System

Abstract

A system is provided.SOLUTION: This system is provided with a means for collecting measure information from the user of each department, a means for storing the collected measure information in a database, a means for periodically acquiring external factor information, and for storing it in the database, a means for analyzing the stored measure information and external factor information, and a means for notifying the user of each department of the analyzed result.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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] There is a need to accurately measure the effectiveness of measures implemented by each department within an organization and create highly accurate forecasts while taking external factors into account. However, the current system does not adequately share information between departments and does not take into account the impact of external factors, making it difficult to accurately grasp the true effectiveness of measures. This leads to a lack of coordination between the marketing and sales departments and a misunderstanding due to external factors, hindering improvement in the performance of the entire organization. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means. Specifically, the system includes a means for collecting policy information from users in each department, a means for storing the collected policy information in a database, a means for periodically acquiring external factor information and storing it in the database, a means for analyzing the stored policy information and external factor information, and a means for notifying users in each department of the analysis results. Furthermore, the system can include a means for analyzing the stored policy information and external factor information using a machine learning algorithm. This system can also add a means for predicting the effects of the next policy and a means for notifying users in each department of the prediction results. This strengthens information sharing among departments and realizes highly accurate forecasts and effect measurement that also take external factors into account.

[0006] "Policy information" is data showing the specific action plans and campaigns implemented by each department, their target values, and the results of their implementation.

[0007] A "database" is a storage area on a computer system for centrally managing and storing collected policy information and external factor information.

[0008] "External factor information" refers to information outside the organization that is thought to affect the effectiveness of measures, and specifically includes weather information, macroeconomic data, and the like.

[0009] A "machine learning algorithm" is a mathematical model and its execution process for making predictions and analyses based on past data.

[0010] "Analysis" refers to the evaluation and calculation of the effectiveness of measures using collected information on measures and external factors.

[0011] "User" refers to the person in charge within an organization who uses this system to input and check policy information and receive analysis results.

[0012] "Notification" is a means of communication to inform users of analysis results or prediction results, and is usually provided as an electronic message.

[0013] The "prediction results" are the results of estimating the effectiveness of future measures using machine learning algorithms.

[0014] "Means" are a set of specific processes or devices designed to perform a particular function or role. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[0027] 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.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] 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.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] 1. Overview of the entire system

[0037] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system operates in cooperation with the server, terminals, and users, promoting information sharing between departments and conducting analysis that takes external factors into account.

[0038] 2. Collection and accumulation of policy information

[0039] The user uses a device to input campaign information into the AI ​​chatbot. For example, they can enter details such as, "We have launched a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0040] The device sends this policy information to the server via an AI chatbot.

[0041] The server stores the received policy information in a database.

[0042] 3. Collecting information on external factors

[0043] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[0044] The acquired information on external factors is stored in a database and integrated with other policy information.

[0045] 4. Data Analysis

[0046] The server uses machine learning algorithms to analyze the accumulated information on measures and external factors. The purpose of the analysis is to evaluate the true effectiveness of each measure and clarify how external factors are affecting it.

[0047] For example, the effectiveness of a TV commercial campaign implemented by the marketing department can be evaluated independently from the impact of heavy rain that occurred at the same time.

[0048] 5. Notification and sharing of analysis results

[0049] The server notifies users in each department of the results of the analysis via an AI chatbot, providing detailed reports such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas."

[0050] Users can use their devices to receive these analysis results and provide feedback on the effectiveness of the measures.

[0051] 6. Feedback and Reassessment

[0052] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including details such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%."

[0053] The server stores this feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[0054] 7. Predicting future measures

[0055] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future measures.

[0056] For example, it is possible to generate prediction results such as, "A target audience rating of 15% for the next campaign is reasonable. Also, taking into account weather forecasts, the audience rating in the Kanto region may be affected."

[0057] The device will notify relevant users of the prediction results via an AI chatbot, helping them plan their actions.

[0058] Specific examples

[0059] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses machine learning algorithms to analyze the effectiveness of the campaign, including the impact of heavy rain on viewership. Finally, the server notifies the marketing department of the results of the analysis and provides a forecast to help plan future campaigns.

[0060] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation while taking external factors into account.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0064] Step 2:

[0065] The terminal sends the policy information entered by the user to the server via an AI chatbot.

[0066] Step 3:

[0067] The server stores the received policy information in a database.

[0068] Step 4:

[0069] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[0070] Step 5:

[0071] The server stores the acquired external factor information in a database.

[0072] Step 6:

[0073] The server uses machine learning algorithms to analyze the accumulated policy information and external factor information, and evaluates the impact of each policy factor.

[0074] Step 7:

[0075] The server notifies users in each department of the analysis results via an AI chatbot, generating a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas."

[0076] Step 8:

[0077] The user receives notifications from the AI ​​chatbot on their device, checks the analysis results, and provides feedback if necessary.

[0078] Step 9:

[0079] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including detailed information such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%."

[0080] Step 10:

[0081] The server stores the received feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[0082] Step 11:

[0083] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future measures.

[0084] Step 12:

[0085] The server notifies users in each department of the results of the predictions via an AI chatbot, providing, for example, a prediction such as, "A target audience rating of 15% for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected."

[0086] Step 13:

[0087] Users can use their devices to receive the forecast results and reflect them in their next action plan. Through this process, collaboration between departments is strengthened, and highly accurate effect measurement and forecast creation are achieved while taking external factors into account.

[0088] Example 1

[0089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0090] With conventional policy effectiveness measurement systems, it was difficult to centrally collect and analyze policy information from each department and information on external factors, and to effectively communicate and share the results. Another problem was the low accuracy of predicting the next policy plan using policy feedback information. This resulted in a decrease in the accuracy of policy effectiveness measurement and decision-making, making it difficult to formulate effective policy plans.

[0091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0092] In this invention, the server includes means for collecting policy information from users in each department and storing it in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information using a machine learning algorithm, means for notifying users in each department of the analysis results, means for collecting feedback from users in each department, means for storing the collected feedback information in the database, means for reevaluating based on the feedback information, means for predicting the effectiveness of the next policy, and means for notifying users in each department of the prediction results. This makes it possible to comprehensively analyze policy information and external factor information and utilize feedback to measure effectiveness and predict future policies with high accuracy.

[0093] "Policy information" refers to data on the plans and activities implemented by each department.

[0094] "Departmental users" refers to people who work in different departments of a company or organization.

[0095] "Terminal" means an electronic device used by a user to input and view information.

[0096] A "database" is a system for organizing and storing information.

[0097] "External factor information" refers to external conditions and data that affect policies, such as weather information and economic data.

[0098] A "server" is a central system for receiving, storing, and analyzing information from users.

[0099] A "machine learning algorithm" is a program that finds useful patterns and predictions from large amounts of data.

[0100] "Analysis Results" means analytical data obtained using machine learning algorithms or other means.

[0101] "Feedback information" refers to ratings and additional information provided by users.

[0102] "Reevaluation" refers to additional analysis based on newly collected information or feedback.

[0103] "Predicted results" refers to data that predicts the effects and results of future measures.

[0104] This invention is a system that uses AI chatbots to automatically collect, store, and analyze information about each department's measures and their effects. This system operates in cooperation with a server, terminals, and users.

[0105] Specific system configuration

[0106] 1. A terminal is a device through which a user inputs policy information. Specifically, this includes PCs, tablets, smartphones, etc.

[0107] 2. The server is a computer system that stores received policy information, collects external factor information, and analyzes the data using machine learning algorithms. The database uses a relational database such as MySQL or PostgreSQL. Machine learning uses Python's pandas library, scikit-learn, TensorFlow, etc.

[0108] 3. Users are people working in various departments, such as marketing and sales. They can input policy information through the AI ​​chatbot and receive analysis and prediction results.

[0109] Data collection and storage

[0110] The user launches the AI ​​chatbot on their device and inputs information about the campaign. For example, they might input information like, "We've launched a new TV commercial campaign. Our target audience rating is 10%, and the actual result is 12%." The device then sends the input campaign information to the server, which then stores this information in a database.

[0111] Gathering information on external factors

[0112] The server periodically calls the Web API to obtain external factor information. Specifically, it obtains weather information and macroeconomic data from the weather information API and economic data API, and stores this in a database.

[0113] Data analysis

[0114] The server retrieves information about campaigns and external factors from the database and performs analysis using machine learning algorithms. The purpose of the analysis is to evaluate the true effectiveness of each campaign and clarify the influence of external factors. For example, to evaluate the effectiveness of a TV commercial campaign, a regression analysis is performed to isolate the impact of heavy rain on viewer ratings.

[0115] Communicating and sharing analysis results

[0116] The server generates a report of the analysis results and notifies the user through an AI chatbot. For example, the report may include, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas." The user can view the report on their device and provide feedback.

[0117] Feedback and Reassessment

[0118] The user sends feedback information to the server through the AI ​​chatbot. For example, they might send information like, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%." The server then stores this feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[0119] Predicting future measures

[0120] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate, and taking into account weather forecasts, audience ratings may be affected in the Kanto region." The device then notifies the user of this prediction via an AI chatbot.

[0121] Examples of specific examples and prompts

[0122] For example, a marketing department launches a new TV commercial campaign, and users input that information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses machine learning algorithms to analyze the effectiveness of the campaign and generate analysis results, including the impact of heavy rain on viewership. Finally, the server notifies the marketing department of the analysis results and provides predictions that can be used as a reference for planning future campaigns.

[0123] An example of a prompt sentence would be, "We have launched a new TV commercial campaign. The target viewership rate was 10%, and the actual rate was 12%. There was some fluctuation in viewership rate due to heavy rain. Please tell us your predictions for the next campaign." The system will then respond to this.

[0124] As described above, this system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation that takes external factors into account.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] The user launches the AI ​​chatbot on their device and inputs policy information.

[0128] Input: Information about your new TV ad campaign (e.g., "We launched a new TV ad campaign. Our target viewership was 10%, and our actual result was 12%)

[0129] Output: Request data including policy information

[0130] Specific operation: The user enters policy information in text format into the AI ​​chatbot on the device and clicks the input button.

[0131] Step 2:

[0132] The terminal transmits the input policy information to the server.

[0133] Input: Policy information entered by the user

[0134] Output: Policy information sent to the server

[0135] Specific operation: The terminal sends the text entered by the user to the server via the HTTPS protocol.

[0136] Step 3:

[0137] The server stores the received policy information in a database.

[0138] Input: Submitted policy information

[0139] Output: Policy information stored in the database

[0140] Specific operation: The server stores policy information as records in a database such as MySQL or PostgreSQL.

[0141] Step 4:

[0142] The server periodically acquires the external factor information and stores it in a database.

[0143] Input: Request to get external factor information

[0144] Output: External factor information stored in the database

[0145] Specific operation: The server periodically calls the weather information API and economic data API to obtain and store weather information, macroeconomic data, etc.

[0146] Step 5:

[0147] The server analyzes the accumulated policy information and external factor information.

[0148] Input: Policy information and external factor information stored in the database

[0149] Output: Analysis results

[0150] Specific operation: The server retrieves the necessary information from the database using SQL queries and analyzes it using machine learning algorithms such as Python's pandas library, scikit-learn, and TensorFlow.

[0151] Step 6:

[0152] The server notifies the users in each department of the analysis results.

[0153] Input: Analysis results

[0154] Output: A message to inform the user

[0155] Specific operation: The server notifies the user of the analysis results through an AI chatbot and generates a detailed analysis report.

[0156] Step 7:

[0157] The user inputs feedback information and sends it to the server.

[0158] Input: Feedback information (e.g., "We also implemented a unique store promotion, which resulted in a 10% increase in overall sales.")

[0159] Output: Feedback information sent to the server

[0160] Specific actions: The user uses the device to enter feedback information into the AI ​​chatbot and clicks the send button.

[0161] Step 8:

[0162] The server stores the received feedback information in a database.

[0163] Input: Feedback information

[0164] Output: Feedback information stored in a database

[0165] Specific operation: The server stores the feedback information as a record in the database.

[0166] Step 9:

[0167] The server will reassess based on the accumulated data and feedback information.

[0168] Input: Policy information, external factors, feedback information

[0169] Output: Reevaluation results

[0170] Specific operation: The server performs analysis again using all data collected so far and updates the analysis results.

[0171] Step 10:

[0172] The server predicts the effect of the next measure and generates a predicted result.

[0173] Input: Stored data and machine learning algorithms

[0174] Output: Prediction result of next action

[0175] Specific operation: The server operates a model to predict the effectiveness of future measures based on past data and analysis results, and generates prediction results.

[0176] Step 11:

[0177] The terminal notifies the user of the prediction result.

[0178] Input: Prediction result

[0179] Output: A message to inform the user

[0180] Specific operation: Receives the prediction results sent from the server and notifies the user through the AI ​​chatbot.

[0181] (Application example 1)

[0182] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0183] With conventional systems, it was difficult to accurately evaluate the effectiveness of measures implemented by each department and obtain appropriate feedback. It was also difficult to make accurate predictions that took external factors into account, leading to uncertainty about the next measure plan. Furthermore, collecting measure information and feedback from physical stores was cumbersome, which tended to delay integrated analysis.

[0184] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0185] In this invention, the server includes means for collecting policy information from users in each department and storing it in a database, means for periodically acquiring and storing external factor information, means for analyzing the collected policy information and external factor information using a machine learning algorithm, means for notifying users in each department of the analysis results and a prediction of the effectiveness of the next policy to help them plan the policy, means for users of the physical store to input policy information via a smart device and collect feedback, and means for generating accurate prediction results based on the acquired external factor information and providing them to users. This makes it possible to accurately evaluate the effectiveness of policies in each department and provide highly accurate predictions that take external factors into account.

[0186] "Users in each department" refers to employees and staff members who belong to different departments of a company or organization.

[0187] "Policy information" refers to detailed information on specific initiatives, campaigns, and promotions implemented by each department.

[0188] "Database" refers to an electronic recording system for storing and managing policy information and external factor information.

[0189] "External factor information" refers to external data that may affect the effectiveness of policies, such as weather forecasts and economic indicators.

[0190] A "machine learning algorithm" refers to a mathematical technique that allows computers to learn patterns from data and make predictions and analyses.

[0191] "Analysis results" refers to the output after analyzing policy information and external factor information using a machine learning algorithm.

[0192] "Smart devices" refers to highly functional mobile devices that can connect to the Internet, such as smartphones and tablets.

[0193] "Feedback" refers to evaluations and comments regarding the results and effectiveness of measures provided by users.

[0194] "Prediction results" refer to the results of predicting the effects of future measures using machine learning algorithms.

[0195] "User" refers to the operators, staff, or customers of physical stores who use the system.

[0196] "Brick and mortar store" refers to a physical store where transactions are conducted directly with customers face-to-face.

[0197] This invention is a system that uses AI chatbots to effectively collect, analyze, and predict policy information. This system operates in cooperation with servers, terminals, and users, enabling accurate collection and analysis of policy information.

[0198] First, the user inputs information about the store's initiatives via a smart device (smartphone or tablet). For example, detailed information such as "Sales during the weekend sale reached 120% of the target. Due to the fine weather, customer traffic increased" can be entered into the chatbot. This allows the context and results of the initiatives to be recorded in detail.

[0199] Policy information sent from smart devices is transferred to the server and stored in a database. The server periodically obtains external factor information (e.g., weather forecasts and economic indicators) from Web APIs and other data sources, and stores this information in the database as well.

[0200] The server analyzes the collected information on measures and external factors using a machine learning algorithm (e.g., Random Forest Regressor). This analysis evaluates the true effect of each measure and clarifies the influence of external factors. For example, it can analyze the effect of a weekend sale on sunny weather separately from other factors.

[0201] The analysis results are communicated to relevant users via an AI chatbot. For example, a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas." This allows users to provide feedback on the effectiveness of the campaign and use it to plan the next campaign.

[0202] Furthermore, the server uses the accumulated data and machine learning algorithms to predict the effectiveness of the next campaign. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected." The device then notifies the relevant user of this prediction via an AI chatbot, which helps with campaign planning.

[0203] As a specific example, by entering a prompt such as "What is a reasonable sales target for the weekend sale? The weather forecast says it's going to rain" into the chatbot, the system will instantly generate and provide a prediction for the next initiative.

[0204] This system efficiently collects information on measures taken by physical stores and enables highly accurate analysis and predictions that take external factors into account, allowing for accurate evaluation of the effectiveness of measures and the optimization of future measures.

[0205] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0206] Step 1:

[0207] Input: A user inputs campaign information using a smart device (e.g., "Sales from the weekend sale reached 120% of the target. The sunny weather led to an increase in customer traffic.").

[0208] Processing: The device sends this policy information to the server via an AI chatbot.

[0209] Output: The policy information is sent to the server and recorded in the database.

[0210] Step 2:

[0211] Input: Policy information submitted by the user.

[0212] Processing: The server periodically obtains external information (e.g., weather forecasts, economic indicators) using Web APIs and data feeds.

[0213] Output: The latest external factor information is stored on the server.

[0214] Step 3:

[0215] Input: Policy information and external factor information are stored in the database.

[0216] Processing: The server analyzes the policy information and external factor information using a machine learning algorithm (e.g., RandomForestRegressor), thereby evaluating the true effectiveness of each policy and the influence of external factors.

[0217] Output: The analysis results are generated (e.g., "The effectiveness of the weekend sale was 20% higher than usual. The sunny weather led to an increase in customer traffic.").

[0218] Step 4:

[0219] Input: Analysis results.

[0220] Processing: The server notifies the user of the analysis results via an AI chatbot.

[0221] Output: A detailed report is displayed on the user's device (e.g., "The effectiveness of our weekend sale was 20% higher than usual. The sunny weather led to an increase in foot traffic.").

[0222] Step 5:

[0223] Input: User feedback (e.g., "We'll further validate the results of this weekend's sale. We'll also add regional sales data.").

[0224] Processing: The AI ​​chatbot receives feedback from the user and sends it to the server.

[0225] Output: Feedback information is stored in a database and used for future analysis and prediction.

[0226] Step 6:

[0227] Input: Accumulated data and feedback information.

[0228] Processing: The server uses machine learning algorithms to predict the effectiveness of the next initiative (e.g., prompt: "What is a reasonable sales target for the next weekend sale? The weather forecast says it's going to rain.").

[0229] Output: A prediction result is generated (e.g., "The target sales for the next weekend sale are expected to increase by 10%. However, rain may affect this.").

[0230] Step 7:

[0231] Input: Prediction results.

[0232] Processing: The server notifies the user of the prediction results through an AI chatbot.

[0233] Output: The prediction results are displayed on the user's device and can be used to plan future measures.

[0234] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0235] 1. Overview of the entire system

[0236] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system involves servers, terminals, and users working together to promote information sharing between departments and perform analysis that takes into account external factors and user emotions.

[0237] 2. Collection and accumulation of policy information

[0238] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0239] The device sends this policy information to the server via an AI chatbot.

[0240] The server stores the received policy information in a database.

[0241] 3. Collecting information on external factors

[0242] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[0243] The acquired information on external factors is stored in a database and integrated with other policy information.

[0244] 4. Introducing the Emotion Engine

[0245] The server embeds an emotion engine into the AI ​​chatbot, which analyzes the user's input information and feedback and recognizes their emotional state (e.g., satisfaction, dissatisfaction, expectation, etc.).

[0246] For example, if a user types, "This campaign didn't work as well as expected," the emotion engine will recognize the emotion of dissatisfaction.

[0247] 5. Data Analysis

[0248] The server uses machine learning algorithms to analyze the accumulated policy information and external factor information, and evaluates the impact of each policy factor.

[0249] In addition, the analysis results of the emotion engine are also integrated to provide a comprehensive evaluation that includes the user's emotions.

[0250] For example, a detailed report can be generated such as, "The effectiveness of the TV commercial campaign was 20% higher than usual, but user sentiment analysis revealed that some users were dissatisfied."

[0251] 6. Notification and sharing of analysis results

[0252] The server notifies users in each department of the analysis results via an AI chatbot.

[0253] Users can use their devices to receive these analysis results and provide feedback on the effectiveness of the measures.

[0254] 7. Feedback and Reassessment

[0255] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including details such as, "We also implemented a store-specific promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected."

[0256] The server stores this feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[0257] 8. Forecasting future measures

[0258] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future measures.

[0259] For example, the system generates predictions such as, "A target audience rating of 15% for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected. Furthermore, previous measures resulted in low satisfaction among some users, so it is recommended that you take measures to improve the situation."

[0260] The device will notify relevant users of the prediction results via an AI chatbot, helping them plan their actions.

[0261] Specific examples

[0262] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign and includes the impact of heavy rain on viewership. The emotion engine also recognizes that there were many complaints from users' feedback. Finally, the server notifies the marketing department of the results of the analysis and provides predictions to be used as a reference for planning future campaigns.

[0263] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation, taking into account external factors and user emotions.

[0264] The processing flow will be explained below.

[0265] Step 1:

[0266] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0267] Step 2:

[0268] The device sends the input policy information to the server via an AI chatbot. This information includes the policy's purpose, means, implementation period, target values, and actual results.

[0269] Step 3:

[0270] The server stores the received policy information in a database, checking the consistency of the input data and converting the data format.

[0271] Step 4:

[0272] The server periodically obtains external information such as weather and macroeconomic data from web APIs and data feeds, and stores this information in a database along with policy information.

[0273] Step 5:

[0274] The server uses an emotion engine to analyze the user's input information and feedback and recognize their emotional state. For example, if a user inputs "This campaign did not have the expected effect," the emotion engine will recognize the emotion as dissatisfied.

[0275] Step 6:

[0276] The server uses a machine learning algorithm to analyze the accumulated information on measures, external factors, and the analysis results of the emotion engine, and evaluates the effectiveness of each measure and how external factors and user emotions have affected its effectiveness.

[0277] Step 7:

[0278] The server notifies users in each department of the analysis results via an AI chatbot, generating a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual, but there was dissatisfaction feedback from multiple users."

[0279] Step 8:

[0280] The user receives notifications from the AI ​​chatbot on their device, checks the analysis results, and provides their own feelings and additional feedback information (e.g., "We also implemented a unique store promotion at the same time, which increased overall sales by 10%.").

[0281] Step 9:

[0282] The device sends the feedback information provided by the user to the server via an AI chatbot.

[0283] Step 10:

[0284] The server stores the received feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[0285] Step 11:

[0286] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates predictions such as, "A 15% target viewer rating is appropriate for the next campaign. Also, previous campaigns have resulted in low satisfaction among some users, so it is recommended that you take measures to improve them."

[0287] Step 12:

[0288] The server notifies the relevant users of the prediction results through an AI chatbot.

[0289] Step 13:

[0290] Users can use their devices to receive the prediction results and reflect them in their next action plan. Through this process, collaboration between departments is strengthened, and highly accurate effect measurement and forecast creation are achieved by taking into account external factors and user sentiment.

[0291] Example 2

[0292] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0293] In today's business environment, it is extremely important for each department to implement measures and accurately evaluate their effectiveness. However, in conventional systems, the collection and analysis of measure information was done manually, which was time-consuming and costly, and the accuracy of the evaluation was limited. Furthermore, it was not possible to take external factors or user sentiment into account, making it difficult to accurately grasp the effectiveness of measures. Furthermore, there were few ways to predict future measure effects, leading to high uncertainty when planning the next measure. This has created a demand for an accurate and efficient system for comprehensive effect measurement and forecast creation.

[0294] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting policy information from users in each department, means for storing the collected policy information in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information, means for notifying users in each department of the analysis results, means for analyzing user emotions, means for integrating the emotion analysis results into policy information analysis, means for collecting user feedback information and storing it in the database, and means for predicting future policies and notifying users in each department of the prediction results. This enables an integrated analysis of policy information and external factors, making it possible to achieve highly accurate effect evaluation and future policy forecasting that also takes user emotional information into consideration.

[0295] "Policy information" refers to data and results regarding specific policies implemented by each department.

[0296] "External factor information" refers to data related to the external environment, such as weather information and macroeconomic data, that affect the effectiveness of policies.

[0297] "Database" refers to an information management system for organizing and storing collected policy information and external factor information.

[0298] "Analysis means" refers to the techniques and processes for analyzing accumulated data and evaluating the effectiveness of measures.

[0299] "Notification means" refers to the technology and process for communicating analysis and prediction results to users in each department.

[0300] "Sentiment analysis" refers to the techniques and processes of extracting and analyzing a user's emotional state from input information.

[0301] "Feedback information" refers to evaluation data provided after a measure is implemented, such as users' opinions and satisfaction with the measure, and areas for improvement.

[0302] "Machine learning algorithms" refers to statistical methods and artificial intelligence techniques used for data analysis and prediction.

[0303] "Effectiveness forecasting" refers to the technology and process of predicting future policy effects based on past and current data.

[0304] 1. Overview of the entire system

[0305] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system involves servers, terminals, and users working together to promote information sharing between departments and perform analysis that takes into account external factors and user emotions.

[0306] 2. Collection and accumulation of policy information

[0307] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target audience rating is 10%, and the actual result is 12%." The device then sends this campaign information to the server via the AI ​​chatbot. The server then stores the received campaign information in a database.

[0308] 3. Collecting information on external factors

[0309] The server periodically obtains external factor information such as weather information and macroeconomic data from web APIs and data feeds. The obtained external factor information is stored in a database and integrated with other policy information.

[0310] 4. Introducing the Emotion Engine

[0311] The server incorporates an emotion engine into the AI ​​chatbot. This emotion engine analyzes the user's input information and feedback and recognizes their emotional state (e.g., satisfaction, dissatisfaction, expectation, etc.). For example, if a user inputs, "This campaign did not have the desired effect," the emotion engine recognizes the emotion as dissatisfaction.

[0312] 5. Data Analysis

[0313] The server uses a machine learning algorithm to analyze the accumulated campaign information and external factor information. This evaluates the degree of impact of each campaign factor. It also integrates the analysis results of the emotion engine to provide a comprehensive evaluation that includes user emotions. For example, it generates a detailed report that states, "The effectiveness of the TV commercial campaign was 20% higher than usual, but some users expressed dissatisfaction."

[0314] 6. Notification and sharing of analysis results

[0315] The server notifies users in each department of the analysis results via an AI chatbot. Users can then receive these results using their devices and provide feedback on the effectiveness of the measures.

[0316] 7. Feedback and Reassessment

[0317] Feedback information provided by users is also sent to the server via the AI ​​chatbot. For example, it may include details such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected." The server stores this feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[0318] 8. Forecasting future measures

[0319] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected. Furthermore, previous campaigns have resulted in low satisfaction among some users, so it is recommended that improvements be made." The device then notifies relevant users of the prediction results via an AI chatbot, helping them plan campaigns.

[0320] Specific examples

[0321] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign and includes the impact of heavy rain on viewership. The emotion engine also recognizes that there were many complaints from users' feedback. Finally, the server notifies the marketing department of the results of the analysis and provides predictions to be used as a reference for planning future campaigns.

[0322] Below are some specific examples of prompt sentences that can be input to the generative AI model in this system.

[0323] "We ran a new TV commercial campaign. Our target viewer rating was 10%, and the actual result was 12%. There were many days of heavy rain during the campaign period, which is thought to have affected the viewer rating. We have received some dissatisfaction from users in their feedback. Please suggest improvements for the next campaign based on your analysis."

[0324] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation, taking into account external factors and user emotions.

[0325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0326] Step 1: User inputs policy information

[0327] Users input information about their initiatives into the AI ​​chatbot using their own devices. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%." This input is structured in text format.

[0328] Input: The user inputs the policy information in text format.

[0329] Output: The policy information entered into the terminal is saved.

[0330] Step 2: Sending policy information from the device to the server

[0331] The device sends the input policy information to the server via an AI chatbot, where it is properly formatted and converted into a usable form.

[0332] Input: Policy information stored on the device.

[0333] Output: Policy information is sent to the server via the AI ​​chatbot.

[0334] Step 3: Storing policy information on the server

[0335] The server stores the received policy information in a database. When the server receives the information, it stores it in the appropriate table in the database and creates an index to enable fast searches.

[0336] Input: Policy information sent to the server.

[0337] Output: Policy information stored in a database.

[0338] Step 4: Server collects external information

[0339] The server periodically retrieves external information such as weather information and macroeconomic data from web APIs and data feeds, for example, from the OpenWeatherMap API or government economic data portals, and stores it in a database.

[0340] Input: Requests for external information from web APIs or data feeds.

[0341] Output: External factor information stored in a database.

[0342] Step 5: Analysis of policy information and external factor information by the server

[0343] The server analyzes the accumulated policy information and external factor information using machine learning algorithms (e.g., random forest, linear regression), and evaluates the impact of each policy factor.

[0344] Input: Policy information and external factor information stored in the database.

[0345] Output: Analyzed data and results (e.g., effectiveness assessment).

[0346] Step 6: Emotion analysis using the emotion engine

[0347] The server uses an emotion engine for policy information and feedback information. For example, it uses natural language processing (NLP) technology to analyze emotions from user input and recognize emotional states such as satisfaction, dissatisfaction, and expectation.

[0348] Input: User text input and feedback.

[0349] Output: Analysis results representing the user's emotional state.

[0350] Step 7: Server generates and notifies analysis results

[0351] The server generates a detailed report based on the analysis results and notifies users in each department. For example, a report such as "The effectiveness of the TV commercial campaign was 20% higher than usual, but some users expressed dissatisfaction" can be compiled and sent to users via an AI chatbot.

[0352] Input: Analysis results from machine learning and sentiment engine.

[0353] Output: Detailed report and user notification.

[0354] Step 8: User feedback

[0355] The user inputs feedback based on the analysis results into the AI ​​chatbot, for example, by writing specific comments such as, "We also implemented a store-specific promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected."

[0356] Input: User feedback.

[0357] Output: Feedback information stored on the device.

[0358] Step 9: Sending feedback information from the device to the server

[0359] The device sends the user's feedback information to the server through the AI ​​chatbot, which then formats the feedback information appropriately and sends it to the server.

[0360] Input: Feedback information stored on the device.

[0361] Output: Feedback information sent to the server.

[0362] Step 10: Server accumulates and re-evaluates feedback information

[0363] The server stores the received feedback information in a database, then performs a comprehensive analysis including the feedback information, and uses the results to help improve future measures.

[0364] Input: The feedback information sent to the server.

[0365] Output: Feedback information stored in a database.

[0366] Step 11: Server creates forecast of future measures

[0367] The server predicts the effectiveness of future campaigns based on accumulated campaign information, external factor information, feedback information, and sentiment analysis results. For example, it generates a prediction such as, "A target audience rating of 15% for the next campaign is appropriate. Taking into account weather forecasts, audience ratings in the Kanto region may be affected," and notifies the device.

[0368] Input: Policy information, external factor information, feedback information, and sentiment analysis results stored in the database.

[0369] Output: Predicted results of future actions notified to the user.

[0370] (Application example 2)

[0371] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0372] Conventional policy evaluation systems only quantitatively evaluate the effectiveness of policies, and do not comprehensively evaluate them, taking into account customer sentiment or external factors. This makes it difficult to accurately measure the effectiveness or predict future policies, making it difficult to improve customer satisfaction or formulate appropriate policy plans.

[0373] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0374] In this invention, the server includes means for collecting policy information from users in each department, means for storing the collected policy information in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information, means for notifying users in each department of the analysis results, emotion analysis means for analyzing user satisfaction and dissatisfaction, means for making a comprehensive evaluation based on the policy information, external factor information, and emotion information, and means for notifying users of the policy analysis results and prediction results to use in policy planning. This enables highly accurate effect measurement and future policy prediction taking into account customer emotions and external factors.

[0375] "Policy information" refers to detailed data and information about specific promotions, campaigns, events, etc. that have been implemented.

[0376] A "database" is an information management system for systematically storing and managing various collected information.

[0377] "External factor information" refers to information about external environmental variables that affect the effectiveness of policies, such as weather, economic data, and social trends.

[0378] "Analysis means" refers to a method or process for evaluating and diagnosing collected and accumulated data using techniques such as statistical analysis and machine learning.

[0379] "Notification means" refers to the communication and notification method used to inform users of analysis results and prediction data.

[0380] "Emotion analysis means" is a technology that automatically analyzes emotions such as satisfaction, dissatisfaction, and expectations from user feedback and comments.

[0381] "Comprehensive evaluation" is a process of centrally evaluating multiple data, such as policy information, external factor information, and emotional information, to determine the overall effectiveness.

[0382] "Policy planning" refers to the specific planning of future promotions and campaigns.

[0383] A "machine learning algorithm" is a mathematical technique that learns from data, discovers patterns, and makes future predictions and classifications.

[0384] The system of the present invention uses an AI chatbot to collect policy information and evaluate its effectiveness. The main components of this system are a server, a terminal, and a user. The server collects, stores, and analyzes data, and notifies the user of the results via the terminal.

[0385] 1. Overview of the entire system

[0386] Users input policy information into their devices. This information is sent to the server via an AI chatbot. The server stores the policy information in a database and periodically collects external factor information. The server also performs sentiment analysis of user feedback and comprehensively evaluates the effectiveness of the policy.

[0387] 2. Collection and accumulation of policy information

[0388] The user inputs specific information about the campaign into the device, such as, "We've launched a new promotion. The target achievement rate is 15%, and the actual result is 18%." The input information is sent to the server via an AI chatbot. The server accumulates this information in a database and saves it for future analysis.

[0389] 3. Collecting information on external factors

[0390] The server periodically obtains information on external factors such as weather and economic data via a Web API and stores it in a database, allowing external factors that affect the effectiveness of measures to be taken into account.

[0391] 4. Emotion analysis

[0392] The AI ​​chatbot collects the feedback provided by the user, and the server analyzes the feedback using a sentiment analysis engine. For example, if a user types, "This promotion did not go as expected," the sentiment analysis engine will evaluate this feedback as "dissatisfied."

[0393] 5. Data Analysis

[0394] The server uses a machine learning algorithm to analyze the accumulated campaign information and external factor information. This allows it to evaluate the impact of each campaign factor. It also integrates the results of the sentiment analysis engine to provide a comprehensive evaluation that includes user sentiment. For example, it generates a detailed report that states, "The effectiveness of the promotion was 20% higher than usual, but user sentiment analysis indicates that some users are dissatisfied."

[0395] 6. Notification and sharing of analysis results

[0396] The server notifies users in each department of the analysis results via an AI chatbot. Users can then receive these results using their devices and provide feedback on the effectiveness of the measures.

[0397] 7. Feedback and Reassessment

[0398] Feedback information provided by users is also sent to the server through the AI ​​chatbot, including details such as, "Some products sold out due to a new promotion, but overall customer satisfaction was low." The server stores this feedback information in a database and reflects it in future measures.

[0399] 8. Forecasting future measures

[0400] The server uses the accumulated data, user emotional information, and machine learning algorithms to predict the effectiveness of the next campaign. For example, it generates a prediction such as, "The next promotion is expected to achieve a 20% target. Also, according to the weather forecast, continued rain may affect sales." The device notifies the user of this prediction via an AI chatbot, which helps with campaign planning.

[0401] Specific examples

[0402] For example, a physical store holds a "New Year's sale" and inputs that information into an AI chatbot. The server stores this information in a database, while also collecting weather and economic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign, including the impact of heavy rain on sales. The emotion engine also recognizes that there were many complaints from customers based on their feedback. Finally, the server notifies the store operator of the analysis results and provides predictions to be used as a reference for planning future campaigns.

[0403] Prompt Sentence Examples

[0404] "Please enter information about your new campaign. Include specifics, timeframe, goals, and achievements."

[0405] "Please enter customer feedback. For example, 'I was satisfied with the campaign' or 'I didn't feel it was effective.'"

[0406] In this way, users can comprehensively evaluate the effectiveness of measures taken in running a physical store and more accurately plan future measures.

[0407] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0408] Step 1:

[0409] The user inputs the policy information into the terminal.

[0410] Specific operation: The user uses a smartphone application to input detailed information about the campaign (e.g., promotion content, period, target value, and actual value). The input information is sent to the server via an AI chatbot.

[0411] Input: Policy information (e.g. promotion details, goal achievement rate, results, etc.)

[0412] Output: Policy information sent to the server via the AI ​​chatbot

[0413] Step 2:

[0414] The server stores the policy information in a database.

[0415] Specific operation: The server stores the received policy information in a database and manages it for future analysis.

[0416] Input: Policy information sent from the AI ​​chatbot

[0417] Output: Policy information stored in the database

[0418] Step 3:

[0419] The server periodically acquires information about external factors and stores it in a database.

[0420] Specific operation: The server periodically obtains weather information and economic data using a Web API and stores this external factor information in a database.

[0421] Input: External information (e.g., weather information via Web API, economic data)

[0422] Output: External factor information stored in the database

[0423] Step 4:

[0424] Users enter their feedback into an AI chatbot.

[0425] Specific operation: The user uses the device to input feedback about the campaign or promotion, for example, inputting a comment such as "This promotion did not meet my expectations."

[0426] Input: Feedback information

[0427] Output: Feedback information sent to the server via the AI ​​chatbot

[0428] Step 5:

[0429] The server analyzes the feedback using a sentiment analysis engine.

[0430] Specific operation: The server passes the feedback information to the emotion analysis engine, and extracts the user's emotions (e.g., satisfaction, dissatisfaction, expectation, etc.) as the analysis result.

[0431] Input: Feedback information

[0432] Output: Parsed emotion information

[0433] Step 6:

[0434] The server performs a comprehensive evaluation based on policy information, external factor information, and emotion information.

[0435] Specific operation: The server uses a machine learning algorithm to analyze policy information and external factor information, and also integrates the results of sentiment analysis to evaluate the overall effectiveness of the policy.

[0436] Input: Policy information, external factor information, emotion information

[0437] Output: Comprehensive evaluation results (e.g., detailed report)

[0438] Step 7:

[0439] The server notifies users in each department of the analysis results via an AI chatbot.

[0440] Specific operation: The server notifies the user of the overall evaluation results in real time and provides a detailed report via an AI chatbot.

[0441] Input: Overall evaluation result

[0442] Output: Reports to be sent to users in each department

[0443] Step 8:

[0444] The feedback information provided by the user is sent to the server via the AI ​​chatbot.

[0445] Specific operation: Users enter feedback on campaign results and areas for improvement into the application, which is then sent to the server via an AI chatbot.

[0446] Input: User feedback information

[0447] Output: Feedback information stored in a database

[0448] Step 9:

[0449] The server predicts the effectiveness of the next measure.

[0450] Specific operation: The server uses accumulated policy information, external factor information, emotional information, and machine learning algorithms to predict the effectiveness of the next policy.

[0451] Input: Policy information, external factor information, emotion information

[0452] Output: Prediction of next policy effect

[0453] Step 10:

[0454] The server notifies the user of the prediction results through an AI chatbot.

[0455] Specific operation: The server sends the prediction results to the user via the AI ​​chatbot, and uses them as a reference for planning the next policy.

[0456] Input: Prediction result

[0457] Output: Prediction results notified to the user

[0458] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0459] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0460] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0461] [Second embodiment]

[0462] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0463] 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.

[0464] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[0465] 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.

[0466] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0467] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0468] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0469] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0470] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0471] 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.

[0472] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0473] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0474] 1. Overview of the entire system

[0475] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system operates in cooperation with the server, terminals, and users, promoting information sharing between departments and conducting analysis that takes external factors into account.

[0476] 2. Collection and accumulation of policy information

[0477] The user uses a device to input campaign information into the AI ​​chatbot. For example, they can enter details such as, "We have launched a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0478] The device sends this policy information to the server via an AI chatbot.

[0479] The server stores the received policy information in a database.

[0480] 3. Collecting information on external factors

[0481] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[0482] The acquired information on external factors is stored in a database and integrated with other policy information.

[0483] 4. Data Analysis

[0484] The server uses machine learning algorithms to analyze the accumulated information on measures and external factors. The purpose of the analysis is to evaluate the true effectiveness of each measure and clarify how external factors are affecting it.

[0485] For example, the effectiveness of a TV commercial campaign implemented by the marketing department can be evaluated independently from the impact of heavy rain that occurred at the same time.

[0486] 5. Notification and sharing of analysis results

[0487] The server notifies users in each department of the results of the analysis via an AI chatbot, providing detailed reports such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas."

[0488] Users can use their devices to receive these analysis results and provide feedback on the effectiveness of the measures.

[0489] 6. Feedback and Reassessment

[0490] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including details such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%."

[0491] The server stores this feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[0492] 7. Predicting future measures

[0493] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future measures.

[0494] For example, it is possible to generate prediction results such as, "A target audience rating of 15% for the next campaign is reasonable. Also, taking into account weather forecasts, the audience rating in the Kanto region may be affected."

[0495] The device will notify relevant users of the prediction results via an AI chatbot, helping them plan their actions.

[0496] Specific examples

[0497] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses machine learning algorithms to analyze the effectiveness of the campaign, including the impact of heavy rain on viewership. Finally, the server notifies the marketing department of the results of the analysis and provides a forecast to help plan future campaigns.

[0498] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation while taking external factors into account.

[0499] The processing flow will be explained below.

[0500] Step 1:

[0501] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0502] Step 2:

[0503] The terminal sends the policy information entered by the user to the server via an AI chatbot.

[0504] Step 3:

[0505] The server stores the received policy information in a database.

[0506] Step 4:

[0507] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[0508] Step 5:

[0509] The server stores the acquired external factor information in a database.

[0510] Step 6:

[0511] The server uses machine learning algorithms to analyze the accumulated policy information and external factor information, and evaluates the impact of each policy factor.

[0512] Step 7:

[0513] The server notifies users in each department of the analysis results via an AI chatbot, generating a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas."

[0514] Step 8:

[0515] The user receives notifications from the AI ​​chatbot on their device, checks the analysis results, and provides feedback if necessary.

[0516] Step 9:

[0517] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including detailed information such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%."

[0518] Step 10:

[0519] The server stores the received feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[0520] Step 11:

[0521] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future measures.

[0522] Step 12:

[0523] The server notifies users in each department of the results of the predictions via an AI chatbot, providing, for example, a prediction such as, "A target audience rating of 15% for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected."

[0524] Step 13:

[0525] Users can use their devices to receive the forecast results and reflect them in their next action plan. Through this process, collaboration between departments is strengthened, and highly accurate effect measurement and forecast creation are achieved while taking external factors into account.

[0526] Example 1

[0527] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0528] With conventional policy effectiveness measurement systems, it was difficult to centrally collect and analyze policy information from each department and information on external factors, and to effectively communicate and share the results. Another problem was the low accuracy of predicting the next policy plan using policy feedback information. This resulted in a decrease in the accuracy of policy effectiveness measurement and decision-making, making it difficult to formulate effective policy plans.

[0529] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0530] In this invention, the server includes means for collecting policy information from users in each department and storing it in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information using a machine learning algorithm, means for notifying users in each department of the analysis results, means for collecting feedback from users in each department, means for storing the collected feedback information in the database, means for reevaluating based on the feedback information, means for predicting the effectiveness of the next policy, and means for notifying users in each department of the prediction results. This makes it possible to comprehensively analyze policy information and external factor information and utilize feedback to measure effectiveness and predict future policies with high accuracy.

[0531] "Policy information" refers to data on the plans and activities implemented by each department.

[0532] "Departmental users" refers to people who work in different departments of a company or organization.

[0533] "Terminal" means an electronic device used by a user to input and view information.

[0534] A "database" is a system for organizing and storing information.

[0535] "External factor information" refers to external conditions and data that affect policies, such as weather information and economic data.

[0536] A "server" is a central system for receiving, storing, and analyzing information from users.

[0537] A "machine learning algorithm" is a program that finds useful patterns and predictions from large amounts of data.

[0538] "Analysis Results" means analytical data obtained using machine learning algorithms or other means.

[0539] "Feedback information" refers to ratings and additional information provided by users.

[0540] "Reevaluation" refers to additional analysis based on newly collected information or feedback.

[0541] "Predicted results" refers to data that predicts the effects and results of future measures.

[0542] This invention is a system that uses AI chatbots to automatically collect, store, and analyze information about each department's measures and their effects. This system operates in cooperation with a server, terminals, and users.

[0543] Specific system configuration

[0544] 1. A terminal is a device through which a user inputs policy information. Specifically, this includes PCs, tablets, smartphones, etc.

[0545] 2. The server is a computer system that stores received policy information, collects external factor information, and analyzes the data using machine learning algorithms. The database uses a relational database such as MySQL or PostgreSQL. Machine learning uses Python's pandas library, scikit-learn, TensorFlow, etc.

[0546] 3. Users are people working in various departments, such as marketing and sales. They can input policy information through the AI ​​chatbot and receive analysis and prediction results.

[0547] Data collection and storage

[0548] The user launches the AI ​​chatbot on their device and inputs information about the campaign. For example, they might input information like, "We've launched a new TV commercial campaign. Our target audience rating is 10%, and the actual result is 12%." The device then sends the input campaign information to the server, which then stores this information in a database.

[0549] Gathering information on external factors

[0550] The server periodically calls the Web API to obtain external factor information. Specifically, it obtains weather information and macroeconomic data from the weather information API and economic data API, and stores this in a database.

[0551] Data analysis

[0552] The server retrieves information about campaigns and external factors from the database and performs analysis using machine learning algorithms. The purpose of the analysis is to evaluate the true effectiveness of each campaign and clarify the influence of external factors. For example, to evaluate the effectiveness of a TV commercial campaign, a regression analysis is performed to isolate the impact of heavy rain on viewer ratings.

[0553] Communicating and sharing analysis results

[0554] The server generates a report of the analysis results and notifies the user through an AI chatbot. For example, the report may include, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas." The user can view the report on their device and provide feedback.

[0555] Feedback and Reassessment

[0556] The user sends feedback information to the server through the AI ​​chatbot. For example, they might send information like, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%." The server then stores this feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[0557] Predicting future measures

[0558] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate, and taking into account weather forecasts, audience ratings may be affected in the Kanto region." The device then notifies the user of this prediction via an AI chatbot.

[0559] Examples of specific examples and prompts

[0560] For example, a marketing department launches a new TV commercial campaign, and users input that information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses machine learning algorithms to analyze the effectiveness of the campaign and generate analysis results, including the impact of heavy rain on viewership. Finally, the server notifies the marketing department of the analysis results and provides predictions that can be used as a reference for planning future campaigns.

[0561] An example of a prompt sentence would be, "We have launched a new TV commercial campaign. The target viewership rate was 10%, and the actual rate was 12%. There was some fluctuation in viewership rate due to heavy rain. Please tell us your predictions for the next campaign." The system will then respond to this.

[0562] As described above, this system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation that takes external factors into account.

[0563] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0564] Step 1:

[0565] The user launches the AI ​​chatbot on their device and inputs policy information.

[0566] Input: Information about your new TV ad campaign (e.g., "We launched a new TV ad campaign. Our target viewership was 10%, and our actual result was 12%)

[0567] Output: Request data including policy information

[0568] Specific operation: The user enters policy information in text format into the AI ​​chatbot on the device and clicks the input button.

[0569] Step 2:

[0570] The terminal transmits the input policy information to the server.

[0571] Input: Policy information entered by the user

[0572] Output: Policy information sent to the server

[0573] Specific operation: The terminal sends the text entered by the user to the server via the HTTPS protocol.

[0574] Step 3:

[0575] The server stores the received policy information in a database.

[0576] Input: Submitted policy information

[0577] Output: Policy information stored in the database

[0578] Specific operation: The server stores policy information as records in a database such as MySQL or PostgreSQL.

[0579] Step 4:

[0580] The server periodically acquires the external factor information and stores it in a database.

[0581] Input: Request to get external factor information

[0582] Output: External factor information stored in the database

[0583] Specific operation: The server periodically calls the weather information API and economic data API to obtain and store weather information, macroeconomic data, etc.

[0584] Step 5:

[0585] The server analyzes the accumulated policy information and external factor information.

[0586] Input: Policy information and external factor information stored in the database

[0587] Output: Analysis results

[0588] Specific operation: The server retrieves the necessary information from the database using SQL queries and analyzes it using machine learning algorithms such as Python's pandas library, scikit-learn, and TensorFlow.

[0589] Step 6:

[0590] The server notifies the users in each department of the analysis results.

[0591] Input: Analysis results

[0592] Output: A message to inform the user

[0593] Specific operation: The server notifies the user of the analysis results through an AI chatbot and generates a detailed analysis report.

[0594] Step 7:

[0595] The user inputs feedback information and sends it to the server.

[0596] Input: Feedback information (e.g., "We also implemented a unique store promotion, which resulted in a 10% increase in overall sales.")

[0597] Output: Feedback information sent to the server

[0598] Specific actions: The user uses the device to enter feedback information into the AI ​​chatbot and clicks the send button.

[0599] Step 8:

[0600] The server stores the received feedback information in a database.

[0601] Input: Feedback information

[0602] Output: Feedback information stored in a database

[0603] Specific operation: The server stores the feedback information as a record in the database.

[0604] Step 9:

[0605] The server will reassess based on the accumulated data and feedback information.

[0606] Input: Policy information, external factors, feedback information

[0607] Output: Reevaluation results

[0608] Specific operation: The server performs analysis again using all data collected so far and updates the analysis results.

[0609] Step 10:

[0610] The server predicts the effect of the next measure and generates a predicted result.

[0611] Input: Stored data and machine learning algorithms

[0612] Output: Prediction result of next action

[0613] Specific operation: The server operates a model to predict the effectiveness of future measures based on past data and analysis results, and generates prediction results.

[0614] Step 11:

[0615] The terminal notifies the user of the prediction result.

[0616] Input: Prediction result

[0617] Output: A message to inform the user

[0618] Specific operation: Receives the prediction results sent from the server and notifies the user through the AI ​​chatbot.

[0619] (Application example 1)

[0620] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0621] With conventional systems, it was difficult to accurately evaluate the effectiveness of measures implemented by each department and obtain appropriate feedback. It was also difficult to make accurate predictions that took external factors into account, leading to uncertainty about the next measure plan. Furthermore, collecting measure information and feedback from physical stores was cumbersome, which tended to delay integrated analysis.

[0622] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0623] In this invention, the server includes means for collecting policy information from users in each department and storing it in a database, means for periodically acquiring and storing external factor information, means for analyzing the collected policy information and external factor information using a machine learning algorithm, means for notifying users in each department of the analysis results and a prediction of the effectiveness of the next policy to help them plan the policy, means for users of the physical store to input policy information via a smart device and collect feedback, and means for generating accurate prediction results based on the acquired external factor information and providing them to users. This makes it possible to accurately evaluate the effectiveness of policies in each department and provide highly accurate predictions that take external factors into account.

[0624] "Users in each department" refers to employees and staff members who belong to different departments of a company or organization.

[0625] "Policy information" refers to detailed information on specific initiatives, campaigns, and promotions implemented by each department.

[0626] "Database" refers to an electronic recording system for storing and managing policy information and external factor information.

[0627] "External factor information" refers to external data that may affect the effectiveness of policies, such as weather forecasts and economic indicators.

[0628] A "machine learning algorithm" refers to a mathematical technique that allows computers to learn patterns from data and make predictions and analyses.

[0629] "Analysis results" refers to the output after analyzing policy information and external factor information using a machine learning algorithm.

[0630] "Smart devices" refers to highly functional mobile devices that can connect to the Internet, such as smartphones and tablets.

[0631] "Feedback" refers to evaluations and comments regarding the results and effectiveness of measures provided by users.

[0632] "Prediction results" refer to the results of predicting the effects of future measures using machine learning algorithms.

[0633] "User" refers to the operators, staff, or customers of physical stores who use the system.

[0634] "Brick and mortar store" refers to a physical store where transactions are conducted directly with customers face-to-face.

[0635] This invention is a system that uses AI chatbots to effectively collect, analyze, and predict policy information. This system operates in cooperation with servers, terminals, and users, enabling accurate collection and analysis of policy information.

[0636] First, the user inputs information about the store's initiatives via a smart device (smartphone or tablet). For example, detailed information such as "Sales during the weekend sale reached 120% of the target. Due to the fine weather, customer traffic increased" can be entered into the chatbot. This allows the context and results of the initiatives to be recorded in detail.

[0637] Policy information sent from smart devices is transferred to the server and stored in a database. The server periodically obtains external factor information (e.g., weather forecasts and economic indicators) from Web APIs and other data sources, and stores this information in the database as well.

[0638] The server analyzes the collected information on measures and external factors using a machine learning algorithm (e.g., Random Forest Regressor). This analysis evaluates the true effect of each measure and clarifies the influence of external factors. For example, it can analyze the effect of a weekend sale on sunny weather separately from other factors.

[0639] The analysis results are communicated to relevant users via an AI chatbot. For example, a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas." This allows users to provide feedback on the effectiveness of the campaign and use it to plan the next campaign.

[0640] Furthermore, the server uses the accumulated data and machine learning algorithms to predict the effectiveness of the next campaign. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected." The device then notifies the relevant user of this prediction via an AI chatbot, which helps with campaign planning.

[0641] As a specific example, by entering a prompt such as "What is a reasonable sales target for the weekend sale? The weather forecast says it's going to rain" into the chatbot, the system will instantly generate and provide a prediction for the next initiative.

[0642] This system efficiently collects information on measures taken by physical stores and enables highly accurate analysis and predictions that take external factors into account, allowing for accurate evaluation of the effectiveness of measures and the optimization of future measures.

[0643] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0644] Step 1:

[0645] Input: A user inputs campaign information using a smart device (e.g., "Sales from the weekend sale reached 120% of the target. The sunny weather led to an increase in customer traffic.").

[0646] Processing: The device sends this policy information to the server via an AI chatbot.

[0647] Output: The policy information is sent to the server and recorded in the database.

[0648] Step 2:

[0649] Input: Policy information submitted by the user.

[0650] Processing: The server periodically obtains external information (e.g., weather forecasts, economic indicators) using Web APIs and data feeds.

[0651] Output: The latest external factor information is stored on the server.

[0652] Step 3:

[0653] Input: Policy information and external factor information are stored in the database.

[0654] Processing: The server analyzes the policy information and external factor information using a machine learning algorithm (e.g., RandomForestRegressor), thereby evaluating the true effectiveness of each policy and the influence of external factors.

[0655] Output: The analysis results are generated (e.g., "The effectiveness of the weekend sale was 20% higher than usual. The sunny weather led to an increase in customer traffic.").

[0656] Step 4:

[0657] Input: Analysis results.

[0658] Processing: The server notifies the user of the analysis results via an AI chatbot.

[0659] Output: A detailed report is displayed on the user's device (e.g., "The effectiveness of our weekend sale was 20% higher than usual. The sunny weather led to an increase in foot traffic.").

[0660] Step 5:

[0661] Input: User feedback (e.g., "We'll further validate the results of this weekend's sale. We'll also add regional sales data.").

[0662] Processing: The AI ​​chatbot receives feedback from the user and sends it to the server.

[0663] Output: Feedback information is stored in a database and used for future analysis and prediction.

[0664] Step 6:

[0665] Input: Accumulated data and feedback information.

[0666] Processing: The server uses machine learning algorithms to predict the effectiveness of the next initiative (e.g., prompt: "What is a reasonable sales target for the next weekend sale? The weather forecast says it's going to rain.").

[0667] Output: A prediction result is generated (e.g., "The target sales for the next weekend sale are expected to increase by 10%. However, rain may affect this.").

[0668] Step 7:

[0669] Input: Prediction results.

[0670] Processing: The server notifies the user of the prediction results through an AI chatbot.

[0671] Output: The prediction results are displayed on the user's device and can be used to plan future measures.

[0672] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0673] 1. Overview of the entire system

[0674] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system involves servers, terminals, and users working together to promote information sharing between departments and perform analysis that takes into account external factors and user emotions.

[0675] 2. Collection and accumulation of policy information

[0676] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0677] The device sends this policy information to the server via an AI chatbot.

[0678] The server stores the received policy information in a database.

[0679] 3. Collecting information on external factors

[0680] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[0681] The acquired information on external factors is stored in a database and integrated with other policy information.

[0682] 4. Introducing the Emotion Engine

[0683] The server embeds an emotion engine into the AI ​​chatbot, which analyzes the user's input information and feedback and recognizes their emotional state (e.g., satisfaction, dissatisfaction, expectation, etc.).

[0684] For example, if a user types, "This campaign didn't work as well as expected," the emotion engine will recognize the emotion of dissatisfaction.

[0685] 5. Data Analysis

[0686] The server uses machine learning algorithms to analyze the accumulated policy information and external factor information, and evaluates the impact of each policy factor.

[0687] In addition, the analysis results of the emotion engine are also integrated to provide a comprehensive evaluation that includes the user's emotions.

[0688] For example, a detailed report can be generated such as, "The effectiveness of the TV commercial campaign was 20% higher than usual, but user sentiment analysis revealed that some users were dissatisfied."

[0689] 6. Notification and sharing of analysis results

[0690] The server notifies users in each department of the analysis results via an AI chatbot.

[0691] Users can use their devices to receive these analysis results and provide feedback on the effectiveness of the measures.

[0692] 7. Feedback and Reassessment

[0693] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including details such as, "We also implemented a store-specific promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected."

[0694] The server stores this feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[0695] 8. Forecasting future measures

[0696] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future measures.

[0697] For example, the system generates predictions such as, "A target audience rating of 15% for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected. Furthermore, previous measures resulted in low satisfaction among some users, so it is recommended that you take measures to improve the situation."

[0698] The device will notify relevant users of the prediction results via an AI chatbot, helping them plan their actions.

[0699] Specific examples

[0700] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign and includes the impact of heavy rain on viewership. The emotion engine also recognizes that there were many complaints from users' feedback. Finally, the server notifies the marketing department of the results of the analysis and provides predictions to be used as a reference for planning future campaigns.

[0701] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation, taking into account external factors and user emotions.

[0702] The processing flow will be explained below.

[0703] Step 1:

[0704] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0705] Step 2:

[0706] The device sends the input policy information to the server via an AI chatbot. This information includes the policy's purpose, means, implementation period, target values, and actual results.

[0707] Step 3:

[0708] The server stores the received policy information in a database, checking the consistency of the input data and converting the data format.

[0709] Step 4:

[0710] The server periodically obtains external information such as weather and macroeconomic data from web APIs and data feeds, and stores this information in a database along with policy information.

[0711] Step 5:

[0712] The server uses an emotion engine to analyze the user's input information and feedback and recognize their emotional state. For example, if a user inputs "This campaign did not have the expected effect," the emotion engine will recognize the emotion as dissatisfied.

[0713] Step 6:

[0714] The server uses a machine learning algorithm to analyze the accumulated information on measures, external factors, and the analysis results of the emotion engine, and evaluates the effectiveness of each measure and how external factors and user emotions have affected its effectiveness.

[0715] Step 7:

[0716] The server notifies users in each department of the analysis results via an AI chatbot, generating a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual, but there was dissatisfaction feedback from multiple users."

[0717] Step 8:

[0718] The user receives notifications from the AI ​​chatbot on their device, checks the analysis results, and provides their own feelings and additional feedback information (e.g., "We also implemented a unique store promotion at the same time, which increased overall sales by 10%.").

[0719] Step 9:

[0720] The device sends the feedback information provided by the user to the server via an AI chatbot.

[0721] Step 10:

[0722] The server stores the received feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[0723] Step 11:

[0724] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates predictions such as, "A 15% target viewer rating is appropriate for the next campaign. Also, previous campaigns have resulted in low satisfaction among some users, so it is recommended that you take measures to improve them."

[0725] Step 12:

[0726] The server notifies the relevant users of the prediction results through an AI chatbot.

[0727] Step 13:

[0728] Users can use their devices to receive the prediction results and reflect them in their next action plan. Through this process, collaboration between departments is strengthened, and highly accurate effect measurement and forecast creation are achieved by taking into account external factors and user sentiment.

[0729] Example 2

[0730] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0731] In today's business environment, it is extremely important for each department to implement measures and accurately evaluate their effectiveness. However, in conventional systems, the collection and analysis of measure information was done manually, which was time-consuming and costly, and the accuracy of the evaluation was limited. Furthermore, it was not possible to take external factors or user sentiment into account, making it difficult to accurately grasp the effectiveness of measures. Furthermore, there were few ways to predict future measure effects, leading to high uncertainty when planning the next measure. This has created a demand for an accurate and efficient system for comprehensive effect measurement and forecast creation.

[0732] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting policy information from users in each department, means for storing the collected policy information in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information, means for notifying users in each department of the analysis results, means for analyzing user emotions, means for integrating the emotion analysis results into policy information analysis, means for collecting user feedback information and storing it in the database, and means for predicting future policies and notifying users in each department of the prediction results. This enables an integrated analysis of policy information and external factors, making it possible to achieve highly accurate effect evaluation and future policy forecasting that also takes user emotional information into consideration.

[0733] "Policy information" refers to data and results regarding specific policies implemented by each department.

[0734] "External factor information" refers to data related to the external environment, such as weather information and macroeconomic data, that affect the effectiveness of policies.

[0735] "Database" refers to an information management system for organizing and storing collected policy information and external factor information.

[0736] "Analysis means" refers to the techniques and processes for analyzing accumulated data and evaluating the effectiveness of measures.

[0737] "Notification means" refers to the technology and process for communicating analysis and prediction results to users in each department.

[0738] "Sentiment analysis" refers to the techniques and processes of extracting and analyzing a user's emotional state from input information.

[0739] "Feedback information" refers to evaluation data provided after a measure is implemented, such as users' opinions and satisfaction with the measure, and areas for improvement.

[0740] "Machine learning algorithms" refers to statistical methods and artificial intelligence techniques used for data analysis and prediction.

[0741] "Effectiveness forecasting" refers to the technology and process of predicting future policy effects based on past and current data.

[0742] 1. Overview of the entire system

[0743] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system involves servers, terminals, and users working together to promote information sharing between departments and perform analysis that takes into account external factors and user emotions.

[0744] 2. Collection and accumulation of policy information

[0745] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target audience rating is 10%, and the actual result is 12%." The device then sends this campaign information to the server via the AI ​​chatbot. The server then stores the received campaign information in a database.

[0746] 3. Collecting information on external factors

[0747] The server periodically obtains external factor information such as weather information and macroeconomic data from web APIs and data feeds. The obtained external factor information is stored in a database and integrated with other policy information.

[0748] 4. Introducing the Emotion Engine

[0749] The server incorporates an emotion engine into the AI ​​chatbot. This emotion engine analyzes the user's input information and feedback and recognizes their emotional state (e.g., satisfaction, dissatisfaction, expectation, etc.). For example, if a user inputs, "This campaign did not have the desired effect," the emotion engine recognizes the emotion as dissatisfaction.

[0750] 5. Data Analysis

[0751] The server uses a machine learning algorithm to analyze the accumulated campaign information and external factor information. This evaluates the degree of impact of each campaign factor. It also integrates the analysis results of the emotion engine to provide a comprehensive evaluation that includes user emotions. For example, it generates a detailed report that states, "The effectiveness of the TV commercial campaign was 20% higher than usual, but some users expressed dissatisfaction."

[0752] 6. Notification and sharing of analysis results

[0753] The server notifies users in each department of the analysis results via an AI chatbot. Users can then receive these results using their devices and provide feedback on the effectiveness of the measures.

[0754] 7. Feedback and Reassessment

[0755] Feedback information provided by users is also sent to the server via the AI ​​chatbot. For example, it may include details such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected." The server stores this feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[0756] 8. Forecasting future measures

[0757] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected. Furthermore, previous campaigns have resulted in low satisfaction among some users, so it is recommended that improvements be made." The device then notifies relevant users of the prediction results via an AI chatbot, helping them plan campaigns.

[0758] Specific examples

[0759] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign and includes the impact of heavy rain on viewership. The emotion engine also recognizes that there were many complaints from users' feedback. Finally, the server notifies the marketing department of the results of the analysis and provides predictions to be used as a reference for planning future campaigns.

[0760] Below are some specific examples of prompt sentences that can be input to the generative AI model in this system.

[0761] "We ran a new TV commercial campaign. Our target viewer rating was 10%, and the actual result was 12%. There were many days of heavy rain during the campaign period, which is thought to have affected the viewer rating. We have received some dissatisfaction from users in their feedback. Please suggest improvements for the next campaign based on your analysis."

[0762] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation, taking into account external factors and user emotions.

[0763] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0764] Step 1: User inputs policy information

[0765] Users input information about their initiatives into the AI ​​chatbot using their own devices. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%." This input is structured in text format.

[0766] Input: The user inputs the policy information in text format.

[0767] Output: The policy information entered into the terminal is saved.

[0768] Step 2: Sending policy information from the device to the server

[0769] The device sends the input policy information to the server via an AI chatbot, where it is properly formatted and converted into a usable form.

[0770] Input: Policy information stored on the device.

[0771] Output: Policy information is sent to the server via the AI ​​chatbot.

[0772] Step 3: Storing policy information on the server

[0773] The server stores the received policy information in a database. When the server receives the information, it stores it in the appropriate table in the database and creates an index to enable fast searches.

[0774] Input: Policy information sent to the server.

[0775] Output: Policy information stored in a database.

[0776] Step 4: Server collects external information

[0777] The server periodically retrieves external information such as weather information and macroeconomic data from web APIs and data feeds, for example, from the OpenWeatherMap API or government economic data portals, and stores it in a database.

[0778] Input: Requests for external information from web APIs or data feeds.

[0779] Output: External factor information stored in a database.

[0780] Step 5: Analysis of policy information and external factor information by the server

[0781] The server analyzes the accumulated policy information and external factor information using machine learning algorithms (e.g., random forest, linear regression), and evaluates the impact of each policy factor.

[0782] Input: Policy information and external factor information stored in the database.

[0783] Output: Analyzed data and results (e.g., effectiveness assessment).

[0784] Step 6: Emotion analysis using the emotion engine

[0785] The server uses an emotion engine for policy information and feedback information. For example, it uses natural language processing (NLP) technology to analyze emotions from user input and recognize emotional states such as satisfaction, dissatisfaction, and expectation.

[0786] Input: User text input and feedback.

[0787] Output: Analysis results representing the user's emotional state.

[0788] Step 7: Server generates and notifies analysis results

[0789] The server generates a detailed report based on the analysis results and notifies users in each department. For example, a report such as "The effectiveness of the TV commercial campaign was 20% higher than usual, but some users expressed dissatisfaction" can be compiled and sent to users via an AI chatbot.

[0790] Input: Analysis results from machine learning and sentiment engine.

[0791] Output: Detailed report and user notification.

[0792] Step 8: User feedback

[0793] The user inputs feedback based on the analysis results into the AI ​​chatbot, for example, by writing specific comments such as, "We also implemented a store-specific promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected."

[0794] Input: User feedback.

[0795] Output: Feedback information stored on the device.

[0796] Step 9: Sending feedback information from the device to the server

[0797] The device sends the user's feedback information to the server through the AI ​​chatbot, which then formats the feedback information appropriately and sends it to the server.

[0798] Input: Feedback information stored on the device.

[0799] Output: Feedback information sent to the server.

[0800] Step 10: Server accumulates and re-evaluates feedback information

[0801] The server stores the received feedback information in a database, then performs a comprehensive analysis including the feedback information, and uses the results to help improve future measures.

[0802] Input: The feedback information sent to the server.

[0803] Output: Feedback information stored in a database.

[0804] Step 11: Server creates forecast of future measures

[0805] The server predicts the effectiveness of future campaigns based on accumulated campaign information, external factor information, feedback information, and sentiment analysis results. For example, it generates a prediction such as, "A target audience rating of 15% for the next campaign is appropriate. Taking into account weather forecasts, audience ratings in the Kanto region may be affected," and notifies the device.

[0806] Input: Policy information, external factor information, feedback information, and sentiment analysis results stored in the database.

[0807] Output: Predicted results of future actions notified to the user.

[0808] (Application example 2)

[0809] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0810] Conventional policy evaluation systems only quantitatively evaluate the effectiveness of policies, and do not comprehensively evaluate them, taking into account customer sentiment or external factors. This makes it difficult to accurately measure the effectiveness or predict future policies, making it difficult to improve customer satisfaction or formulate appropriate policy plans.

[0811] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0812] In this invention, the server includes means for collecting policy information from users in each department, means for storing the collected policy information in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information, means for notifying users in each department of the analysis results, emotion analysis means for analyzing user satisfaction and dissatisfaction, means for making a comprehensive evaluation based on the policy information, external factor information, and emotion information, and means for notifying users of the policy analysis results and prediction results to use in policy planning. This enables highly accurate effect measurement and future policy prediction taking into account customer emotions and external factors.

[0813] "Policy information" refers to detailed data and information about specific promotions, campaigns, events, etc. that have been implemented.

[0814] A "database" is an information management system for systematically storing and managing various collected information.

[0815] "External factor information" refers to information about external environmental variables that affect the effectiveness of policies, such as weather, economic data, and social trends.

[0816] "Analysis means" refers to a method or process for evaluating and diagnosing collected and accumulated data using techniques such as statistical analysis and machine learning.

[0817] "Notification means" refers to the communication and notification method used to inform users of analysis results and prediction data.

[0818] "Emotion analysis means" is a technology that automatically analyzes emotions such as satisfaction, dissatisfaction, and expectations from user feedback and comments.

[0819] "Comprehensive evaluation" is a process of centrally evaluating multiple data, such as policy information, external factor information, and emotional information, to determine the overall effectiveness.

[0820] "Policy planning" refers to the specific planning of future promotions and campaigns.

[0821] A "machine learning algorithm" is a mathematical technique that learns from data, discovers patterns, and makes future predictions and classifications.

[0822] The system of the present invention uses an AI chatbot to collect policy information and evaluate its effectiveness. The main components of this system are a server, a terminal, and a user. The server collects, stores, and analyzes data, and notifies the user of the results via the terminal.

[0823] 1. Overview of the entire system

[0824] Users input policy information into their devices. This information is sent to the server via an AI chatbot. The server stores the policy information in a database and periodically collects external factor information. The server also performs sentiment analysis of user feedback and comprehensively evaluates the effectiveness of the policy.

[0825] 2. Collection and accumulation of policy information

[0826] The user inputs specific information about the campaign into the device, such as, "We've launched a new promotion. The target achievement rate is 15%, and the actual result is 18%." The input information is sent to the server via an AI chatbot. The server accumulates this information in a database and saves it for future analysis.

[0827] 3. Collecting information on external factors

[0828] The server periodically obtains information on external factors such as weather and economic data via a Web API and stores it in a database, allowing external factors that affect the effectiveness of measures to be taken into account.

[0829] 4. Emotion analysis

[0830] The AI ​​chatbot collects the feedback provided by the user, and the server analyzes the feedback using a sentiment analysis engine. For example, if a user types, "This promotion did not go as expected," the sentiment analysis engine will evaluate this feedback as "dissatisfied."

[0831] 5. Data Analysis

[0832] The server uses a machine learning algorithm to analyze the accumulated campaign information and external factor information. This allows it to evaluate the impact of each campaign factor. It also integrates the results of the sentiment analysis engine to provide a comprehensive evaluation that includes user sentiment. For example, it generates a detailed report that states, "The effectiveness of the promotion was 20% higher than usual, but user sentiment analysis indicates that some users are dissatisfied."

[0833] 6. Notification and sharing of analysis results

[0834] The server notifies users in each department of the analysis results via an AI chatbot. Users can then receive these results using their devices and provide feedback on the effectiveness of the measures.

[0835] 7. Feedback and Reassessment

[0836] Feedback information provided by users is also sent to the server through the AI ​​chatbot, including details such as, "Some products sold out due to a new promotion, but overall customer satisfaction was low." The server stores this feedback information in a database and reflects it in future measures.

[0837] 8. Forecasting future measures

[0838] The server uses the accumulated data, user emotional information, and machine learning algorithms to predict the effectiveness of the next campaign. For example, it generates a prediction such as, "The next promotion is expected to achieve a 20% target. Also, according to the weather forecast, continued rain may affect sales." The device notifies the user of this prediction via an AI chatbot, which helps with campaign planning.

[0839] Specific examples

[0840] For example, a physical store holds a "New Year's sale" and inputs that information into an AI chatbot. The server stores this information in a database, while also collecting weather and economic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign, including the impact of heavy rain on sales. The emotion engine also recognizes that there were many complaints from customers based on their feedback. Finally, the server notifies the store operator of the analysis results and provides predictions to be used as a reference for planning future campaigns.

[0841] Prompt Sentence Examples

[0842] "Please enter information about your new campaign. Include specifics, timeframe, goals, and achievements."

[0843] "Please enter customer feedback. For example, 'I was satisfied with the campaign' or 'I didn't feel it was effective.'"

[0844] In this way, users can comprehensively evaluate the effectiveness of measures taken in running a physical store and more accurately plan future measures.

[0845] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0846] Step 1:

[0847] The user inputs the policy information into the terminal.

[0848] Specific operation: The user uses a smartphone application to input detailed information about the campaign (e.g., promotion content, period, target value, and actual value). The input information is sent to the server via an AI chatbot.

[0849] Input: Policy information (e.g. promotion details, goal achievement rate, results, etc.)

[0850] Output: Policy information sent to the server via the AI ​​chatbot

[0851] Step 2:

[0852] The server stores the policy information in a database.

[0853] Specific operation: The server stores the received policy information in a database and manages it for future analysis.

[0854] Input: Policy information sent from the AI ​​chatbot

[0855] Output: Policy information stored in the database

[0856] Step 3:

[0857] The server periodically acquires information about external factors and stores it in a database.

[0858] Specific operation: The server periodically obtains weather information and economic data using a Web API and stores this external factor information in a database.

[0859] Input: External information (e.g., weather information via Web API, economic data)

[0860] Output: External factor information stored in the database

[0861] Step 4:

[0862] Users enter their feedback into an AI chatbot.

[0863] Specific operation: The user uses the device to input feedback about the campaign or promotion, for example, inputting a comment such as "This promotion did not meet my expectations."

[0864] Input: Feedback information

[0865] Output: Feedback information sent to the server via the AI ​​chatbot

[0866] Step 5:

[0867] The server analyzes the feedback using a sentiment analysis engine.

[0868] Specific operation: The server passes the feedback information to the emotion analysis engine, and extracts the user's emotions (e.g., satisfaction, dissatisfaction, expectation, etc.) as the analysis result.

[0869] Input: Feedback information

[0870] Output: Parsed emotion information

[0871] Step 6:

[0872] The server performs a comprehensive evaluation based on policy information, external factor information, and emotion information.

[0873] Specific operation: The server uses a machine learning algorithm to analyze policy information and external factor information, and also integrates the results of sentiment analysis to evaluate the overall effectiveness of the policy.

[0874] Input: Policy information, external factor information, emotion information

[0875] Output: Comprehensive evaluation results (e.g., detailed report)

[0876] Step 7:

[0877] The server notifies users in each department of the analysis results via an AI chatbot.

[0878] Specific operation: The server notifies the user of the overall evaluation results in real time and provides a detailed report via an AI chatbot.

[0879] Input: Overall evaluation result

[0880] Output: Reports to be sent to users in each department

[0881] Step 8:

[0882] The feedback information provided by the user is sent to the server via the AI ​​chatbot.

[0883] Specific operation: Users enter feedback on campaign results and areas for improvement into the application, which is then sent to the server via an AI chatbot.

[0884] Input: User feedback information

[0885] Output: Feedback information stored in a database

[0886] Step 9:

[0887] The server predicts the effectiveness of the next measure.

[0888] Specific operation: The server uses accumulated policy information, external factor information, emotional information, and machine learning algorithms to predict the effectiveness of the next policy.

[0889] Input: Policy information, external factor information, emotion information

[0890] Output: Prediction of next policy effect

[0891] Step 10:

[0892] The server notifies the user of the prediction results through an AI chatbot.

[0893] Specific operation: The server sends the prediction results to the user via the AI ​​chatbot, and uses them as a reference for planning the next policy.

[0894] Input: Prediction result

[0895] Output: Prediction results notified to the user

[0896] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0897] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0898] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0899] [Third embodiment]

[0900] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0901] 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.

[0902] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[0903] 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.

[0904] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0905] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0906] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0907] 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.

[0908] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0909] 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.

[0910] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0911] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0912] 1. Overview of the entire system

[0913] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system operates in cooperation with the server, terminals, and users, promoting information sharing between departments and conducting analysis that takes external factors into account.

[0914] 2. Collection and accumulation of policy information

[0915] The user uses a device to input campaign information into the AI ​​chatbot. For example, they can enter details such as, "We have launched a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0916] The device sends this policy information to the server via an AI chatbot.

[0917] The server stores the received policy information in a database.

[0918] 3. Collecting information on external factors

[0919] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[0920] The acquired information on external factors is stored in a database and integrated with other policy information.

[0921] 4. Data Analysis

[0922] The server uses machine learning algorithms to analyze the accumulated information on measures and external factors. The purpose of the analysis is to evaluate the true effectiveness of each measure and clarify how external factors are affecting it.

[0923] For example, the effectiveness of a TV commercial campaign implemented by the marketing department can be evaluated independently from the impact of heavy rain that occurred at the same time.

[0924] 5. Notification and sharing of analysis results

[0925] The server notifies users in each department of the results of the analysis via an AI chatbot, providing detailed reports such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas."

[0926] Users can use their devices to receive these analysis results and provide feedback on the effectiveness of the measures.

[0927] 6. Feedback and Reassessment

[0928] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including details such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%."

[0929] The server stores this feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[0930] 7. Predicting future measures

[0931] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future measures.

[0932] For example, it is possible to generate prediction results such as, "A target audience rating of 15% for the next campaign is reasonable. Also, taking into account weather forecasts, the audience rating in the Kanto region may be affected."

[0933] The device will notify relevant users of the prediction results via an AI chatbot, helping them plan their actions.

[0934] Specific examples

[0935] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses machine learning algorithms to analyze the effectiveness of the campaign, including the impact of heavy rain on viewership. Finally, the server notifies the marketing department of the results of the analysis and provides a forecast to help plan future campaigns.

[0936] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation while taking external factors into account.

[0937] The processing flow will be explained below.

[0938] Step 1:

[0939] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[0940] Step 2:

[0941] The terminal sends the policy information entered by the user to the server via an AI chatbot.

[0942] Step 3:

[0943] The server stores the received policy information in a database.

[0944] Step 4:

[0945] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[0946] Step 5:

[0947] The server stores the acquired external factor information in a database.

[0948] Step 6:

[0949] The server uses machine learning algorithms to analyze the accumulated policy information and external factor information, and evaluates the impact of each policy factor.

[0950] Step 7:

[0951] The server notifies users in each department of the analysis results via an AI chatbot, generating a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas."

[0952] Step 8:

[0953] The user receives notifications from the AI ​​chatbot on their device, checks the analysis results, and provides feedback if necessary.

[0954] Step 9:

[0955] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including detailed information such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%."

[0956] Step 10:

[0957] The server stores the received feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[0958] Step 11:

[0959] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future measures.

[0960] Step 12:

[0961] The server notifies users in each department of the results of the predictions via an AI chatbot, providing, for example, a prediction such as, "A target audience rating of 15% for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected."

[0962] Step 13:

[0963] Users can use their devices to receive the forecast results and reflect them in their next action plan. Through this process, collaboration between departments is strengthened, and highly accurate effect measurement and forecast creation are achieved while taking external factors into account.

[0964] Example 1

[0965] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0966] With conventional policy effectiveness measurement systems, it was difficult to centrally collect and analyze policy information from each department and information on external factors, and to effectively communicate and share the results. Another problem was the low accuracy of predicting the next policy plan using policy feedback information. This resulted in a decrease in the accuracy of policy effectiveness measurement and decision-making, making it difficult to formulate effective policy plans.

[0967] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0968] In this invention, the server includes means for collecting policy information from users in each department and storing it in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information using a machine learning algorithm, means for notifying users in each department of the analysis results, means for collecting feedback from users in each department, means for storing the collected feedback information in the database, means for reevaluating based on the feedback information, means for predicting the effectiveness of the next policy, and means for notifying users in each department of the prediction results. This makes it possible to comprehensively analyze policy information and external factor information and utilize feedback to measure effectiveness and predict future policies with high accuracy.

[0969] "Policy information" refers to data on the plans and activities implemented by each department.

[0970] "Departmental users" refers to people who work in different departments of a company or organization.

[0971] "Terminal" means an electronic device used by a user to input and view information.

[0972] A "database" is a system for organizing and storing information.

[0973] "External factor information" refers to external conditions and data that affect policies, such as weather information and economic data.

[0974] A "server" is a central system for receiving, storing, and analyzing information from users.

[0975] A "machine learning algorithm" is a program that finds useful patterns and predictions from large amounts of data.

[0976] "Analysis Results" means analytical data obtained using machine learning algorithms or other means.

[0977] "Feedback information" refers to ratings and additional information provided by users.

[0978] "Reevaluation" refers to additional analysis based on newly collected information or feedback.

[0979] "Predicted results" refers to data that predicts the effects and results of future measures.

[0980] This invention is a system that uses AI chatbots to automatically collect, store, and analyze information about each department's measures and their effects. This system operates in cooperation with a server, terminals, and users.

[0981] Specific system configuration

[0982] 1. A terminal is a device through which a user inputs policy information. Specifically, this includes PCs, tablets, smartphones, etc.

[0983] 2. The server is a computer system that stores received policy information, collects external factor information, and analyzes the data using machine learning algorithms. The database uses a relational database such as MySQL or PostgreSQL. Machine learning uses Python's pandas library, scikit-learn, TensorFlow, etc.

[0984] 3. Users are people working in various departments, such as marketing and sales. They can input policy information through the AI ​​chatbot and receive analysis and prediction results.

[0985] Data collection and storage

[0986] The user launches the AI ​​chatbot on their device and inputs information about the campaign. For example, they might input information like, "We've launched a new TV commercial campaign. Our target audience rating is 10%, and the actual result is 12%." The device then sends the input campaign information to the server, which then stores this information in a database.

[0987] Gathering information on external factors

[0988] The server periodically calls the Web API to obtain external factor information. Specifically, it obtains weather information and macroeconomic data from the weather information API and economic data API, and stores this in a database.

[0989] Data analysis

[0990] The server retrieves information about campaigns and external factors from the database and performs analysis using machine learning algorithms. The purpose of the analysis is to evaluate the true effectiveness of each campaign and clarify the influence of external factors. For example, to evaluate the effectiveness of a TV commercial campaign, a regression analysis is performed to isolate the impact of heavy rain on viewer ratings.

[0991] Communicating and sharing analysis results

[0992] The server generates a report of the analysis results and notifies the user through an AI chatbot. For example, the report may include, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas." The user can view the report on their device and provide feedback.

[0993] Feedback and Reassessment

[0994] The user sends feedback information to the server through the AI ​​chatbot. For example, they might send information like, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%." The server then stores this feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[0995] Predicting future measures

[0996] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate, and taking into account weather forecasts, audience ratings may be affected in the Kanto region." The device then notifies the user of this prediction via an AI chatbot.

[0997] Examples of specific examples and prompts

[0998] For example, a marketing department launches a new TV commercial campaign, and users input that information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses machine learning algorithms to analyze the effectiveness of the campaign and generate analysis results, including the impact of heavy rain on viewership. Finally, the server notifies the marketing department of the analysis results and provides predictions that can be used as a reference for planning future campaigns.

[0999] An example of a prompt sentence would be, "We have launched a new TV commercial campaign. The target viewership rate was 10%, and the actual rate was 12%. There was some fluctuation in viewership rate due to heavy rain. Please tell us your predictions for the next campaign." The system will then respond to this.

[1000] As described above, this system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation that takes external factors into account.

[1001] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1002] Step 1:

[1003] The user launches the AI ​​chatbot on their device and inputs policy information.

[1004] Input: Information about your new TV ad campaign (e.g., "We launched a new TV ad campaign. Our target viewership was 10%, and our actual result was 12%)

[1005] Output: Request data including policy information

[1006] Specific operation: The user enters policy information in text format into the AI ​​chatbot on the device and clicks the input button.

[1007] Step 2:

[1008] The terminal transmits the input policy information to the server.

[1009] Input: Policy information entered by the user

[1010] Output: Policy information sent to the server

[1011] Specific operation: The terminal sends the text entered by the user to the server via the HTTPS protocol.

[1012] Step 3:

[1013] The server stores the received policy information in a database.

[1014] Input: Submitted policy information

[1015] Output: Policy information stored in the database

[1016] Specific operation: The server stores policy information as records in a database such as MySQL or PostgreSQL.

[1017] Step 4:

[1018] The server periodically acquires the external factor information and stores it in a database.

[1019] Input: Request to get external factor information

[1020] Output: External factor information stored in the database

[1021] Specific operation: The server periodically calls the weather information API and economic data API to obtain and store weather information, macroeconomic data, etc.

[1022] Step 5:

[1023] The server analyzes the accumulated policy information and external factor information.

[1024] Input: Policy information and external factor information stored in the database

[1025] Output: Analysis results

[1026] Specific operation: The server retrieves the necessary information from the database using SQL queries and analyzes it using machine learning algorithms such as Python's pandas library, scikit-learn, and TensorFlow.

[1027] Step 6:

[1028] The server notifies the users in each department of the analysis results.

[1029] Input: Analysis results

[1030] Output: A message to inform the user

[1031] Specific operation: The server notifies the user of the analysis results through an AI chatbot and generates a detailed analysis report.

[1032] Step 7:

[1033] The user inputs feedback information and sends it to the server.

[1034] Input: Feedback information (e.g., "We also implemented a unique store promotion, which resulted in a 10% increase in overall sales.")

[1035] Output: Feedback information sent to the server

[1036] Specific actions: The user uses the device to enter feedback information into the AI ​​chatbot and clicks the send button.

[1037] Step 8:

[1038] The server stores the received feedback information in a database.

[1039] Input: Feedback information

[1040] Output: Feedback information stored in a database

[1041] Specific operation: The server stores the feedback information as a record in the database.

[1042] Step 9:

[1043] The server will reassess based on the accumulated data and feedback information.

[1044] Input: Policy information, external factors, feedback information

[1045] Output: Reevaluation results

[1046] Specific operation: The server performs analysis again using all data collected so far and updates the analysis results.

[1047] Step 10:

[1048] The server predicts the effect of the next measure and generates a predicted result.

[1049] Input: Stored data and machine learning algorithms

[1050] Output: Prediction result of next action

[1051] Specific operation: The server operates a model to predict the effectiveness of future measures based on past data and analysis results, and generates prediction results.

[1052] Step 11:

[1053] The terminal notifies the user of the prediction result.

[1054] Input: Prediction result

[1055] Output: A message to inform the user

[1056] Specific operation: Receives the prediction results sent from the server and notifies the user through the AI ​​chatbot.

[1057] (Application example 1)

[1058] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1059] With conventional systems, it was difficult to accurately evaluate the effectiveness of measures implemented by each department and obtain appropriate feedback. It was also difficult to make accurate predictions that took external factors into account, leading to uncertainty about the next measure plan. Furthermore, collecting measure information and feedback from physical stores was cumbersome, which tended to delay integrated analysis.

[1060] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1061] In this invention, the server includes means for collecting policy information from users in each department and storing it in a database, means for periodically acquiring and storing external factor information, means for analyzing the collected policy information and external factor information using a machine learning algorithm, means for notifying users in each department of the analysis results and a prediction of the effectiveness of the next policy to help them plan the policy, means for users of the physical store to input policy information via a smart device and collect feedback, and means for generating accurate prediction results based on the acquired external factor information and providing them to users. This makes it possible to accurately evaluate the effectiveness of policies in each department and provide highly accurate predictions that take external factors into account.

[1062] "Users in each department" refers to employees and staff members who belong to different departments of a company or organization.

[1063] "Policy information" refers to detailed information on specific initiatives, campaigns, and promotions implemented by each department.

[1064] "Database" refers to an electronic recording system for storing and managing policy information and external factor information.

[1065] "External factor information" refers to external data that may affect the effectiveness of policies, such as weather forecasts and economic indicators.

[1066] A "machine learning algorithm" refers to a mathematical technique that allows computers to learn patterns from data and make predictions and analyses.

[1067] "Analysis results" refers to the output after analyzing policy information and external factor information using a machine learning algorithm.

[1068] "Smart devices" refers to highly functional mobile devices that can connect to the Internet, such as smartphones and tablets.

[1069] "Feedback" refers to evaluations and comments regarding the results and effectiveness of measures provided by users.

[1070] "Prediction results" refer to the results of predicting the effects of future measures using machine learning algorithms.

[1071] "User" refers to the operators, staff, or customers of physical stores who use the system.

[1072] "Brick and mortar store" refers to a physical store where transactions are conducted directly with customers face-to-face.

[1073] This invention is a system that uses AI chatbots to effectively collect, analyze, and predict policy information. This system operates in cooperation with servers, terminals, and users, enabling accurate collection and analysis of policy information.

[1074] First, the user inputs information about the store's initiatives via a smart device (smartphone or tablet). For example, detailed information such as "Sales during the weekend sale reached 120% of the target. Due to the fine weather, customer traffic increased" can be entered into the chatbot. This allows the context and results of the initiatives to be recorded in detail.

[1075] Policy information sent from smart devices is transferred to the server and stored in a database. The server periodically obtains external factor information (e.g., weather forecasts and economic indicators) from Web APIs and other data sources, and stores this information in the database as well.

[1076] The server analyzes the collected information on measures and external factors using a machine learning algorithm (e.g., Random Forest Regressor). This analysis evaluates the true effect of each measure and clarifies the influence of external factors. For example, it can analyze the effect of a weekend sale on sunny weather separately from other factors.

[1077] The analysis results are communicated to relevant users via an AI chatbot. For example, a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas." This allows users to provide feedback on the effectiveness of the campaign and use it to plan the next campaign.

[1078] Furthermore, the server uses the accumulated data and machine learning algorithms to predict the effectiveness of the next campaign. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected." The device then notifies the relevant user of this prediction via an AI chatbot, which helps with campaign planning.

[1079] As a specific example, by entering a prompt such as "What is a reasonable sales target for the weekend sale? The weather forecast says it's going to rain" into the chatbot, the system will instantly generate and provide a prediction for the next initiative.

[1080] This system efficiently collects information on measures taken by physical stores and enables highly accurate analysis and predictions that take external factors into account, allowing for accurate evaluation of the effectiveness of measures and the optimization of future measures.

[1081] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1082] Step 1:

[1083] Input: A user inputs campaign information using a smart device (e.g., "Sales from the weekend sale reached 120% of the target. The sunny weather led to an increase in customer traffic.").

[1084] Processing: The device sends this policy information to the server via an AI chatbot.

[1085] Output: The policy information is sent to the server and recorded in the database.

[1086] Step 2:

[1087] Input: Policy information submitted by the user.

[1088] Processing: The server periodically obtains external information (e.g., weather forecasts, economic indicators) using Web APIs and data feeds.

[1089] Output: The latest external factor information is stored on the server.

[1090] Step 3:

[1091] Input: Policy information and external factor information are stored in the database.

[1092] Processing: The server analyzes the policy information and external factor information using a machine learning algorithm (e.g., RandomForestRegressor), thereby evaluating the true effectiveness of each policy and the influence of external factors.

[1093] Output: The analysis results are generated (e.g., "The effectiveness of the weekend sale was 20% higher than usual. The sunny weather led to an increase in customer traffic.").

[1094] Step 4:

[1095] Input: Analysis results.

[1096] Processing: The server notifies the user of the analysis results via an AI chatbot.

[1097] Output: A detailed report is displayed on the user's device (e.g., "The effectiveness of our weekend sale was 20% higher than usual. The sunny weather led to an increase in foot traffic.").

[1098] Step 5:

[1099] Input: User feedback (e.g., "We'll further validate the results of this weekend's sale. We'll also add regional sales data.").

[1100] Processing: The AI ​​chatbot receives feedback from the user and sends it to the server.

[1101] Output: Feedback information is stored in a database and used for future analysis and prediction.

[1102] Step 6:

[1103] Input: Accumulated data and feedback information.

[1104] Processing: The server uses machine learning algorithms to predict the effectiveness of the next initiative (e.g., prompt: "What is a reasonable sales target for the next weekend sale? The weather forecast says it's going to rain.").

[1105] Output: A prediction result is generated (e.g., "The target sales for the next weekend sale are expected to increase by 10%. However, rain may affect this.").

[1106] Step 7:

[1107] Input: Prediction results.

[1108] Processing: The server notifies the user of the prediction results through an AI chatbot.

[1109] Output: The prediction results are displayed on the user's device and can be used to plan future measures.

[1110] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1111] 1. Overview of the entire system

[1112] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system involves servers, terminals, and users working together to promote information sharing between departments and perform analysis that takes into account external factors and user emotions.

[1113] 2. Collection and accumulation of policy information

[1114] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[1115] The device sends this policy information to the server via an AI chatbot.

[1116] The server stores the received policy information in a database.

[1117] 3. Collecting information on external factors

[1118] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[1119] The acquired information on external factors is stored in a database and integrated with other policy information.

[1120] 4. Introducing the Emotion Engine

[1121] The server embeds an emotion engine into the AI ​​chatbot, which analyzes the user's input information and feedback and recognizes their emotional state (e.g., satisfaction, dissatisfaction, expectation, etc.).

[1122] For example, if a user types, "This campaign didn't work as well as expected," the emotion engine will recognize the emotion of dissatisfaction.

[1123] 5. Data Analysis

[1124] The server uses machine learning algorithms to analyze the accumulated policy information and external factor information, and evaluates the impact of each policy factor.

[1125] In addition, the analysis results of the emotion engine are also integrated to provide a comprehensive evaluation that includes the user's emotions.

[1126] For example, a detailed report can be generated such as, "The effectiveness of the TV commercial campaign was 20% higher than usual, but user sentiment analysis revealed that some users were dissatisfied."

[1127] 6. Notification and sharing of analysis results

[1128] The server notifies users in each department of the analysis results via an AI chatbot.

[1129] Users can use their devices to receive these analysis results and provide feedback on the effectiveness of the measures.

[1130] 7. Feedback and Reassessment

[1131] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including details such as, "We also implemented a store-specific promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected."

[1132] The server stores this feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[1133] 8. Forecasting future measures

[1134] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future measures.

[1135] For example, the system generates predictions such as, "A target audience rating of 15% for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected. Furthermore, previous measures resulted in low satisfaction among some users, so it is recommended that you take measures to improve the situation."

[1136] The device will notify relevant users of the prediction results via an AI chatbot, helping them plan their actions.

[1137] Specific examples

[1138] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign and includes the impact of heavy rain on viewership. The emotion engine also recognizes that there were many complaints from users' feedback. Finally, the server notifies the marketing department of the results of the analysis and provides predictions to be used as a reference for planning future campaigns.

[1139] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation, taking into account external factors and user emotions.

[1140] The processing flow will be explained below.

[1141] Step 1:

[1142] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[1143] Step 2:

[1144] The device sends the input policy information to the server via an AI chatbot. This information includes the policy's purpose, means, implementation period, target values, and actual results.

[1145] Step 3:

[1146] The server stores the received policy information in a database, checking the consistency of the input data and converting the data format.

[1147] Step 4:

[1148] The server periodically obtains external information such as weather and macroeconomic data from web APIs and data feeds, and stores this information in a database along with policy information.

[1149] Step 5:

[1150] The server uses an emotion engine to analyze the user's input information and feedback and recognize their emotional state. For example, if a user inputs "This campaign did not have the expected effect," the emotion engine will recognize the emotion as dissatisfied.

[1151] Step 6:

[1152] The server uses a machine learning algorithm to analyze the accumulated information on measures, external factors, and the analysis results of the emotion engine, and evaluates the effectiveness of each measure and how external factors and user emotions have affected its effectiveness.

[1153] Step 7:

[1154] The server notifies users in each department of the analysis results via an AI chatbot, generating a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual, but there was dissatisfaction feedback from multiple users."

[1155] Step 8:

[1156] The user receives notifications from the AI ​​chatbot on their device, checks the analysis results, and provides their own feelings and additional feedback information (e.g., "We also implemented a unique store promotion at the same time, which increased overall sales by 10%.").

[1157] Step 9:

[1158] The device sends the feedback information provided by the user to the server via an AI chatbot.

[1159] Step 10:

[1160] The server stores the received feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[1161] Step 11:

[1162] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates predictions such as, "A 15% target viewer rating is appropriate for the next campaign. Also, previous campaigns have resulted in low satisfaction among some users, so it is recommended that you take measures to improve them."

[1163] Step 12:

[1164] The server notifies the relevant users of the prediction results through an AI chatbot.

[1165] Step 13:

[1166] Users can use their devices to receive the prediction results and reflect them in their next action plan. Through this process, collaboration between departments is strengthened, and highly accurate effect measurement and forecast creation are achieved by taking into account external factors and user sentiment.

[1167] Example 2

[1168] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1169] In today's business environment, it is extremely important for each department to implement measures and accurately evaluate their effectiveness. However, in conventional systems, the collection and analysis of measure information was done manually, which was time-consuming and costly, and the accuracy of the evaluation was limited. Furthermore, it was not possible to take external factors or user sentiment into account, making it difficult to accurately grasp the effectiveness of measures. Furthermore, there were few ways to predict future measure effects, leading to high uncertainty when planning the next measure. This has created a demand for an accurate and efficient system for comprehensive effect measurement and forecast creation.

[1170] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting policy information from users in each department, means for storing the collected policy information in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information, means for notifying users in each department of the analysis results, means for analyzing user emotions, means for integrating the emotion analysis results into policy information analysis, means for collecting user feedback information and storing it in the database, and means for predicting future policies and notifying users in each department of the prediction results. This enables an integrated analysis of policy information and external factors, making it possible to achieve highly accurate effect evaluation and future policy forecasting that also takes user emotional information into consideration.

[1171] "Policy information" refers to data and results regarding specific policies implemented by each department.

[1172] "External factor information" refers to data related to the external environment, such as weather information and macroeconomic data, that affect the effectiveness of policies.

[1173] "Database" refers to an information management system for organizing and storing collected policy information and external factor information.

[1174] "Analysis means" refers to the techniques and processes for analyzing accumulated data and evaluating the effectiveness of measures.

[1175] "Notification means" refers to the technology and process for communicating analysis and prediction results to users in each department.

[1176] "Sentiment analysis" refers to the techniques and processes of extracting and analyzing a user's emotional state from input information.

[1177] "Feedback information" refers to evaluation data provided after a measure is implemented, such as users' opinions and satisfaction with the measure, and areas for improvement.

[1178] "Machine learning algorithms" refers to statistical methods and artificial intelligence techniques used for data analysis and prediction.

[1179] "Effectiveness forecasting" refers to the technology and process of predicting future policy effects based on past and current data.

[1180] 1. Overview of the entire system

[1181] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system involves servers, terminals, and users working together to promote information sharing between departments and perform analysis that takes into account external factors and user emotions.

[1182] 2. Collection and accumulation of policy information

[1183] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target audience rating is 10%, and the actual result is 12%." The device then sends this campaign information to the server via the AI ​​chatbot. The server then stores the received campaign information in a database.

[1184] 3. Collecting information on external factors

[1185] The server periodically obtains external factor information such as weather information and macroeconomic data from web APIs and data feeds. The obtained external factor information is stored in a database and integrated with other policy information.

[1186] 4. Introducing the Emotion Engine

[1187] The server incorporates an emotion engine into the AI ​​chatbot. This emotion engine analyzes the user's input information and feedback and recognizes their emotional state (e.g., satisfaction, dissatisfaction, expectation, etc.). For example, if a user inputs, "This campaign did not have the desired effect," the emotion engine recognizes the emotion as dissatisfaction.

[1188] 5. Data Analysis

[1189] The server uses a machine learning algorithm to analyze the accumulated campaign information and external factor information. This evaluates the degree of impact of each campaign factor. It also integrates the analysis results of the emotion engine to provide a comprehensive evaluation that includes user emotions. For example, it generates a detailed report that states, "The effectiveness of the TV commercial campaign was 20% higher than usual, but some users expressed dissatisfaction."

[1190] 6. Notification and sharing of analysis results

[1191] The server notifies users in each department of the analysis results via an AI chatbot. Users can then receive these results using their devices and provide feedback on the effectiveness of the measures.

[1192] 7. Feedback and Reassessment

[1193] Feedback information provided by users is also sent to the server via the AI ​​chatbot. For example, it may include details such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected." The server stores this feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[1194] 8. Forecasting future measures

[1195] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected. Furthermore, previous campaigns have resulted in low satisfaction among some users, so it is recommended that improvements be made." The device then notifies relevant users of the prediction results via an AI chatbot, helping them plan campaigns.

[1196] Specific examples

[1197] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign and includes the impact of heavy rain on viewership. The emotion engine also recognizes that there were many complaints from users' feedback. Finally, the server notifies the marketing department of the results of the analysis and provides predictions to be used as a reference for planning future campaigns.

[1198] Below are some specific examples of prompt sentences that can be input to the generative AI model in this system.

[1199] "We ran a new TV commercial campaign. Our target viewer rating was 10%, and the actual result was 12%. There were many days of heavy rain during the campaign period, which is thought to have affected the viewer rating. We have received some dissatisfaction from users in their feedback. Please suggest improvements for the next campaign based on your analysis."

[1200] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation, taking into account external factors and user emotions.

[1201] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1202] Step 1: User inputs policy information

[1203] Users input information about their initiatives into the AI ​​chatbot using their own devices. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%." This input is structured in text format.

[1204] Input: The user inputs the policy information in text format.

[1205] Output: The policy information entered into the terminal is saved.

[1206] Step 2: Sending policy information from the device to the server

[1207] The device sends the input policy information to the server via an AI chatbot, where it is properly formatted and converted into a usable form.

[1208] Input: Policy information stored on the device.

[1209] Output: Policy information is sent to the server via the AI ​​chatbot.

[1210] Step 3: Storing policy information on the server

[1211] The server stores the received policy information in a database. When the server receives the information, it stores it in the appropriate table in the database and creates an index to enable fast searches.

[1212] Input: Policy information sent to the server.

[1213] Output: Policy information stored in a database.

[1214] Step 4: Server collects external information

[1215] The server periodically retrieves external information such as weather information and macroeconomic data from web APIs and data feeds, for example, from the OpenWeatherMap API or government economic data portals, and stores it in a database.

[1216] Input: Requests for external information from web APIs or data feeds.

[1217] Output: External factor information stored in a database.

[1218] Step 5: Analysis of policy information and external factor information by the server

[1219] The server analyzes the accumulated policy information and external factor information using machine learning algorithms (e.g., random forest, linear regression), and evaluates the impact of each policy factor.

[1220] Input: Policy information and external factor information stored in the database.

[1221] Output: Analyzed data and results (e.g., effectiveness assessment).

[1222] Step 6: Emotion analysis using the emotion engine

[1223] The server uses an emotion engine for policy information and feedback information. For example, it uses natural language processing (NLP) technology to analyze emotions from user input and recognize emotional states such as satisfaction, dissatisfaction, and expectation.

[1224] Input: User text input and feedback.

[1225] Output: Analysis results representing the user's emotional state.

[1226] Step 7: Server generates and notifies analysis results

[1227] The server generates a detailed report based on the analysis results and notifies users in each department. For example, a report such as "The effectiveness of the TV commercial campaign was 20% higher than usual, but some users expressed dissatisfaction" can be compiled and sent to users via an AI chatbot.

[1228] Input: Analysis results from machine learning and sentiment engine.

[1229] Output: Detailed report and user notification.

[1230] Step 8: User feedback

[1231] The user inputs feedback based on the analysis results into the AI ​​chatbot, for example, by writing specific comments such as, "We also implemented a store-specific promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected."

[1232] Input: User feedback.

[1233] Output: Feedback information stored on the device.

[1234] Step 9: Sending feedback information from the device to the server

[1235] The device sends the user's feedback information to the server through the AI ​​chatbot, which then formats the feedback information appropriately and sends it to the server.

[1236] Input: Feedback information stored on the device.

[1237] Output: Feedback information sent to the server.

[1238] Step 10: Server accumulates and re-evaluates feedback information

[1239] The server stores the received feedback information in a database, then performs a comprehensive analysis including the feedback information, and uses the results to help improve future measures.

[1240] Input: The feedback information sent to the server.

[1241] Output: Feedback information stored in a database.

[1242] Step 11: Server creates forecast of future measures

[1243] The server predicts the effectiveness of future campaigns based on accumulated campaign information, external factor information, feedback information, and sentiment analysis results. For example, it generates a prediction such as, "A target audience rating of 15% for the next campaign is appropriate. Taking into account weather forecasts, audience ratings in the Kanto region may be affected," and notifies the device.

[1244] Input: Policy information, external factor information, feedback information, and sentiment analysis results stored in the database.

[1245] Output: Predicted results of future actions notified to the user.

[1246] (Application example 2)

[1247] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1248] Conventional policy evaluation systems only quantitatively evaluate the effectiveness of policies, and do not comprehensively evaluate them, taking into account customer sentiment or external factors. This makes it difficult to accurately measure the effectiveness or predict future policies, making it difficult to improve customer satisfaction or formulate appropriate policy plans.

[1249] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1250] In this invention, the server includes means for collecting policy information from users in each department, means for storing the collected policy information in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information, means for notifying users in each department of the analysis results, emotion analysis means for analyzing user satisfaction and dissatisfaction, means for making a comprehensive evaluation based on the policy information, external factor information, and emotion information, and means for notifying users of the policy analysis results and prediction results to use in policy planning. This enables highly accurate effect measurement and future policy prediction taking into account customer emotions and external factors.

[1251] "Policy information" refers to detailed data and information about specific promotions, campaigns, events, etc. that have been implemented.

[1252] A "database" is an information management system for systematically storing and managing various collected information.

[1253] "External factor information" refers to information about external environmental variables that affect the effectiveness of policies, such as weather, economic data, and social trends.

[1254] "Analysis means" refers to a method or process for evaluating and diagnosing collected and accumulated data using techniques such as statistical analysis and machine learning.

[1255] "Notification means" refers to the communication and notification method used to inform users of analysis results and prediction data.

[1256] "Emotion analysis means" is a technology that automatically analyzes emotions such as satisfaction, dissatisfaction, and expectations from user feedback and comments.

[1257] "Comprehensive evaluation" is a process of centrally evaluating multiple data, such as policy information, external factor information, and emotional information, to determine the overall effectiveness.

[1258] "Policy planning" refers to the specific planning of future promotions and campaigns.

[1259] A "machine learning algorithm" is a mathematical technique that learns from data, discovers patterns, and makes future predictions and classifications.

[1260] The system of the present invention uses an AI chatbot to collect policy information and evaluate its effectiveness. The main components of this system are a server, a terminal, and a user. The server collects, stores, and analyzes data, and notifies the user of the results via the terminal.

[1261] 1. Overview of the entire system

[1262] Users input policy information into their devices. This information is sent to the server via an AI chatbot. The server stores the policy information in a database and periodically collects external factor information. The server also performs sentiment analysis of user feedback and comprehensively evaluates the effectiveness of the policy.

[1263] 2. Collection and accumulation of policy information

[1264] The user inputs specific information about the campaign into the device, such as, "We've launched a new promotion. The target achievement rate is 15%, and the actual result is 18%." The input information is sent to the server via an AI chatbot. The server accumulates this information in a database and saves it for future analysis.

[1265] 3. Collecting information on external factors

[1266] The server periodically obtains information on external factors such as weather and economic data via a Web API and stores it in a database, allowing external factors that affect the effectiveness of measures to be taken into account.

[1267] 4. Emotion analysis

[1268] The AI ​​chatbot collects the feedback provided by the user, and the server analyzes the feedback using a sentiment analysis engine. For example, if a user types, "This promotion did not go as expected," the sentiment analysis engine will evaluate this feedback as "dissatisfied."

[1269] 5. Data Analysis

[1270] The server uses a machine learning algorithm to analyze the accumulated campaign information and external factor information. This allows it to evaluate the impact of each campaign factor. It also integrates the results of the sentiment analysis engine to provide a comprehensive evaluation that includes user sentiment. For example, it generates a detailed report that states, "The effectiveness of the promotion was 20% higher than usual, but user sentiment analysis indicates that some users are dissatisfied."

[1271] 6. Notification and sharing of analysis results

[1272] The server notifies users in each department of the analysis results via an AI chatbot. Users can then receive these results using their devices and provide feedback on the effectiveness of the measures.

[1273] 7. Feedback and Reassessment

[1274] Feedback information provided by users is also sent to the server through the AI ​​chatbot, including details such as, "Some products sold out due to a new promotion, but overall customer satisfaction was low." The server stores this feedback information in a database and reflects it in future measures.

[1275] 8. Forecasting future measures

[1276] The server uses the accumulated data, user emotional information, and machine learning algorithms to predict the effectiveness of the next campaign. For example, it generates a prediction such as, "The next promotion is expected to achieve a 20% target. Also, according to the weather forecast, continued rain may affect sales." The device notifies the user of this prediction via an AI chatbot, which helps with campaign planning.

[1277] Specific examples

[1278] For example, a physical store holds a "New Year's sale" and inputs that information into an AI chatbot. The server stores this information in a database, while also collecting weather and economic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign, including the impact of heavy rain on sales. The emotion engine also recognizes that there were many complaints from customers based on their feedback. Finally, the server notifies the store operator of the analysis results and provides predictions to be used as a reference for planning future campaigns.

[1279] Prompt Sentence Examples

[1280] "Please enter information about your new campaign. Include specifics, timeframe, goals, and achievements."

[1281] "Please enter customer feedback. For example, 'I was satisfied with the campaign' or 'I didn't feel it was effective.'"

[1282] In this way, users can comprehensively evaluate the effectiveness of measures taken in running a physical store and more accurately plan future measures.

[1283] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1284] Step 1:

[1285] The user inputs the policy information into the terminal.

[1286] Specific operation: The user uses a smartphone application to input detailed information about the campaign (e.g., promotion content, period, target value, and actual value). The input information is sent to the server via an AI chatbot.

[1287] Input: Policy information (e.g. promotion details, goal achievement rate, results, etc.)

[1288] Output: Policy information sent to the server via the AI ​​chatbot

[1289] Step 2:

[1290] The server stores the policy information in a database.

[1291] Specific operation: The server stores the received policy information in a database and manages it for future analysis.

[1292] Input: Policy information sent from the AI ​​chatbot

[1293] Output: Policy information stored in the database

[1294] Step 3:

[1295] The server periodically acquires information about external factors and stores it in a database.

[1296] Specific operation: The server periodically obtains weather information and economic data using a Web API and stores this external factor information in a database.

[1297] Input: External information (e.g., weather information via Web API, economic data)

[1298] Output: External factor information stored in the database

[1299] Step 4:

[1300] Users enter their feedback into an AI chatbot.

[1301] Specific operation: The user uses the device to input feedback about the campaign or promotion, for example, inputting a comment such as "This promotion did not meet my expectations."

[1302] Input: Feedback information

[1303] Output: Feedback information sent to the server via the AI ​​chatbot

[1304] Step 5:

[1305] The server analyzes the feedback using a sentiment analysis engine.

[1306] Specific operation: The server passes the feedback information to the emotion analysis engine, and extracts the user's emotions (e.g., satisfaction, dissatisfaction, expectation, etc.) as the analysis result.

[1307] Input: Feedback information

[1308] Output: Parsed emotion information

[1309] Step 6:

[1310] The server performs a comprehensive evaluation based on policy information, external factor information, and emotion information.

[1311] Specific operation: The server uses a machine learning algorithm to analyze policy information and external factor information, and also integrates the results of sentiment analysis to evaluate the overall effectiveness of the policy.

[1312] Input: Policy information, external factor information, emotion information

[1313] Output: Comprehensive evaluation results (e.g., detailed report)

[1314] Step 7:

[1315] The server notifies users in each department of the analysis results via an AI chatbot.

[1316] Specific operation: The server notifies the user of the overall evaluation results in real time and provides a detailed report via an AI chatbot.

[1317] Input: Overall evaluation result

[1318] Output: Reports to be sent to users in each department

[1319] Step 8:

[1320] The feedback information provided by the user is sent to the server via the AI ​​chatbot.

[1321] Specific operation: Users enter feedback on campaign results and areas for improvement into the application, which is then sent to the server via an AI chatbot.

[1322] Input: User feedback information

[1323] Output: Feedback information stored in a database

[1324] Step 9:

[1325] The server predicts the effectiveness of the next measure.

[1326] Specific operation: The server uses accumulated policy information, external factor information, emotional information, and machine learning algorithms to predict the effectiveness of the next policy.

[1327] Input: Policy information, external factor information, emotion information

[1328] Output: Prediction of next policy effect

[1329] Step 10:

[1330] The server notifies the user of the prediction results through an AI chatbot.

[1331] Specific operation: The server sends the prediction results to the user via the AI ​​chatbot, and uses them as a reference for planning the next policy.

[1332] Input: Prediction result

[1333] Output: Prediction results notified to the user

[1334] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1335] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1336] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1337] [Fourth embodiment]

[1338] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1339] 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.

[1340] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[1341] 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.

[1342] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1343] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1344] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1345] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1346] 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.

[1347] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1348] 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.

[1349] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1350] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1351] 1. Overview of the entire system

[1352] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system operates in cooperation with the server, terminals, and users, promoting information sharing between departments and conducting analysis that takes external factors into account.

[1353] 2. Collection and accumulation of policy information

[1354] The user uses a device to input campaign information into the AI ​​chatbot. For example, they can enter details such as, "We have launched a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[1355] The device sends this policy information to the server via an AI chatbot.

[1356] The server stores the received policy information in a database.

[1357] 3. Collecting information on external factors

[1358] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[1359] The acquired information on external factors is stored in a database and integrated with other policy information.

[1360] 4. Data Analysis

[1361] The server uses machine learning algorithms to analyze the accumulated information on measures and external factors. The purpose of the analysis is to evaluate the true effectiveness of each measure and clarify how external factors are affecting it.

[1362] For example, the effectiveness of a TV commercial campaign implemented by the marketing department can be evaluated independently from the impact of heavy rain that occurred at the same time.

[1363] 5. Notification and sharing of analysis results

[1364] The server notifies users in each department of the results of the analysis via an AI chatbot, providing detailed reports such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas."

[1365] Users can use their devices to receive these analysis results and provide feedback on the effectiveness of the measures.

[1366] 6. Feedback and Reassessment

[1367] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including details such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%."

[1368] The server stores this feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[1369] 7. Predicting future measures

[1370] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future measures.

[1371] For example, it is possible to generate prediction results such as, "A target audience rating of 15% for the next campaign is reasonable. Also, taking into account weather forecasts, the audience rating in the Kanto region may be affected."

[1372] The device will notify relevant users of the prediction results via an AI chatbot, helping them plan their actions.

[1373] Specific examples

[1374] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses machine learning algorithms to analyze the effectiveness of the campaign, including the impact of heavy rain on viewership. Finally, the server notifies the marketing department of the results of the analysis and provides a forecast to help plan future campaigns.

[1375] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation while taking external factors into account.

[1376] The processing flow will be explained below.

[1377] Step 1:

[1378] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[1379] Step 2:

[1380] The terminal sends the policy information entered by the user to the server via an AI chatbot.

[1381] Step 3:

[1382] The server stores the received policy information in a database.

[1383] Step 4:

[1384] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[1385] Step 5:

[1386] The server stores the acquired external factor information in a database.

[1387] Step 6:

[1388] The server uses machine learning algorithms to analyze the accumulated policy information and external factor information, and evaluates the impact of each policy factor.

[1389] Step 7:

[1390] The server notifies users in each department of the analysis results via an AI chatbot, generating a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas."

[1391] Step 8:

[1392] The user receives notifications from the AI ​​chatbot on their device, checks the analysis results, and provides feedback if necessary.

[1393] Step 9:

[1394] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including detailed information such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%."

[1395] Step 10:

[1396] The server stores the received feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[1397] Step 11:

[1398] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future measures.

[1399] Step 12:

[1400] The server notifies users in each department of the results of the predictions via an AI chatbot, providing, for example, a prediction such as, "A target audience rating of 15% for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected."

[1401] Step 13:

[1402] Users can use their devices to receive the forecast results and reflect them in their next action plan. Through this process, collaboration between departments is strengthened, and highly accurate effect measurement and forecast creation are achieved while taking external factors into account.

[1403] Example 1

[1404] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1405] With conventional policy effectiveness measurement systems, it was difficult to centrally collect and analyze policy information from each department and information on external factors, and to effectively communicate and share the results. Another problem was the low accuracy of predicting the next policy plan using policy feedback information. This resulted in a decrease in the accuracy of policy effectiveness measurement and decision-making, making it difficult to formulate effective policy plans.

[1406] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1407] In this invention, the server includes means for collecting policy information from users in each department and storing it in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information using a machine learning algorithm, means for notifying users in each department of the analysis results, means for collecting feedback from users in each department, means for storing the collected feedback information in the database, means for reevaluating based on the feedback information, means for predicting the effectiveness of the next policy, and means for notifying users in each department of the prediction results. This makes it possible to comprehensively analyze policy information and external factor information and utilize feedback to measure effectiveness and predict future policies with high accuracy.

[1408] "Policy information" refers to data on the plans and activities implemented by each department.

[1409] "Departmental users" refers to people who work in different departments of a company or organization.

[1410] "Terminal" means an electronic device used by a user to input and view information.

[1411] A "database" is a system for organizing and storing information.

[1412] "External factor information" refers to external conditions and data that affect policies, such as weather information and economic data.

[1413] A "server" is a central system for receiving, storing, and analyzing information from users.

[1414] A "machine learning algorithm" is a program that finds useful patterns and predictions from large amounts of data.

[1415] "Analysis Results" means analytical data obtained using machine learning algorithms or other means.

[1416] "Feedback information" refers to ratings and additional information provided by users.

[1417] "Reevaluation" refers to additional analysis based on newly collected information or feedback.

[1418] "Predicted results" refers to data that predicts the effects and results of future measures.

[1419] This invention is a system that uses AI chatbots to automatically collect, store, and analyze information about each department's measures and their effects. This system operates in cooperation with a server, terminals, and users.

[1420] Specific system configuration

[1421] 1. A terminal is a device through which a user inputs policy information. Specifically, this includes PCs, tablets, smartphones, etc.

[1422] 2. The server is a computer system that stores received policy information, collects external factor information, and analyzes the data using machine learning algorithms. The database uses a relational database such as MySQL or PostgreSQL. Machine learning uses Python's pandas library, scikit-learn, TensorFlow, etc.

[1423] 3. Users are people working in various departments, such as marketing and sales. They can input policy information through the AI ​​chatbot and receive analysis and prediction results.

[1424] Data collection and storage

[1425] The user launches the AI ​​chatbot on their device and inputs information about the campaign. For example, they might input information like, "We've launched a new TV commercial campaign. Our target audience rating is 10%, and the actual result is 12%." The device then sends the input campaign information to the server, which then stores this information in a database.

[1426] Gathering information on external factors

[1427] The server periodically calls the Web API to obtain external factor information. Specifically, it obtains weather information and macroeconomic data from the weather information API and economic data API, and stores this in a database.

[1428] Data analysis

[1429] The server retrieves information about campaigns and external factors from the database and performs analysis using machine learning algorithms. The purpose of the analysis is to evaluate the true effectiveness of each campaign and clarify the influence of external factors. For example, to evaluate the effectiveness of a TV commercial campaign, a regression analysis is performed to isolate the impact of heavy rain on viewer ratings.

[1430] Communicating and sharing analysis results

[1431] The server generates a report of the analysis results and notifies the user through an AI chatbot. For example, the report may include, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas." The user can view the report on their device and provide feedback.

[1432] Feedback and Reassessment

[1433] The user sends feedback information to the server through the AI ​​chatbot. For example, they might send information like, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%." The server then stores this feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[1434] Predicting future measures

[1435] The server uses accumulated data and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate, and taking into account weather forecasts, audience ratings may be affected in the Kanto region." The device then notifies the user of this prediction via an AI chatbot.

[1436] Examples of specific examples and prompts

[1437] For example, a marketing department launches a new TV commercial campaign, and users input that information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses machine learning algorithms to analyze the effectiveness of the campaign and generate analysis results, including the impact of heavy rain on viewership. Finally, the server notifies the marketing department of the analysis results and provides predictions that can be used as a reference for planning future campaigns.

[1438] An example of a prompt sentence would be, "We have launched a new TV commercial campaign. The target viewership rate was 10%, and the actual rate was 12%. There was some fluctuation in viewership rate due to heavy rain. Please tell us your predictions for the next campaign." The system will then respond to this.

[1439] As described above, this system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation that takes external factors into account.

[1440] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1441] Step 1:

[1442] The user launches the AI ​​chatbot on their device and inputs policy information.

[1443] Input: Information about your new TV ad campaign (e.g., "We launched a new TV ad campaign. Our target viewership was 10%, and our actual result was 12%)

[1444] Output: Request data including policy information

[1445] Specific operation: The user enters policy information in text format into the AI ​​chatbot on the device and clicks the input button.

[1446] Step 2:

[1447] The terminal transmits the input policy information to the server.

[1448] Input: Policy information entered by the user

[1449] Output: Policy information sent to the server

[1450] Specific operation: The terminal sends the text entered by the user to the server via the HTTPS protocol.

[1451] Step 3:

[1452] The server stores the received policy information in a database.

[1453] Input: Submitted policy information

[1454] Output: Policy information stored in the database

[1455] Specific operation: The server stores policy information as records in a database such as MySQL or PostgreSQL.

[1456] Step 4:

[1457] The server periodically acquires the external factor information and stores it in a database.

[1458] Input: Request to get external factor information

[1459] Output: External factor information stored in the database

[1460] Specific operation: The server periodically calls the weather information API and economic data API to obtain and store weather information, macroeconomic data, etc.

[1461] Step 5:

[1462] The server analyzes the accumulated policy information and external factor information.

[1463] Input: Policy information and external factor information stored in the database

[1464] Output: Analysis results

[1465] Specific operation: The server retrieves the necessary information from the database using SQL queries and analyzes it using machine learning algorithms such as Python's pandas library, scikit-learn, and TensorFlow.

[1466] Step 6:

[1467] The server notifies the users in each department of the analysis results.

[1468] Input: Analysis results

[1469] Output: A message to inform the user

[1470] Specific operation: The server notifies the user of the analysis results through an AI chatbot and generates a detailed analysis report.

[1471] Step 7:

[1472] The user inputs feedback information and sends it to the server.

[1473] Input: Feedback information (e.g., "We also implemented a unique store promotion, which resulted in a 10% increase in overall sales.")

[1474] Output: Feedback information sent to the server

[1475] Specific actions: The user uses the device to enter feedback information into the AI ​​chatbot and clicks the send button.

[1476] Step 8:

[1477] The server stores the received feedback information in a database.

[1478] Input: Feedback information

[1479] Output: Feedback information stored in a database

[1480] Specific operation: The server stores the feedback information as a record in the database.

[1481] Step 9:

[1482] The server will reassess based on the accumulated data and feedback information.

[1483] Input: Policy information, external factors, feedback information

[1484] Output: Reevaluation results

[1485] Specific operation: The server performs analysis again using all data collected so far and updates the analysis results.

[1486] Step 10:

[1487] The server predicts the effect of the next measure and generates a predicted result.

[1488] Input: Stored data and machine learning algorithms

[1489] Output: Prediction result of next action

[1490] Specific operation: The server operates a model to predict the effectiveness of future measures based on past data and analysis results, and generates prediction results.

[1491] Step 11:

[1492] The terminal notifies the user of the prediction result.

[1493] Input: Prediction result

[1494] Output: A message to inform the user

[1495] Specific operation: Receives the prediction results sent from the server and notifies the user through the AI ​​chatbot.

[1496] (Application example 1)

[1497] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1498] With conventional systems, it was difficult to accurately evaluate the effectiveness of measures implemented by each department and obtain appropriate feedback. It was also difficult to make accurate predictions that took external factors into account, leading to uncertainty about the next measure plan. Furthermore, collecting measure information and feedback from physical stores was cumbersome, which tended to delay integrated analysis.

[1499] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1500] In this invention, the server includes means for collecting policy information from users in each department and storing it in a database, means for periodically acquiring and storing external factor information, means for analyzing the collected policy information and external factor information using a machine learning algorithm, means for notifying users in each department of the analysis results and a prediction of the effectiveness of the next policy to help them plan the policy, means for users of the physical store to input policy information via a smart device and collect feedback, and means for generating accurate prediction results based on the acquired external factor information and providing them to users. This makes it possible to accurately evaluate the effectiveness of policies in each department and provide highly accurate predictions that take external factors into account.

[1501] "Users in each department" refers to employees and staff members who belong to different departments of a company or organization.

[1502] "Policy information" refers to detailed information on specific initiatives, campaigns, and promotions implemented by each department.

[1503] "Database" refers to an electronic recording system for storing and managing policy information and external factor information.

[1504] "External factor information" refers to external data that may affect the effectiveness of policies, such as weather forecasts and economic indicators.

[1505] A "machine learning algorithm" refers to a mathematical technique that allows computers to learn patterns from data and make predictions and analyses.

[1506] "Analysis results" refers to the output after analyzing policy information and external factor information using a machine learning algorithm.

[1507] "Smart devices" refers to highly functional mobile devices that can connect to the Internet, such as smartphones and tablets.

[1508] "Feedback" refers to evaluations and comments regarding the results and effectiveness of measures provided by users.

[1509] "Prediction results" refer to the results of predicting the effects of future measures using machine learning algorithms.

[1510] "User" refers to the operators, staff, or customers of physical stores who use the system.

[1511] "Brick and mortar store" refers to a physical store where transactions are conducted directly with customers face-to-face.

[1512] This invention is a system that uses AI chatbots to effectively collect, analyze, and predict policy information. This system operates in cooperation with servers, terminals, and users, enabling accurate collection and analysis of policy information.

[1513] First, the user inputs information about the store's initiatives via a smart device (smartphone or tablet). For example, detailed information such as "Sales during the weekend sale reached 120% of the target. Due to the fine weather, customer traffic increased" can be entered into the chatbot. This allows the context and results of the initiatives to be recorded in detail.

[1514] Policy information sent from smart devices is transferred to the server and stored in a database. The server periodically obtains external factor information (e.g., weather forecasts and economic indicators) from Web APIs and other data sources, and stores this information in the database as well.

[1515] The server analyzes the collected information on measures and external factors using a machine learning algorithm (e.g., Random Forest Regressor). This analysis evaluates the true effect of each measure and clarifies the influence of external factors. For example, it can analyze the effect of a weekend sale on sunny weather separately from other factors.

[1516] The analysis results are communicated to relevant users via an AI chatbot. For example, a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual. Also, heavy rain in the Kanto region affected viewership in some areas." This allows users to provide feedback on the effectiveness of the campaign and use it to plan the next campaign.

[1517] Furthermore, the server uses the accumulated data and machine learning algorithms to predict the effectiveness of the next campaign. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected." The device then notifies the relevant user of this prediction via an AI chatbot, which helps with campaign planning.

[1518] As a specific example, by entering a prompt such as "What is a reasonable sales target for the weekend sale? The weather forecast says it's going to rain" into the chatbot, the system will instantly generate and provide a prediction for the next initiative.

[1519] This system efficiently collects information on measures taken by physical stores and enables highly accurate analysis and predictions that take external factors into account, allowing for accurate evaluation of the effectiveness of measures and the optimization of future measures.

[1520] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1521] Step 1:

[1522] Input: A user inputs campaign information using a smart device (e.g., "Sales from the weekend sale reached 120% of the target. The sunny weather led to an increase in customer traffic.").

[1523] Processing: The device sends this policy information to the server via an AI chatbot.

[1524] Output: The policy information is sent to the server and recorded in the database.

[1525] Step 2:

[1526] Input: Policy information submitted by the user.

[1527] Processing: The server periodically obtains external information (e.g., weather forecasts, economic indicators) using Web APIs and data feeds.

[1528] Output: The latest external factor information is stored on the server.

[1529] Step 3:

[1530] Input: Policy information and external factor information are stored in the database.

[1531] Processing: The server analyzes the policy information and external factor information using a machine learning algorithm (e.g., RandomForestRegressor), thereby evaluating the true effectiveness of each policy and the influence of external factors.

[1532] Output: The analysis results are generated (e.g., "The effectiveness of the weekend sale was 20% higher than usual. The sunny weather led to an increase in customer traffic.").

[1533] Step 4:

[1534] Input: Analysis results.

[1535] Processing: The server notifies the user of the analysis results via an AI chatbot.

[1536] Output: A detailed report is displayed on the user's device (e.g., "The effectiveness of our weekend sale was 20% higher than usual. The sunny weather led to an increase in foot traffic.").

[1537] Step 5:

[1538] Input: User feedback (e.g., "We'll further validate the results of this weekend's sale. We'll also add regional sales data.").

[1539] Processing: The AI ​​chatbot receives feedback from the user and sends it to the server.

[1540] Output: Feedback information is stored in a database and used for future analysis and prediction.

[1541] Step 6:

[1542] Input: Accumulated data and feedback information.

[1543] Processing: The server uses machine learning algorithms to predict the effectiveness of the next initiative (e.g., prompt: "What is a reasonable sales target for the next weekend sale? The weather forecast says it's going to rain.").

[1544] Output: A prediction result is generated (e.g., "The target sales for the next weekend sale are expected to increase by 10%. However, rain may affect this.").

[1545] Step 7:

[1546] Input: Prediction results.

[1547] Processing: The server notifies the user of the prediction results through an AI chatbot.

[1548] Output: The prediction results are displayed on the user's device and can be used to plan future measures.

[1549] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1550] 1. Overview of the entire system

[1551] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system involves servers, terminals, and users working together to promote information sharing between departments and perform analysis that takes into account external factors and user emotions.

[1552] 2. Collection and accumulation of policy information

[1553] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[1554] The device sends this policy information to the server via an AI chatbot.

[1555] The server stores the received policy information in a database.

[1556] 3. Collecting information on external factors

[1557] The server periodically obtains external information such as weather information and macroeconomic data from Web APIs and data feeds.

[1558] The acquired information on external factors is stored in a database and integrated with other policy information.

[1559] 4. Introducing the Emotion Engine

[1560] The server embeds an emotion engine into the AI ​​chatbot, which analyzes the user's input information and feedback and recognizes their emotional state (e.g., satisfaction, dissatisfaction, expectation, etc.).

[1561] For example, if a user types, "This campaign didn't work as well as expected," the emotion engine will recognize the emotion of dissatisfaction.

[1562] 5. Data Analysis

[1563] The server uses machine learning algorithms to analyze the accumulated policy information and external factor information, and evaluates the impact of each policy factor.

[1564] In addition, the analysis results of the emotion engine are also integrated to provide a comprehensive evaluation that includes the user's emotions.

[1565] For example, a detailed report can be generated such as, "The effectiveness of the TV commercial campaign was 20% higher than usual, but user sentiment analysis revealed that some users were dissatisfied."

[1566] 6. Notification and sharing of analysis results

[1567] The server notifies users in each department of the analysis results via an AI chatbot.

[1568] Users can use their devices to receive these analysis results and provide feedback on the effectiveness of the measures.

[1569] 7. Feedback and Reassessment

[1570] Feedback information provided by users is also sent to the server via the AI ​​chatbot, including details such as, "We also implemented a store-specific promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected."

[1571] The server stores this feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[1572] 8. Forecasting future measures

[1573] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future measures.

[1574] For example, the system generates predictions such as, "A target audience rating of 15% for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected. Furthermore, previous measures resulted in low satisfaction among some users, so it is recommended that you take measures to improve the situation."

[1575] The device will notify relevant users of the prediction results via an AI chatbot, helping them plan their actions.

[1576] Specific examples

[1577] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign and includes the impact of heavy rain on viewership. The emotion engine also recognizes that there were many complaints from users' feedback. Finally, the server notifies the marketing department of the results of the analysis and provides predictions to be used as a reference for planning future campaigns.

[1578] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation, taking into account external factors and user emotions.

[1579] The processing flow will be explained below.

[1580] Step 1:

[1581] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%."

[1582] Step 2:

[1583] The device sends the input policy information to the server via an AI chatbot. This information includes the policy's purpose, means, implementation period, target values, and actual results.

[1584] Step 3:

[1585] The server stores the received policy information in a database, checking the consistency of the input data and converting the data format.

[1586] Step 4:

[1587] The server periodically obtains external information such as weather and macroeconomic data from web APIs and data feeds, and stores this information in a database along with policy information.

[1588] Step 5:

[1589] The server uses an emotion engine to analyze the user's input information and feedback and recognize their emotional state. For example, if a user inputs "This campaign did not have the expected effect," the emotion engine will recognize the emotion as dissatisfied.

[1590] Step 6:

[1591] The server uses a machine learning algorithm to analyze the accumulated information on measures, external factors, and the analysis results of the emotion engine, and evaluates the effectiveness of each measure and how external factors and user emotions have affected its effectiveness.

[1592] Step 7:

[1593] The server notifies users in each department of the analysis results via an AI chatbot, generating a detailed report such as, "The effectiveness of the TV commercial campaign was 20% higher than usual, but there was dissatisfaction feedback from multiple users."

[1594] Step 8:

[1595] The user receives notifications from the AI ​​chatbot on their device, checks the analysis results, and provides their own feelings and additional feedback information (e.g., "We also implemented a unique store promotion at the same time, which increased overall sales by 10%.").

[1596] Step 9:

[1597] The device sends the feedback information provided by the user to the server via an AI chatbot.

[1598] Step 10:

[1599] The server stores the received feedback information in a database and uses it to improve the accuracy of future analyses and predictions.

[1600] Step 11:

[1601] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates predictions such as, "A 15% target viewer rating is appropriate for the next campaign. Also, previous campaigns have resulted in low satisfaction among some users, so it is recommended that you take measures to improve them."

[1602] Step 12:

[1603] The server notifies the relevant users of the prediction results through an AI chatbot.

[1604] Step 13:

[1605] Users can use their devices to receive the prediction results and reflect them in their next action plan. Through this process, collaboration between departments is strengthened, and highly accurate effect measurement and forecast creation are achieved by taking into account external factors and user sentiment.

[1606] Example 2

[1607] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1608] In today's business environment, it is extremely important for each department to implement measures and accurately evaluate their effectiveness. However, in conventional systems, the collection and analysis of measure information was done manually, which was time-consuming and costly, and the accuracy of the evaluation was limited. Furthermore, it was not possible to take external factors or user sentiment into account, making it difficult to accurately grasp the effectiveness of measures. Furthermore, there were few ways to predict future measure effects, leading to high uncertainty when planning the next measure. This has created a demand for an accurate and efficient system for comprehensive effect measurement and forecast creation.

[1609] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting policy information from users in each department, means for storing the collected policy information in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information, means for notifying users in each department of the analysis results, means for analyzing user emotions, means for integrating the emotion analysis results into policy information analysis, means for collecting user feedback information and storing it in the database, and means for predicting future policies and notifying users in each department of the prediction results. This enables an integrated analysis of policy information and external factors, making it possible to achieve highly accurate effect evaluation and future policy forecasting that also takes user emotional information into consideration.

[1610] "Policy information" refers to data and results regarding specific policies implemented by each department.

[1611] "External factor information" refers to data related to the external environment, such as weather information and macroeconomic data, that affect the effectiveness of policies.

[1612] "Database" refers to an information management system for organizing and storing collected policy information and external factor information.

[1613] "Analysis means" refers to the techniques and processes for analyzing accumulated data and evaluating the effectiveness of measures.

[1614] "Notification means" refers to the technology and process for communicating analysis and prediction results to users in each department.

[1615] "Sentiment analysis" refers to the techniques and processes of extracting and analyzing a user's emotional state from input information.

[1616] "Feedback information" refers to evaluation data provided after a measure is implemented, such as users' opinions and satisfaction with the measure, and areas for improvement.

[1617] "Machine learning algorithms" refers to statistical methods and artificial intelligence techniques used for data analysis and prediction.

[1618] "Effectiveness forecasting" refers to the technology and process of predicting future policy effects based on past and current data.

[1619] 1. Overview of the entire system

[1620] This invention is a system that uses an AI chatbot to automatically collect, store, and analyze information on each department's measures and their effects, and then uses this information to measure the effects and create forecasts. This system involves servers, terminals, and users working together to promote information sharing between departments and perform analysis that takes into account external factors and user emotions.

[1621] 2. Collection and accumulation of policy information

[1622] The user uses a device to input campaign information into the AI ​​chatbot. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target audience rating is 10%, and the actual result is 12%." The device then sends this campaign information to the server via the AI ​​chatbot. The server then stores the received campaign information in a database.

[1623] 3. Collecting information on external factors

[1624] The server periodically obtains external factor information such as weather information and macroeconomic data from web APIs and data feeds. The obtained external factor information is stored in a database and integrated with other policy information.

[1625] 4. Introducing the Emotion Engine

[1626] The server incorporates an emotion engine into the AI ​​chatbot. This emotion engine analyzes the user's input information and feedback and recognizes their emotional state (e.g., satisfaction, dissatisfaction, expectation, etc.). For example, if a user inputs, "This campaign did not have the desired effect," the emotion engine recognizes the emotion as dissatisfaction.

[1627] 5. Data Analysis

[1628] The server uses a machine learning algorithm to analyze the accumulated campaign information and external factor information. This evaluates the degree of impact of each campaign factor. It also integrates the analysis results of the emotion engine to provide a comprehensive evaluation that includes user emotions. For example, it generates a detailed report that states, "The effectiveness of the TV commercial campaign was 20% higher than usual, but some users expressed dissatisfaction."

[1629] 6. Notification and sharing of analysis results

[1630] The server notifies users in each department of the analysis results via an AI chatbot. Users can then receive these results using their devices and provide feedback on the effectiveness of the measures.

[1631] 7. Feedback and Reassessment

[1632] Feedback information provided by users is also sent to the server via the AI ​​chatbot. For example, it may include details such as, "We also implemented a unique store promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected." The server stores this feedback information in a database and uses it to improve the accuracy of future analysis and predictions.

[1633] 8. Forecasting future measures

[1634] The server uses accumulated data, user sentiment information, and machine learning algorithms to predict the effectiveness of future campaigns. For example, it generates a prediction such as, "A 15% target audience rating for the next campaign is appropriate. Also, taking into account weather forecasts, audience ratings in the Kanto region may be affected. Furthermore, previous campaigns have resulted in low satisfaction among some users, so it is recommended that improvements be made." The device then notifies relevant users of the prediction results via an AI chatbot, helping them plan campaigns.

[1635] Specific examples

[1636] For example, the marketing department launches a new TV commercial campaign and inputs the information into an AI chatbot. The server stores this information in a database, while also collecting weather and macroeconomic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign and includes the impact of heavy rain on viewership. The emotion engine also recognizes that there were many complaints from users' feedback. Finally, the server notifies the marketing department of the results of the analysis and provides predictions to be used as a reference for planning future campaigns.

[1637] Below are some specific examples of prompt sentences that can be input to the generative AI model in this system.

[1638] "We ran a new TV commercial campaign. Our target viewer rating was 10%, and the actual result was 12%. There were many days of heavy rain during the campaign period, which is thought to have affected the viewer rating. We have received some dissatisfaction from users in their feedback. Please suggest improvements for the next campaign based on your analysis."

[1639] In this way, the system strengthens collaboration between departments and enables highly accurate effect measurement and forecast creation, taking into account external factors and user emotions.

[1640] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1641] Step 1: User inputs policy information

[1642] Users input information about their initiatives into the AI ​​chatbot using their own devices. For example, they input specific information such as, "We have implemented a new TV commercial campaign. Our target viewership rate is 10%, and the actual result is 12%." This input is structured in text format.

[1643] Input: The user inputs the policy information in text format.

[1644] Output: The policy information entered into the terminal is saved.

[1645] Step 2: Sending policy information from the device to the server

[1646] The device sends the input policy information to the server via an AI chatbot, where it is properly formatted and converted into a usable form.

[1647] Input: Policy information stored on the device.

[1648] Output: Policy information is sent to the server via the AI ​​chatbot.

[1649] Step 3: Storing policy information on the server

[1650] The server stores the received policy information in a database. When the server receives the information, it stores it in the appropriate table in the database and creates an index to enable fast searches.

[1651] Input: Policy information sent to the server.

[1652] Output: Policy information stored in a database.

[1653] Step 4: Server collects external information

[1654] The server periodically retrieves external information such as weather information and macroeconomic data from web APIs and data feeds, for example, from the OpenWeatherMap API or government economic data portals, and stores it in a database.

[1655] Input: Requests for external information from web APIs or data feeds.

[1656] Output: External factor information stored in a database.

[1657] Step 5: Analysis of policy information and external factor information by the server

[1658] The server analyzes the accumulated policy information and external factor information using machine learning algorithms (e.g., random forest, linear regression), and evaluates the impact of each policy factor.

[1659] Input: Policy information and external factor information stored in the database.

[1660] Output: Analyzed data and results (e.g., effectiveness assessment).

[1661] Step 6: Emotion analysis using the emotion engine

[1662] The server uses an emotion engine for policy information and feedback information. For example, it uses natural language processing (NLP) technology to analyze emotions from user input and recognize emotional states such as satisfaction, dissatisfaction, and expectation.

[1663] Input: User text input and feedback.

[1664] Output: Analysis results representing the user's emotional state.

[1665] Step 7: Server generates and notifies analysis results

[1666] The server generates a detailed report based on the analysis results and notifies users in each department. For example, a report such as "The effectiveness of the TV commercial campaign was 20% higher than usual, but some users expressed dissatisfaction" can be compiled and sent to users via an AI chatbot.

[1667] Input: Analysis results from machine learning and sentiment engine.

[1668] Output: Detailed report and user notification.

[1669] Step 8: User feedback

[1670] The user inputs feedback based on the analysis results into the AI ​​chatbot, for example, by writing specific comments such as, "We also implemented a store-specific promotion at the same time, which increased overall sales by 10%. However, customer satisfaction was lower than expected."

[1671] Input: User feedback.

[1672] Output: Feedback information stored on the device.

[1673] Step 9: Sending feedback information from the device to the server

[1674] The device sends the user's feedback information to the server through the AI ​​chatbot, which then formats the feedback information appropriately and sends it to the server.

[1675] Input: Feedback information stored on the device.

[1676] Output: Feedback information sent to the server.

[1677] Step 10: Server accumulates and re-evaluates feedback information

[1678] The server stores the received feedback information in a database, then performs a comprehensive analysis including the feedback information, and uses the results to help improve future measures.

[1679] Input: The feedback information sent to the server.

[1680] Output: Feedback information stored in a database.

[1681] Step 11: Server creates forecast of future measures

[1682] The server predicts the effectiveness of future campaigns based on accumulated campaign information, external factor information, feedback information, and sentiment analysis results. For example, it generates a prediction such as, "A target audience rating of 15% for the next campaign is appropriate. Taking into account weather forecasts, audience ratings in the Kanto region may be affected," and notifies the device.

[1683] Input: Policy information, external factor information, feedback information, and sentiment analysis results stored in the database.

[1684] Output: Predicted results of future actions notified to the user.

[1685] (Application example 2)

[1686] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1687] Conventional policy evaluation systems only quantitatively evaluate the effectiveness of policies, and do not comprehensively evaluate them, taking into account customer sentiment or external factors. This makes it difficult to accurately measure the effectiveness or predict future policies, making it difficult to improve customer satisfaction or formulate appropriate policy plans.

[1688] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1689] In this invention, the server includes means for collecting policy information from users in each department, means for storing the collected policy information in a database, means for periodically acquiring external factor information and storing it in the database, means for analyzing the stored policy information and external factor information, means for notifying users in each department of the analysis results, emotion analysis means for analyzing user satisfaction and dissatisfaction, means for making a comprehensive evaluation based on the policy information, external factor information, and emotion information, and means for notifying users of the policy analysis results and prediction results to use in policy planning. This enables highly accurate effect measurement and future policy prediction taking into account customer emotions and external factors.

[1690] "Policy information" refers to detailed data and information about specific promotions, campaigns, events, etc. that have been implemented.

[1691] A "database" is an information management system for systematically storing and managing various collected information.

[1692] "External factor information" refers to information about external environmental variables that affect the effectiveness of policies, such as weather, economic data, and social trends.

[1693] "Analysis means" refers to a method or process for evaluating and diagnosing collected and accumulated data using techniques such as statistical analysis and machine learning.

[1694] "Notification means" refers to the communication and notification method used to inform users of analysis results and prediction data.

[1695] "Emotion analysis means" is a technology that automatically analyzes emotions such as satisfaction, dissatisfaction, and expectations from user feedback and comments.

[1696] "Comprehensive evaluation" is a process of centrally evaluating multiple data, such as policy information, external factor information, and emotional information, to determine the overall effectiveness.

[1697] "Policy planning" refers to the specific planning of future promotions and campaigns.

[1698] A "machine learning algorithm" is a mathematical technique that learns from data, discovers patterns, and makes future predictions and classifications.

[1699] The system of the present invention uses an AI chatbot to collect policy information and evaluate its effectiveness. The main components of this system are a server, a terminal, and a user. The server collects, stores, and analyzes data, and notifies the user of the results via the terminal.

[1700] 1. Overview of the entire system

[1701] Users input policy information into their devices. This information is sent to the server via an AI chatbot. The server stores the policy information in a database and periodically collects external factor information. The server also performs sentiment analysis of user feedback and comprehensively evaluates the effectiveness of the policy.

[1702] 2. Collection and accumulation of policy information

[1703] The user inputs specific information about the campaign into the device, such as, "We've launched a new promotion. The target achievement rate is 15%, and the actual result is 18%." The input information is sent to the server via an AI chatbot. The server accumulates this information in a database and saves it for future analysis.

[1704] 3. Collecting information on external factors

[1705] The server periodically obtains information on external factors such as weather and economic data via a Web API and stores it in a database, allowing external factors that affect the effectiveness of measures to be taken into account.

[1706] 4. Emotion analysis

[1707] The AI ​​chatbot collects the feedback provided by the user, and the server analyzes the feedback using a sentiment analysis engine. For example, if a user types, "This promotion did not go as expected," the sentiment analysis engine will evaluate this feedback as "dissatisfied."

[1708] 5. Data Analysis

[1709] The server uses a machine learning algorithm to analyze the accumulated campaign information and external factor information. This allows it to evaluate the impact of each campaign factor. It also integrates the results of the sentiment analysis engine to provide a comprehensive evaluation that includes user sentiment. For example, it generates a detailed report that states, "The effectiveness of the promotion was 20% higher than usual, but user sentiment analysis indicates that some users are dissatisfied."

[1710] 6. Notification and sharing of analysis results

[1711] The server notifies users in each department of the analysis results via an AI chatbot. Users can then receive these results using their devices and provide feedback on the effectiveness of the measures.

[1712] 7. Feedback and Reassessment

[1713] Feedback information provided by users is also sent to the server through the AI ​​chatbot, including details such as, "Some products sold out due to a new promotion, but overall customer satisfaction was low." The server stores this feedback information in a database and reflects it in future measures.

[1714] 8. Forecasting future measures

[1715] The server uses the accumulated data, user emotional information, and machine learning algorithms to predict the effectiveness of the next campaign. For example, it generates a prediction such as, "The next promotion is expected to achieve a 20% target. Also, according to the weather forecast, continued rain may affect sales." The device notifies the user of this prediction via an AI chatbot, which helps with campaign planning.

[1716] Specific examples

[1717] For example, a physical store holds a "New Year's sale" and inputs that information into an AI chatbot. The server stores this information in a database, while also collecting weather and economic data. After the campaign ends, the server uses a machine learning algorithm to analyze the effectiveness of the campaign, including the impact of heavy rain on sales. The emotion engine also recognizes that there were many complaints from customers based on their feedback. Finally, the server notifies the store operator of the analysis results and provides predictions to be used as a reference for planning future campaigns.

[1718] Prompt Sentence Examples

[1719] "Please enter information about your new campaign. Include specifics, timeframe, goals, and achievements."

[1720] "Please enter customer feedback. For example, 'I was satisfied with the campaign' or 'I didn't feel it was effective.'"

[1721] In this way, users can comprehensively evaluate the effectiveness of measures taken in running a physical store and more accurately plan future measures.

[1722] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1723] Step 1:

[1724] The user inputs the policy information into the terminal.

[1725] Specific operation: The user uses a smartphone application to input detailed information about the campaign (e.g., promotion content, period, target value, and actual value). The input information is sent to the server via an AI chatbot.

[1726] Input: Policy information (e.g. promotion details, goal achievement rate, results, etc.)

[1727] Output: Policy information sent to the server via the AI ​​chatbot

[1728] Step 2:

[1729] The server stores the policy information in a database.

[1730] Specific operation: The server stores the received policy information in a database and manages it for future analysis.

[1731] Input: Policy information sent from the AI ​​chatbot

[1732] Output: Policy information stored in the database

[1733] Step 3:

[1734] The server periodically acquires information about external factors and stores it in a database.

[1735] Specific operation: The server periodically obtains weather information and economic data using a Web API and stores this external factor information in a database.

[1736] Input: External information (e.g., weather information via Web API, economic data)

[1737] Output: External factor information stored in the database

[1738] Step 4:

[1739] Users enter their feedback into an AI chatbot.

[1740] Specific operation: The user uses the device to input feedback about the campaign or promotion, for example, inputting a comment such as "This promotion did not meet my expectations."

[1741] Input: Feedback information

[1742] Output: Feedback information sent to the server via the AI ​​chatbot

[1743] Step 5:

[1744] The server analyzes the feedback using a sentiment analysis engine.

[1745] Specific operation: The server passes the feedback information to the emotion analysis engine, and extracts the user's emotions (e.g., satisfaction, dissatisfaction, expectation, etc.) as the analysis result.

[1746] Input: Feedback information

[1747] Output: Parsed emotion information

[1748] Step 6:

[1749] The server performs a comprehensive evaluation based on policy information, external factor information, and emotion information.

[1750] Specific operation: The server uses a machine learning algorithm to analyze policy information and external factor information, and also integrates the results of sentiment analysis to evaluate the overall effectiveness of the policy.

[1751] Input: Policy information, external factor information, emotion information

[1752] Output: Comprehensive evaluation results (e.g., detailed report)

[1753] Step 7:

[1754] The server notifies users in each department of the analysis results via an AI chatbot.

[1755] Specific operation: The server notifies the user of the overall evaluation results in real time and provides a detailed report via an AI chatbot.

[1756] Input: Overall evaluation result

[1757] Output: Reports to be sent to users in each department

[1758] Step 8:

[1759] The feedback information provided by the user is sent to the server via the AI ​​chatbot.

[1760] Specific operation: Users enter feedback on campaign results and areas for improvement into the application, which is then sent to the server via an AI chatbot.

[1761] Input: User feedback information

[1762] Output: Feedback information stored in a database

[1763] Step 9:

[1764] The server predicts the effectiveness of the next measure.

[1765] Specific operation: The server uses accumulated policy information, external factor information, emotional information, and machine learning algorithms to predict the effectiveness of the next policy.

[1766] Input: Policy information, external factor information, emotion information

[1767] Output: Prediction of next policy effect

[1768] Step 10:

[1769] The server notifies the user of the prediction results through an AI chatbot.

[1770] Specific operation: The server sends the prediction results to the user via the AI ​​chatbot, and uses them as a reference for planning the next policy.

[1771] Input: Prediction result

[1772] Output: Prediction results notified to the user

[1773] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1774] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1775] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1776] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1777] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1778] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1779] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1780] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1781] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1782] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1783] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1784] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1785] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1786] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1787] 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.

[1788] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1789] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1790] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1791] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1792] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1793] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1794] The following is further disclosed regarding the above embodiment.

[1795] (Claim 1)

[1796] A means of collecting policy information from users in each department,

[1797] A means for storing the collected policy information in a database;

[1798] a means for periodically acquiring external factor information and storing it in the database;

[1799] A means for analyzing the accumulated policy information and external factor information;

[1800] A system that includes a means for notifying users in each department of the analysis results.

[1801] (Claim 2)

[1802] 2. The system according to claim 1, further comprising means for analyzing the accumulated policy information and external factor information using a machine learning algorithm.

[1803] (Claim 3)

[1804] 2. The system according to claim 1, further comprising: a means for predicting the effect of the next measure; and a means for notifying users in each department of the results of the prediction.

[1805] "Example 1"

[1806] (Claim 1)

[1807] A means of collecting policy information from users in each department,

[1808] A means for storing the collected policy information in a database;

[1809] a means for periodically acquiring external factor information and storing it in the database;

[1810] A means for analyzing the accumulated policy information and external factor information;

[1811] A means for analyzing policy information using machine learning algorithms and assessing the impact of external factors;

[1812] A means of notifying users in each department of the analysis results;

[1813] A means of collecting feedback from users across departments;

[1814] means for storing the collected feedback information in a database;

[1815] A means for reassessing based on feedback information;

[1816] A means of predicting the effectiveness of the next measure,

[1817] A means for notifying users in each department of the prediction results;

[1818] A system including:

[1819] (Claim 2)

[1820] The system according to claim 1, further comprising means for analyzing the accumulated policy information and external factor information using a machine learning algorithm and measuring the effectiveness.

[1821] (Claim 3)

[1822] 2. The system according to claim 1, further comprising means for creating a forecast of future measures and notifying users in each department of the results of the forecast.

[1823] "Application Example 1"

[1824] (Claim 1)

[1825] A means of collecting policy information from users in each department,

[1826] A means for storing the collected policy information in a database;

[1827] a means for periodically acquiring external factor information and storing it in the database;

[1828] A means for analyzing the collected policy information and external factor information using a machine learning algorithm;

[1829] The analysis results and the predicted effects of the next measures will be notified to users in each department, helping them plan measures.

[1830] A means for customers of physical stores to input information about measures via smart devices and collect feedback,

[1831] A means for generating highly accurate pred...

Claims

1. A means of collecting policy information from users in each department, A means for storing the collected policy information in a database; a means for periodically acquiring external factor information and storing it in the database; A means for analyzing the accumulated policy information and external factor information; A system that includes a means for notifying users in each department of the analysis results.

2. The system according to claim 1, further comprising means for analyzing the accumulated policy information and external factor information using a machine learning algorithm.

3. 2. The system according to claim 1, further comprising: means for predicting the effect of the next measure; and means for notifying users in each department of the results of the prediction.

Images