies the customer's interests and concerns. The behavior history analysis unit may also predict what action the customer is likely to take next based on the customer's behavior data. Furthermore, the behavior history analysis unit may combine the customer's behavior data with the reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotion based on the customer's behavior history.

[0110] The marketing support system may further include a social media analysis unit that analyzes the social media activities of the customer. The social media analysis unit collects and analyzes activity data of the customer on social media. For example, the social media analysis unit may analyze what kind of posts the customer has made and what accounts the customer follows, and identify the customer's interests and concerns. The social media analysis unit may also predict what kind of post the customer is likely to make next, based on the customer's social media activities. Furthermore, the social media analysis unit may combine the customer's social media activities with reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotions based on the customer's social media activities.

[0111] The marketing support system may further include a location information analysis unit that analyzes the geographical location information of the customer. The location information analysis unit collects and analyzes the customer's current location and past movement history. For example, the location information analysis unit may analyze which area the customer lives in and which area the customer frequently visits, and identify the customer's living area and range of movement. The location information analysis unit may also predict which area the customer is likely to visit next, based on the customer's location information. Furthermore, the location information analysis unit may combine the customer's location information and reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotions based on the customer's geographical location information.

[0112] The marketing support system can further include a purchasing willingness prediction unit that predicts a customer's purchasing willingness. The purchasing willingness prediction unit predicts a customer's purchasing willingness based on the customer's reaction information and behavioral data. For example, the purchasing willingness prediction unit analyzes the content of the customer's comments and ratings to determine the level of purchasing willingness of the customer. The purchasing willingness prediction unit can also predict the product that the customer is likely to purchase next based on the customer's behavioral data. Furthermore, the purchasing willingness prediction unit can combine the customer's purchasing willingness and reaction information to more accurately determine the customer's needs and emotions. This allows the marketing support system to realize more effective promotions based on the customer's purchasing willingness.

[0113] The marketing support system can further estimate the customer's emotions and adjust the timing of promotion based on the estimated emotions. For example, when the customer has positive emotions, the timing of promotion can be advanced. On the other hand, when the customer has negative emotions, the timing of promotion can be delayed. This allows promotion to be performed at the optimal timing according to the customer's emotions. For example, when the customer has positive emotions, promotion can be performed immediately to increase purchasing motivation. Also, when the customer has negative emotions, promotion can be temporarily withheld and the customer's emotions can be waited for to improve. Furthermore, changes in the customer's emotions can be monitored in real time and the timing of promotion can be dynamically adjusted. This allows more effective promotion to be realized based on the customer's emotions.

[0114] The marketing support system can further estimate the customer's emotions and customize the content of the promotion based on the estimated emotions. For example, when the customer has positive emotions, the content of the promotion can be strengthened. On the other hand, when the customer has negative emotions, the content of the promotion can be changed to resolve the customer's dissatisfaction. This makes it possible to provide optimal promotion content according to the customer's emotions. For example, when the customer has positive emotions, benefits and discounts can be provided to further increase purchasing motivation. Also, when the customer has negative emotions, information and support for solving the problem can be provided to resolve the customer's dissatisfaction. Furthermore, it is also possible to monitor changes in the customer's emotions in real time and dynamically adjust the content of the promotion. This makes it possible to realize more effective promotion based on the customer's emotions.

[0115] The marketing support system can further estimate the customer's emotions and select a promotion channel based on the estimated emotions. For example, if the customer has positive emotions, a positive channel such as SNS or email can be selected. On the other hand, if the customer has negative emotions, a channel that allows individual support such as telephone or face-to-face can be selected. This makes it possible to provide the optimal promotion channel according to the customer's emotions. For example, if the customer has positive emotions, a campaign on SNS can be implemented to increase the customer's purchasing motivation. Also, if the customer has negative emotions, the problem can be solved through customer support to eliminate the customer's dissatisfaction. Furthermore, it is also possible to monitor changes in the customer's emotions in real time and dynamically adjust the promotion channel. This makes it possible to realize more effective promotion based on the customer's emotions.

[0116] The marketing support system can further estimate the customer's emotions and adjust the frequency of promotions based on the estimated emotions. For example, when the customer has positive emotions, the frequency of promotions can be increased. On the other hand, when the customer has negative emotions, the frequency of promotions can be decreased. This makes it possible to provide an optimal promotion frequency according to the customer's emotions. For example, when the customer has positive emotions, promotions can be carried out several times a week to increase purchasing motivation. Also, when the customer has negative emotions, promotions can be limited to once a month to reduce the burden on the customer. Furthermore, it is also possible to monitor changes in the customer's emotions in real time and dynamically adjust the frequency of promotions. This makes it possible to realize more effective promotions based on the customer's emotions.

[0117] The marketing support system can further estimate the customer's emotions and adjust the promotion format based on the estimated emotions. For example, if the customer has positive emotions, a visual format such as a video or image can be selected. On the other hand, if the customer has negative emotions, a descriptive format such as text or audio can be selected. This makes it possible to provide an optimal promotion format according to the customer's emotions. For example, if the customer has positive emotions, a video conveying the appeal of the product can be provided to increase the customer's desire to purchase. Also, if the customer has negative emotions, a text containing a detailed description of the product and how to use it can be provided to alleviate the customer's anxiety. Furthermore, it is also possible to monitor changes in the customer's emotions in real time and dynamically adjust the promotion format. This makes it possible to realize more effective promotion based on the customer's emotions.

[0118] The process flow of the second embodiment will be briefly described below.

[0119] Step 1: The collection unit collects reaction information indicating customer reactions to the promotional post. The reaction information includes, for example, the contents of customer comments, the contents of ratings, and the number of impressions such as page views, likes, and retweets. The collection unit collects this information from the SNS platform through an API. It can also use web scraping technology to collect publicly available comments and ratings. Furthermore, the collection unit collects reaction information in real time, enabling rapid analysis. Step 2: The determination unit determines at least one of the customer's needs and emotions based on the reaction information collected by the collection unit. The determination unit uses natural language processing technology and machine learning models to analyze the content of the customer's comments and determine positive or negative emotions. It can also determine the customer's needs. Furthermore, the determination unit can monitor changes in the customer's emotions in real time based on the collected reaction information. Step 3: The notification unit notifies the poster of the promotional post when the result of the determination by the determination unit satisfies a predetermined condition. For example, when the negative emotion value exceeds a threshold, the notification unit can detect the risk of a social media outrage early on and send a notification encouraging a quick response. In addition, when the positive emotion value is high, the notification unit can also send a notification suggesting strengthening the promotion.

[0120] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0121] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0122] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0123] For example, the collection unit is realized by either the smart device 14 or the data processing device 12. For example, the control unit 46A of the smart device 14 can collect reaction information by using the API of an SNS platform. In addition, the specific processing unit 290 of the data processing device 12 can collect published comments and evaluations by using a web scraping technique. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes the content of the customer's comments by using a natural language processing technique to calculate an emotion score. The notification unit is realized by, for example, the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and notifies the poster of the promotion post based on the determination result. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 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.

[0126] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0127] 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.

[0128] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0129] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0130] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0131] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0132] 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.

[0133] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0134] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0135] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0136] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0138] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0139] For example, the collection unit is realized by either the smart glasses 214 or the data processing device 12. For example, the control unit 46A of the smart glasses 214 can collect reaction information by using the API of the SNS platform. In addition, the specific processing unit 290 of the data processing device 12 can collect published comments and evaluations by using a web scraping technique. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes the content of the customer's comments by using a natural language processing technique and calculates an emotion score. The notification unit is realized by, for example, the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and notifies the poster of the promotion post based on the determination result. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 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.

[0142] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0143] 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.

[0144] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0145] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0146] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0147] 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.

[0148] 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.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0150] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0152] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0154] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0155] For example, the collection unit is realized by either the headset type terminal 314 or the data processing device 12. For example, the control unit 46A of the headset type terminal 314 can collect reaction information by using the API of the SNS platform. In addition, the specific processing unit 290 of the data processing device 12 can collect published comments and evaluations by using web scraping technology. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes the content of the customer's comments by using natural language processing technology and calculates an emotion score. The notification unit is realized by, for example, the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and notifies the poster of the promotion post based on the determination result. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0158] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0159] 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.

[0160] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0161] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0162] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0163] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0164] 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.

[0165] 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.

[0166] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0167] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0169] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0171] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0172] For example, the collection unit is realized by either the robot 414 or the data processing device 12. For example, the control unit 46A of the robot 414 can collect reaction information by using the API of an SNS platform. In addition, the specific processing unit 290 of the data processing device 12 can collect published comments and evaluations by using a web scraping technique. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes the content of the customer's comments by using a natural language processing technique to calculate an emotion score. The notification unit is realized by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and notifies the poster of the promotion post based on the determination result. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0173] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0174] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0175] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0176] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0177] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0178] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0179] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0180] 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.

[0181] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0182] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0183] 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.

[0184] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0185] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0186] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0187] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0188] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0189] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0190] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0191] (Appendix 1) A collection unit that collects response information indicative of customer responses to the promotional posts; A determination unit that determines at least one of the needs and emotions of the customer based on the reaction information collected by the collection unit; a notification unit that notifies the poster of the promotional post when a result of the determination by the determination unit satisfies a predetermined condition. A system characterized by: (Appendix 2) The determination unit is Determine the customer's negative sentiment value, The notification unit is When the negative emotion value exceeds a threshold, the notification is performed. 2. The system of claim 1, (Appendix 3) The collecting unit includes: Information indicating the contents of comments and evaluations of customers regarding the promotional posting is collected as the reaction information. 2. The system of claim 1, (Appendix 4) The determination unit is determining at least one of the customer's needs and emotions based on the reaction information collected by the collection unit and a promotion category of the promotional post; 2. The system of claim 1, (Appendix 5) The determination unit is Determine at least one of the needs and emotions of the customer based on the reaction information collected by the collection unit and attributes of the customer who reacted to the promotional post. 2. The system of claim 1, (Appendix 6) Based on the result of the determination by the determination unit, Equipped with an estimation unit that predicts the effectiveness of promotional posts 2. The system of claim 1, (Appendix 7) Based on the result of the determination by the determination unit, Equipped with a suggestion section that suggests improvements to promotional posts 2. The system of claim 1, (Appendix 8) The collecting unit includes: Anticipate customer sentiment Adjust the timing of collecting reaction information based on predicted customer sentiment 2. The system of claim 1, (Appendix 9) The collecting unit includes: When collecting data, analyze the customer's past response history and select the appropriate collection method. 2. The system of claim 1, (Appendix 10) The collecting unit includes: Filtering at the time of collection based on the customer's current interests and activities 2. The system of claim 1, (Appendix 11) The collecting unit includes: Anticipate customer sentiment Prioritize the response information to be collected based on predicted customer sentiment 2. The system of claim 1, (Appendix 12) The collecting unit includes: Prioritize collection of relevant response information based on the customer's geographic location at the time of collection 2. The system of claim 1, (Appendix 13) The collecting unit includes: Analyze your social media activity at the time of collection and collect relevant response information 2. The system of claim 1, (Appendix 14) The determination unit is Anticipate customer sentiment Adjust how you word your judgment based on predicted customer sentiment 2. The system of claim 1, (Appendix 15) The determination unit is Adjust the level of detail of the judgment based on the importance of the reaction information when making a judgment. 2. The system of claim 1, (Appendix 16) The determination unit is Apply different judgment algorithms depending on the category of reaction information when judging 2. The system of claim 1, (Appendix 17) The determination unit is Anticipate customer sentiment Adjust the length of the trial based on predicted customer sentiment 2. The system of claim 1, (Appendix 18) The determination unit is Priority of judgment will be determined based on the timing of submission of reaction information at the time of judgment. 2. The system of claim 1, (Appendix 19) The determination unit is Adjust the order of judgments based on the relevance of reaction information during judgment 2. The system of claim 1, (Appendix 20) The notification unit is Anticipate customer sentiment Tailor your notifications based on predicted customer sentiment 2. The system of claim 1, (Appendix 21) The notification unit is When notifying customers, analyze their past response history to select the optimal notification method 2. The system of claim 1, (Appendix 22) The notification unit is Customize notification methods based on the customer's current activity at the time of notification 2. The system of claim 1, (Appendix 23) The notification unit is Anticipate customer sentiment Prioritize notifications based on predicted customer sentiment 2. The system of claim 1, (Appendix 24) The notification unit is When notifying customers, select the optimal notification method based on their geographic location 2. The system of claim 1, (Appendix 25) The notification unit is Analyze customer social media activity to suggest notification methods 2. The system of claim 1, (Appendix 26) The estimation unit is Anticipate customer sentiment Adjust promotion effectiveness estimates based on predicted customer sentiment 2. The system of claim 1, (Appendix 27) The estimation unit is Optimize the estimation algorithm by referring to past promotion effect data when making estimates 2. The system of claim 1, (Appendix 28) The estimation unit is Apply different estimation methods to different promotion categories during estimation 2. The system of claim 1, (Appendix 29) The estimation unit is Anticipate customer sentiment Prioritize inferences based on predicted customer sentiment 2. The system of claim 1, (Appendix 30) The estimation unit is Weighting the estimate based on when the promotion was implemented during the estimation 2. The system of claim 1, (Appendix 31) The estimation unit is Improve accuracy of estimation by referencing promotion-related market data during estimation 2. The system of claim 1, (Appendix 32) The suggestion unit, Anticipate customer sentiment Tailor suggested improvements based on predicted customer sentiment 2. The system of claim 1, (Appendix 33) The suggestion unit, Optimize the proposal algorithm by referring to past promotion improvement data when making proposals 2. The system of claim 1, (Appendix 34) The suggestion unit, Apply different proposal methods to different promotion categories when making proposals 2. The system of claim 1, (Appendix 35) The suggestion unit, Anticipate customer sentiment Prioritize offers based on predicted customer sentiment 2. The system of claim 1, (Appendix 36) The suggestion unit, Weighting offers based on promotion timing at time of offer 2. The system of claim 1, (Appendix 37) The suggestion unit, Refer to promotion-related market data when making proposals to improve the accuracy of proposals 2. The system of claim 1, [Explanation of symbols]

[0192] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects reaction information indicative of customer reactions to the promotional posts; A determination unit that determines at least one of the needs and emotions of the customer based on the reaction information collected by the collection unit; a notification unit that notifies the poster of the promotional post when a result of the determination by the determination unit satisfies a predetermined condition. A system characterized by:

2. The determination unit is determining a negative sentiment value of the customer; The notification unit is When the negative emotion value exceeds a threshold, the notification is performed.

2. The system of claim 1 .

3. The collecting unit includes: Information indicating the contents of the customer's comments and evaluations regarding the promotional posts is collected as the reaction information.

2. The system of claim 1 .

4. The determination unit is determining at least one of the customer's needs and emotions based on the reaction information collected by the collection unit and a promotion category of the promotional post; 2. The system of claim 1 .

5. The determination unit is Determine at least one of the needs and emotions of the customer based on the reaction information collected by the collection unit and attributes of the customer who reacted to the promotional post.

2. The system of claim 1 .

6. An estimation unit that estimates the effectiveness of the promotional post based on the result of the determination by the determination unit.

2. The system of claim 1 .

7. A suggestion unit that suggests improvements to the promotional post based on the result of the determination by the determination unit.

2. The system of claim 1 .

8. The collecting unit includes: Predicting the customer's feelings and adjusting the timing of collecting the reaction information based on the predicted customer's feelings.

2. The system of claim 1 .

9. The collecting unit includes: When collecting data, analyze the customer's past response history and select an appropriate collection method.

2. The system of claim 1 .

Images