System

Abstract

A system is provided.SOLUTION: The system includes a means for acquiring agent data from a database, a means for predicting a condition score of an agent using an AI model based on the agent data, and a means for generating negotiation materials based on the predicted condition score.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] In conventional agency management, the task of properly evaluating an agency's condition and creating sales negotiation materials based on the results was extremely time-consuming and labor-intensive. This increased the workload of shop sales channel agency managers, resulting in reduced work efficiency. Furthermore, manual evaluation and document creation are prone to subjectivity, making consistent evaluations difficult. To address these issues, the present invention aims to provide a system that uses AI to analyze agency data and create sales negotiation materials efficiently and objectively. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. First, it provides a means for acquiring agent data from a database. This means acquires data such as agent sales, customer satisfaction, marketing expenditures, and performance scores. Next, it provides a means for predicting agent condition scores using an AI model based on the acquired agent data. Specifically, it analyzes the data using a linear regression model and calculates a condition score for each agent. Finally, it provides a means for generating sales negotiation materials based on the predicted condition scores. This means can automatically compile evaluation results for each agent and improvement actions based on the results into sales negotiation materials. This reduces the workload of shop sales channel agent managers and improves work efficiency.

[0006] "Agency Data" means data used to evaluate an agency's operational performance, including, among other things, sales, customer satisfaction, marketing expenditures, and performance scores.

[0007] A "database" is a system or medium for systematically storing and managing agency data, including CSV files.

[0008] An "AI model" is a set of mathematical algorithms that use artificial intelligence technology to analyze input data and make specific predictions or evaluations, and in the present invention, a linear regression model is a specific example.

[0009] The "Condition Score" is a numerical value calculated by an AI model to evaluate the operating condition of an agency and indicates the agency's overall performance.

[0010] "Negotiation materials" are materials to be used during negotiations with agents, and include information such as condition scores and improvement actions based on the condition scores.

[0011] A "linear regression model" is a type of machine learning algorithm that linearly models the relationship between features and targets, and is used for prediction and classification.

[0012] The "shop sales channel agency manager" is a person in charge of evaluating the agency's operational performance and conducting business negotiations, and is the target user of the present invention. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This system uses data from agents to predict condition scores using an AI model and generates sales negotiation materials based on the results. This system is composed of multiple steps involving a server, terminals, and users.

[0035] The server first retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundational data for a detailed understanding of the agency's operating condition. The server then inputs the retrieved agency data into an AI model to predict a condition score. Specifically, the server uses a linear regression model to analyze the data and quantify each agency's operating condition.

[0036] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0037] The user conducts sales negotiations using the sales negotiation materials generated by the server. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. This is expected to improve the quality of sales negotiations and the performance of agencies.

[0038] As a concrete example, let's say an agency's data looks like this:

[0039] If Agent A's sales are 1,000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server uses an AI model based on this data to predict a condition score. In this case, the condition score is predicted to be 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0040] In this way, the present invention makes it possible to efficiently and objectively evaluate agent data and automatically generate sales negotiation materials based on the results. This process reduces the user's workload and improves the effectiveness of sales negotiations.

[0041] The processing flow will be explained below.

[0042] Step 1:

[0043] The server retrieves agency data from the database: In this step, the server connects to the database and loads the agency data, which includes data such as sales, customer satisfaction, marketing spend, performance scores, etc. For example, it may load the data from a CSV file using the Pandas library.

[0044] Step 2:

[0045] The server preprocesses the acquired agency data and formats it into a format suitable for the AI ​​model. In this step, the server selects necessary columns from the loaded data and separates them into features (sales, customer satisfaction, marketing expenditures) and targets (performance scores).

[0046] Step 3:

[0047] The server uses the shaped data to train an AI model. Specifically, the server instantiates a linear regression model and trains it using features and targets. The goal of this step is to learn patterns from the data and use them to make future predictions.

[0048] Step 4:

[0049] The server uses the trained model to predict the condition score of each agent. In this step, the server inputs the features of each agent into the model and outputs a condition score. The predicted score is a numerical representation of each agent's performance.

[0050] Step 5:

[0051] The server generates sales materials based on the predicted condition scores. In this step, the server determines the content of the sales materials based on the condition scores of each agent. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high score, it includes a recommendation such as "strengthening sales activities would be effective."

[0052] Step 6:

[0053] The user can obtain the generated sales negotiation materials and use them in sales negotiations. By using the sales negotiation materials provided by the server, the user can objectively evaluate the performance of each agent and propose appropriate improvement actions, thereby effectively promoting sales negotiation activities.

[0054] Example 1

[0055] 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."

[0056] In conventional methods for creating sales negotiation materials, a series of tasks from data collection to analysis and document creation are performed manually, resulting in a significant burden in terms of time and effort. It is also difficult to objectively evaluate the operational status of an agency and make appropriate improvement proposals based on that evaluation. The present invention aims to solve these problems by providing a system that automatically provides efficient and objective evaluations and proposals.

[0057] 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.

[0058] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using a generative AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, and means for providing the generated negotiation materials to a terminal. This makes it possible to quickly and accurately evaluate the agent data and automatically generate negotiation materials based on the evaluation.

[0059] A "database" is a system for efficiently storing, managing, and searching various types of data.

[0060] "Agency Data" means a collection of data including information such as agency sales, customer satisfaction, marketing spend, and performance scores.

[0061] "Generative AI Model" refers to an artificial intelligence model used to analyze agency data and predict specific outcomes.

[0062] The "condition score" is a numerical representation of the operating condition of an agency, calculated based on various indicators.

[0063] "Negotiation Materials" means documents to be used in negotiation activities, which include an Agent's Condition Score and improvement actions.

[0064] "Terminal" refers to a device used by a user, such as a computer or smartphone.

[0065] The present invention is a system that uses agent data to predict condition scores using a generative AI model and generates sales negotiation materials based on the results. This system consists of multiple steps involving a server, terminals, and users.

[0066] The server first retrieves agency data from a database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundation for a detailed understanding of the agency's operational status. SQL (Structured Query Language) is used to retrieve data from the database.

[0067] The server then inputs the acquired agency data into a generative AI model to predict a condition score. This process uses the Python language and the TENSORFLOW (registered trademark) library. A linear regression model is used as the generative AI model. This model can be used to analyze agency data and quantify the operating condition of each agency.

[0068] Based on the predicted condition scores, the server generates sales documents. These documents include each agent's condition score and improvement actions based on that score. For example, for agents with low condition scores, the server suggests improvement actions such as "improving customer satisfaction is necessary," while for agents with high condition scores, it includes recommendations such as "strengthening sales activities would be effective." The Python-docx library is used to generate sales documents. Using this library, it is possible to automatically generate documents in Word format.

[0069] The user conducts sales negotiations using the sales negotiation materials generated by the server. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. This is expected to improve the quality of sales negotiations and the performance of agencies.

[0070] As a concrete example, let's say an agency's data looks like this:

[0071] Sales: 1000

[0072] Customer Satisfaction Rating: 70

[0073] Marketing expenditure: 200

[0074] Performance score: 80

[0075] The server inputs this data into the model and calculates a predicted condition score of 80. Based on this score, the server generates a sales document stating, "Strengthening sales activities would be effective." Based on this document, the user can propose specific measures to the agent during sales negotiations, such as "Strengthening sales activities is important."

[0076] Here are some example prompts to input to a generative AI model:

[0077] Agency A's data:

[0078] Sales: 1000

[0079] Customer Satisfaction Rating: 70

[0080] Marketing expenditure: 200

[0081] Performance score: 80

[0082] Use this data to predict your condition score.

[0083] In this way, the present invention makes it possible to efficiently and objectively evaluate agent data and automatically generate sales negotiation materials based on the results. This process reduces the user's workload and improves the effectiveness of sales negotiations.

[0084] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0085] Step 1:

[0086] The server retrieves agency data from the database. The server executes an SQL query to retrieve "Sales", "Customer Satisfaction", "Marketing Spend", and "Performance Score" data from the database. The input is the agency ID, and the output is a set of corresponding agency data. Specifically, the server sends the following SQL query:

[0087] sql

[0088] SELECT sales, customer_satisfaction, marketing_spend, performance_score FROM agency_data WHERE agency_id = 'A';

[0089] Step 2:

[0090] The server inputs the acquired agency data into a generative AI model to predict a condition score. The server uses Python and TensorFlow to input data into a linear regression model to predict a condition score. The input is the agency data acquired in step 1, and the output is the condition score. Specifically, the server supplies data to the model as follows:

[0091] python

[0092] data = [[1000, 70, 200, 80]] Agency data

[0093] predicted_score = model.predict(data) Predicted condition score

[0094] Step 3:

[0095] The server generates sales documents using the predicted condition scores. The server uses the Python-docx library to generate sales documents in document format. The input is the condition score obtained in step 2, and the output is the sales documents. Specifically, the server creates the documents as follows:

[0096] python

[0097] doc = Document()

[0098] doc.add_heading('Opportunity materials', 0)

[0099] doc.add_paragraph(f'Agent A's condition score: {predicted_score[0][0]}')

[0100] if predicted_score[0][0] < 50:

[0101] doc.add_paragraph('We need to improve customer satisfaction.')

[0102] else:

[0103] doc.add_paragraph('Strengthening sales activities will be effective.')

[0104] doc.save('Business negotiation material_Agency A.docx')

[0105] Step 4:

[0106] The server provides the generated sales documents to the terminal. The terminal provides an interface for the user to access, allowing them to view or download the sales documents sent from the server. The input is the file path of the sales documents generated in step 3, and the output is the sales documents displayed on the user's terminal. Specifically, the server sends the path to the generated file to the terminal, which receives and displays it.

[0107] Through this series of processes, the user can efficiently evaluate the operating status of the agency and make improvement proposals based on appropriate business negotiation materials.

[0108] (Application example 1)

[0109] 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."

[0110] While there are improvement proposals based on data analysis by agents to improve the efficiency of traditional sales activities, there is a lack of effective performance evaluations and improvement proposals for brick-and-mortar store operations. In particular, there is a lack of detailed performance evaluations using brick-and-mortar store operation data and concrete action plans based on those evaluations. This makes it difficult for brick-and-mortar store operators to quickly implement appropriate improvement measures.

[0111] 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.

[0112] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using an AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, and means for acquiring store operation data, predicting a store's condition score using the data, and proposing improvement actions for the store operation based on the predicted score. This makes it possible to evaluate the operation status of each agent and physical store in detail and objectively, and to propose effective improvement proposals based on the evaluation.

[0113] Definitions of important words

[0114] “Agency Data” means data used to gain insight into the operations of an Agency, including sales, customer satisfaction, marketing spend, and performance scores.

[0115] "Database" refers to a data storage system that stores agency data and store operation data and can be accessed as needed.

[0116] An "AI model" is a mathematical and statistical tool that uses artificial intelligence techniques to analyze data and predict a particular outcome, such as a condition score.

[0117] The "condition score" is a numerical indicator of the operating status of an agency or store, and is predicted by an AI model based on various data.

[0118] A "sales deck" is a document generated based on the predicted condition score, including improvement actions and recommendations.

[0119] "Sales" means the total income earned through sales activities during a given period.

[0120] "Customer satisfaction" is a survey and evaluation of the degree of satisfaction that customers have with products and services.

[0121] "Marketing expenditure" is the total amount spent on marketing activities.

[0122] "Performance Score" is a comprehensive score that evaluates the performance of an agency or store based on multiple indicators.

[0123] "Store Operations Data" means data relating to the operation of physical stores, including sales, customer satisfaction, marketing expenditures, and performance scores.

[0124] "Improvement Action" is a specific action plan proposed based on the predicted condition score to improve the operating condition of the agency or store.

[0125] MODE FOR CARRYING OUT THE INVENTION

[0126] The present invention is a system that evaluates the operational status of agencies and brick-and-mortar stores and automatically generates improvement proposals. This system is composed of multiple steps involving a server, terminals, and users.

[0127] The server first retrieves agent and store operation data from the database. This data includes sales, customer satisfaction, marketing expenditures, and performance scores. Based on this data, the server uses an AI model to predict the condition scores of agents and stores. Specifically, it implements a linear regression model using Python and the Scikit-learn library to analyze the data and calculate the condition scores.

[0128] On the user device side, a front-end application is developed using JavaScript (registered trademark) and React Native. The condition score predicted by the server and improvement actions based on it are sent to the front-end application, where users can view them and take appropriate improvement actions.

[0129] The server then automatically generates sales materials based on the predicted condition scores. These sales materials include the condition scores for each store and specific improvement actions based on those scores. For example, if the condition score is low, the suggestion may be, "You need to improve customer satisfaction," while if the score is high, the recommendation may be, "Strengthening sales activities would be effective."

[0130] For example, if a store's sales are 1000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server will predict the condition score to be 75 based on this data. In this case, the sales materials will include a statement such as "Strengthening sales activities would be effective." The following prompt sentence will also be generated:

[0131] If a store has sales of 1000, customer satisfaction of 70, marketing spend of 200, and a performance score of 80, the predicted condition score is 75. Increased sales efforts would be beneficial.

[0132] This allows the server and terminal to analyze data efficiently and objectively, and provide users with specific actions based on the results. By using this system, the operational status of agencies and physical stores can be properly evaluated, and actionable improvement proposals can be quickly received.

[0133] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0134] Program processing steps

[0135] Step 1: Data Acquisition

[0136] The server retrieves agency data and store operations data from the database, including sales, customer satisfaction, marketing expenditures, and performance scores.

[0137] Input: Database connection information

[0138] Output: Agency data and store operation data

[0139] What it does: The server connects to the MySQL database and retrieves the required data.

[0140] Step 2: Data analysis

[0141] The server inputs the acquired data into an AI model to predict a condition score. Specifically, it analyzes the data using a linear regression model.

[0142] Input: Agency data and store operation data

[0143] Output: Condition score

[0144] How it works: The server runs a linear regression model using Python and Scikit-learn to calculate a condition score based on the input data.

[0145] Step 3: Generate sales documents

[0146] The server generates sales documents based on the predicted condition scores, which include the condition scores of each agency and store and the improvement actions based on the scores.

[0147] Input: Condition Score

[0148] Output: Sales documents

[0149] What it does: The server generates a sales deck in HTML or PDF format, including the appropriate content.

[0150] Step 4: Send data

[0151] The server transmits the generated business negotiation materials and condition scores to the user terminal.

[0152] Input: Sales documents, condition score

[0153] Output: Sending data to the user's terminal

[0154] How it works: The server sends data using the HTTP protocol and displays it on the user's terminal.

[0155] Step 5: User Views and Actions

[0156] The user terminal displays the received business negotiation materials and condition score, and the user takes improvement action based on this.

[0157] Input: Sales documents, condition score

[0158] Output: Displayed sales documents, user actions

[0159] How it works: The front-end application (React Native) displays the data, and the user can view and interact with it.

[0160] Step 6: Improvement Action Feedback

[0161] Based on the improvement actions taken by the user, new data is acquired and fed back to the server, which uses this data for future analysis and to improve the accuracy of predictions.

[0162] Input: Improvement action result

[0163] Output: Feedback data

[0164] How it works: A user inputs feedback data through a smartphone application and sends it to a server.

[0165] This allows the server and terminal to exchange data with each other, enabling detailed evaluation of the operational status of agencies and physical stores and providing appropriate improvement proposals.

[0166] 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.

[0167] This system uses agent data to predict condition scores using an AI model and generates sales documents based on the results. It also provides a function to adjust the content of sales documents based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user.

[0168] The server first retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundational data for a detailed understanding of the agency's operating condition. The server then inputs the retrieved agency data into an AI model to predict a condition score. Specifically, the server uses a linear regression model to analyze the data and quantify each agency's operating condition.

[0169] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0170] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. The emotion engine runs on the device and recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine identifies various emotional states, such as when the user is stressed or relaxed. The server uses the emotion data obtained from the emotion engine to adjust the content of sales documents. For example, if the user is stressed, the server generates sales documents using softer expressions, and if the user is relaxed, the server provides sales documents with detailed action plans.

[0171] The user uses the sales documents generated by the server to conduct sales negotiations. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. In addition, the sales documents provided correspond to the user's emotional state, enabling more effective communication.

[0172] As a concrete example, let's say an agency's data looks like this:

[0173] If Agent A's sales are 1,000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server uses an AI model based on this data to predict a condition score. In this case, the condition score is predicted to be 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0174] Furthermore, if the user's emotion engine determines that the user is relaxed as a result of its analysis, the server provides negotiation materials including a detailed action plan. Conversely, if the server determines that the user is stressed, the server generates negotiation materials with simpler, more positive content. In this way, the present invention enables efficient and objective evaluation of agent data and the provision of negotiation materials that correspond to the user's emotional state. This reduces the user's workload and improves the effectiveness of negotiations.

[0175] The processing flow will be explained below.

[0176] Step 1:

[0177] The server retrieves agency data from the database. The server connects to the database and loads data including agency sales, customer satisfaction, marketing expenditures, and performance scores, thereby obtaining detailed operational information for the agency.

[0178] Step 2:

[0179] The server preprocesses the acquired agency data and formats it into a format suitable for the AI ​​model. The server extracts necessary items from the loaded data and sets sales, customer satisfaction, and marketing expenditures as features. It also sets performance scores as targets.

[0180] Step 3:

[0181] The server uses the shaped data to train the AI ​​model. In this step, the server instantiates a linear regression model and trains it using features and targets. The model learns patterns from the agency's data and uses them to make future predictions.

[0182] Step 4:

[0183] The server uses the trained model to predict the condition score of each agent. The server inputs the features of each agent into the model and calculates the condition score. The predicted condition score is a numerical representation of the operating condition of each agent.

[0184] Step 5:

[0185] The server generates sales documents based on the predicted condition scores. Based on each agent's condition score, the server creates sales documents that include improvement actions. For example, if the condition score is low, the server suggests "improving customer satisfaction is necessary," and if the score is high, the server suggests "strengthening sales activities would be effective."

[0186] Step 6:

[0187] The device runs an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice and facial expressions to determine their emotional state. For example, it detects whether the user is relaxed or stressed.

[0188] Step 7:

[0189] The server uses the emotion data obtained from the emotion engine to adjust the content of the sales materials. The server takes into account the user's emotional state and generates materials with detailed action plans if the user is relaxed, and materials with simple, positive content if the user is stressed.

[0190] Step 8:

[0191] The user obtains the sales negotiation materials generated by the server and uses them in sales negotiation activities. The user can use the sales negotiation materials to evaluate the operating status of each agency and propose appropriate improvement actions. In addition, the sales negotiation materials are provided according to the user's emotional state, allowing for more effective communication.

[0192] In this way, the embodiment divided into processing steps realizes efficient evaluation of agent data and provision of negotiation materials based on the user's emotions, thereby reducing the user's workload and improving the effectiveness of negotiations.

[0193] Example 2

[0194] 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."

[0195] Conventional sales negotiation materials generation systems only generate static materials based on agency data, making it difficult to maximize the efficiency and effectiveness of sales negotiations. Furthermore, they provide uniform materials without considering the user's emotional state, which can cause stress and reduce efficiency. Therefore, there is a growing need for a system that can flexibly adjust the content of sales negotiations according to the agency's operational status and the user's emotions.

[0196] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0197] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using a generative AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, means for acquiring emotion data from a terminal including an emotion engine for analyzing a user's emotion, and means for adjusting the content of the negotiation materials based on the emotion data. This makes it possible to flexibly adjust the negotiation materials according to the operating status of the agent and the emotional state of the user, thereby maximizing the efficiency and effectiveness of negotiations.

[0198] "Agency Data" means data including agency sales, customer satisfaction, marketing spend, and performance scores.

[0199] "Generative AI Model" means an artificial intelligence model used to predict a Condition Score based on acquired agency data, and specifically includes a linear regression model.

[0200] "Condition Score" is a numerical value that indicates the operating condition of an agency, predicted using a generative AI model.

[0201] "Sales Decision Document" means a document containing improvement actions and recommendations to an agency that is generated based on a predicted condition score.

[0202] An "emotion engine" is an engine installed in a terminal that analyzes the user's voice and facial expressions to analyze emotional data.

[0203] A "terminal" is a device that collects user emotion data and runs an emotion engine, and provides business negotiation materials in cooperation with a server.

[0204] "Emotion data" is data that indicates the user's emotional state, analyzed using an emotion engine.

[0205] MODE FOR CARRYING OUT THE INVENTION

[0206] This system uses agent data to predict condition scores using an AI model and generates sales documents based on the results. It also provides a function to adjust the content of sales documents based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user.

[0207] Data acquisition and analysis

[0208] The server first retrieves agency data from a database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. Specifically, the data is retrieved using database software such as MySQL or PostgreSQL. This data provides the basis for evaluating performance. The server then formats the retrieved agency data and converts it into a format that can be input into the AI ​​model. This task is typically performed using the Python pandas library.

[0209] Condition score prediction by AI model

[0210] The server inputs the formatted data into a generative AI model to predict a condition score. A linear regression model is used as the generative AI model. For example, a pre-trained model can be used using a machine learning library such as scikit-learn. The model quantifies the operating condition of the agency based on the acquired data.

[0211] Generate sales documents

[0212] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0213] Acquiring emotion data

[0214] The device recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine uses libraries such as TensorFlow and OpenCV to analyze audio and video data. The device uses this hardware and software to identify emotional states in real time. When the user is in front of the device, their facial expressions and speech are captured by the camera and microphone, and analyzed by the emotion engine.

[0215] Adjustment of business documents

[0216] The server receives the emotion data sent from the device and adjusts the content of the sales meeting materials. For example, if the user is feeling stressed, the server generates sales meeting materials using softer expressions, and if the user is relaxed, the server provides sales meeting materials including a detailed action plan. In this way, the sales meeting materials are dynamically adjusted according to the user's current emotional state.

[0217] User Use

[0218] The user uses the sales documents generated by the server to conduct sales negotiations. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. In addition, the sales documents provided correspond to the user's emotional state, enabling more effective communication.

[0219] Specific examples

[0220] For example, suppose Agency A's data looks like this:

[0221] If sales are 1,000, customer satisfaction is 70, marketing expenditures are 200, and the performance score is 80, the server uses this data to predict a condition score using a generative AI model. In this case, the predicted condition score is 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0222] Furthermore, if the user's emotion engine determines that the user is relaxed, the server will provide sales materials with detailed action plans. Conversely, if the server determines that the user is stressed, the server will generate simpler, more positive sales materials.

[0223] Prompt Sentence Examples

[0224] Here are some examples of prompts to input to a generative AI model:

[0225] Data for Agent A: Sales = 1000, Customer Satisfaction = 70, Marketing Expenditure = 200, Performance Score = 80. Based on this data, predict the condition score and generate sales materials. Also, adjust the content of the materials based on the user's emotional state as "Relaxed."

[0226] conclusion

[0227] As a result, the present invention can efficiently and objectively evaluate agent data and provide negotiation materials that correspond to the user's emotional state, thereby reducing the user's workload and improving the effectiveness of negotiations.

[0228] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0229] Step 1: Data Acquisition

[0230] The server retrieves agency data from a database. This data includes agency sales, customer satisfaction, marketing spend, and performance scores. It uses database software such as MySQL or PostgreSQL. As input, it takes a specific agency ID and as output, it gets the corresponding agency data. The specific operation is to execute an SQL query to retrieve the data.

[0231] ...

[0232] sql

[0233] SELECT sales, customer_satisfaction, marketing_spend, performance_score FROM agencies WHERE agency_id = 'A';

[0234] Step 2: Data analysis

[0235] The server formats the acquired agency data and converts it into a format suitable for input to the generative AI model. This is done using the Python pandas library. The acquired agency data is used as input, and the output is data that has been formatted in a format suitable for input to the AI ​​model. For example, the data is converted into a data frame and appropriately scaled.

[0236] The specific operation is to create a data frame using pandas and scale the data using a standard scaler.

[0237] ...

[0238] python

[0239] import pandas as pd

[0240] from sklearn.preprocessing import StandardScaler

[0241] data = {'sales':

[1000] , 'customer_satisfaction':

[70] , 'marketing_spend':

[0200] , 'performance_score':

[80] }

[0242] df = pd.DataFrame(data)

[0243] scaler = StandardScaler()

[0244] scaled_data = scaler.fit_transform(df)

[0245] Step 3: Condition Score Prediction

[0246] The server inputs the formatted data into a generative AI model to predict a condition score. A linear regression model is used as the generative AI model. The scaled data is used as input, and the predicted condition score is obtained as output. The specific operation is to make a prediction using a pre-trained linear regression model.

[0247] ...

[0248] python

[0249] from sklearn.linear_model import LinearRegression

[0250] Use a pre-trained model (training steps omitted)

[0251] model = LinearRegression()

[0252] model.fit(training_data, target) Model training part (example)

[0253] condition_score = model.predict(scaled_data)

[0254] Step 4: Generate sales documents

[0255] The server generates sales materials based on the predicted condition scores. The materials include each agent's condition score and improvement actions based on the condition scores. The predicted condition scores are used as input, and the generated sales materials are obtained as output. The specific operation is to implement logic that generates different messages based on the condition scores.

[0256] ...

[0257] python

[0258] if condition_score >= 75:

[0259] suggestion = "Strengthening sales activities would be effective"

[0260] else:

[0261] suggestion = "Customer satisfaction needs to be improved"

[0262] document = f"Agency A's condition score is {condition_score}. {suggestion}"

[0263] Step 5: Acquire emotion data

[0264] The device recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine uses libraries such as TensorFlow and OpenCV to analyze audio and video data. The user's audio and video data are used as input, and the identified user's emotion data is obtained as output. Specifically, data is acquired using a camera or microphone, and the emotion engine analyzes it.

[0265] ...

[0266] python

[0267] import cv2

[0268] import tensorflow as tf

[0269] cap = cv2.VideoCapture(0)

[0270] _, frame = cap.read()

[0271] emotion_model = tf.keras.models.load_model('emotion_model.h5')

[0272] emotion_prediction = emotion_model.predict(frame)

[0273] Step 6: Adjust the sales materials

[0274] The server adjusts the content of the sales documents based on the emotion data received from the device. It uses emotion data and existing sales documents as input, and obtains adjusted sales documents as output. Specifically, it softens the expressions in the documents or adds details depending on the emotion data.

[0275] ...

[0276] python

[0277] if emotion_prediction == 'stress':

[0278] document = f"Agency A's condition score is {condition_score}. Trimmed to be simple: {suggestion}"

[0279] else:

[0280] document = f"Agency A's condition score is {condition_score}. Includes detailed action plan: {suggestion}"

[0281] Step 7: Provide business documents

[0282] The user checks the sales negotiation materials generated by the server and uses them in sales negotiation activities. The adjusted sales negotiation materials are used as input, and the sales negotiation is conducted as output. The specific operation is to check the materials provided by the server on the terminal.

[0283] ...

[0284] python

[0285] print(document) Display the generated sales document

[0286] (Application example 2)

[0287] 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."

[0288] Conventional sales negotiation systems using agency data can evaluate the operational status of each agency, but they do not support the generation of sales negotiation materials that take the user's emotional state into account, making effective communication difficult. Furthermore, real-time information based on the user's emotional state is required for quick business decisions. To solve this problem, a system is needed that can comprehensively evaluate operational status based on agency data and generate sales negotiation materials that correspond to the user's emotional state.

[0289] 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.

[0290] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using an AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, means for recognizing a user's emotion from voice data, and means for adjusting the content of the negotiation materials based on the recognized emotion, thereby enabling efficient and objective evaluation of the agent data and provision of negotiation materials according to the user's emotional state.

[0291] "Agency Data" means data such as sales, customer satisfaction, marketing spend, and performance scores used to evaluate the operations of an agency.

[0292] A "database" is a system for systematically storing and managing information such as agency data.

[0293] An "AI model" is a mathematical and computational model that uses artificial intelligence technology to analyze and predict data.

[0294] The "condition score" is a numerical indicator of the operating condition of an agency, and is calculated based on various data.

[0295] "Negotiation Materials" means materials that include an agency's condition score and improvement actions and recommendations based thereon.

[0296] "Voice data" is digital data that records voice and is used to recognize the user's emotions.

[0297] An "emotion engine" is software that analyzes voice data, facial expression data, etc. to recognize the user's emotional state.

[0298] A "means" is a method or device for achieving a specific function or purpose.

[0299] The present invention is a system that uses agency data to predict condition scores using an AI model and generates sales materials based on the results. It also includes a function that adjusts the content of sales materials based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user. The server generates and adjusts sales materials using agency data and user emotion data obtained from a database.

[0300] First, the server retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores, providing basic data for a detailed understanding of the agency's operating condition. Next, the server inputs the retrieved agency data into an AI model to predict a condition score. The AI ​​model uses a linear regression model, which quantifies the agency's operating condition.

[0301] The server then generates a sales document based on the predicted condition scores, which includes each agent's condition score and the associated improvement actions.

[0302] Furthermore, an emotion engine runs on the device and analyzes voice data to recognize the user's emotions. The Python library speech_recognition is used for voice recognition, and a transformers pipeline is used for emotion identification. It can identify various emotional states, such as whether the user is stressed or relaxed.

[0303] The server then adjusts the content of the sales presentation materials based on the emotion recognition results. For example, if the user is stressed, the presentation materials will use softer language. On the other hand, if the user is relaxed, the presentation materials will include a detailed action plan.

[0304] As a specific example, if a certain agency's data shows "shipping speed 800, misshipment rate 60, inventory status 150, and productivity score 85," the server predicts the condition score based on this data and calculates the result as "75." Based on this score, sales documents are generated that suggest improvement actions, such as "Improving shipping speed would be effective." Furthermore, if the user's voice data indicates that they are feeling stressed, the server adds the message, "Consider allocating personnel to reduce the workload."

[0305] In this way, the present invention realizes efficient and objective evaluation of agent data and provision of negotiation materials according to the user's emotional state, thereby reducing the user's workload and improving the effectiveness of negotiations.

[0306] An example prompt would be, "Predict the operational condition score for logistics center A based on its shipping speed, misshipment rate, inventory status, and productivity score, and generate improvement suggestions based on the manager's emotional state."

[0307] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0308] Step 1:

[0309] The server retrieves agency data from the database, including sales, customer satisfaction, marketing expenditures, and performance scores. The agency data is taken as input and used for subsequent analysis.

[0310] Step 2:

[0311] The server inputs the acquired agency data into an AI model to predict the agency's condition score. Here, a linear regression model is used to analyze the data. The input is the agency data, and the output is the condition score.

[0312] Step 3:

[0313] The server generates sales documents based on the predicted condition scores, which include improvement actions and recommendations for each agent depending on the condition score. The input is the condition score, and the sales documents are generated as the output.

[0314] Step 4:

[0315] The emotion engine installed on the device recognizes emotions from the user's voice data. Here, we use the speech_recognition and transformers pipeline. The input is the user's voice data, and the output is the user's recognized emotional state.

[0316] Step 5:

[0317] The server adjusts the content of the sales documents based on the recognized emotional state. For example, if the user is feeling stressed, the sales documents are adjusted to use softer expressions. The input is the emotional state and the sales documents, and the adjusted sales documents are obtained as the output.

[0318] Step 6:

[0319] The user conducts business negotiations using the business negotiation materials generated and adjusted by the server. Here, the user proceeds while checking proposals based on the operational status of each agency and business negotiation materials that correspond to the user's emotional state. The input is the business negotiation materials, and the user uses them to conduct business negotiations as the output.

[0320] 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.

[0321] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0322] 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.

[0323] [Second embodiment]

[0324] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0325] 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.

[0326] 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).

[0327] 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.

[0328] 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.

[0329] 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).

[0330] 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.

[0331] 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.

[0332] 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.

[0333] 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.

[0334] 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.

[0335] 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."

[0336] This system uses data from agents to predict condition scores using an AI model and generates sales negotiation materials based on the results. This system is composed of multiple steps involving a server, terminals, and users.

[0337] The server first retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundational data for a detailed understanding of the agency's operating condition. The server then inputs the retrieved agency data into an AI model to predict a condition score. Specifically, the server uses a linear regression model to analyze the data and quantify each agency's operating condition.

[0338] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0339] The user conducts sales negotiations using the sales negotiation materials generated by the server. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. This is expected to improve the quality of sales negotiations and the performance of agencies.

[0340] As a concrete example, let's say an agency's data looks like this:

[0341] If Agent A's sales are 1,000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server uses an AI model based on this data to predict a condition score. In this case, the condition score is predicted to be 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0342] In this way, the present invention makes it possible to efficiently and objectively evaluate agent data and automatically generate sales negotiation materials based on the results. This process reduces the user's workload and improves the effectiveness of sales negotiations.

[0343] The processing flow will be explained below.

[0344] Step 1:

[0345] The server retrieves agency data from the database: In this step, the server connects to the database and loads the agency data, which includes data such as sales, customer satisfaction, marketing spend, performance scores, etc. For example, it may load the data from a CSV file using the Pandas library.

[0346] Step 2:

[0347] The server preprocesses the acquired agency data and formats it into a format suitable for the AI ​​model. In this step, the server selects necessary columns from the loaded data and separates them into features (sales, customer satisfaction, marketing expenditures) and targets (performance scores).

[0348] Step 3:

[0349] The server uses the shaped data to train an AI model. Specifically, the server instantiates a linear regression model and trains it using features and targets. The goal of this step is to learn patterns from the data and use them to make future predictions.

[0350] Step 4:

[0351] The server uses the trained model to predict the condition score of each agent. In this step, the server inputs the features of each agent into the model and outputs a condition score. The predicted score is a numerical representation of each agent's performance.

[0352] Step 5:

[0353] The server generates sales materials based on the predicted condition scores. In this step, the server determines the content of the sales materials based on the condition scores of each agent. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high score, it includes a recommendation such as "strengthening sales activities would be effective."

[0354] Step 6:

[0355] The user can obtain the generated sales negotiation materials and use them in sales negotiations. By using the sales negotiation materials provided by the server, the user can objectively evaluate the performance of each agent and propose appropriate improvement actions, thereby effectively promoting sales negotiation activities.

[0356] Example 1

[0357] 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."

[0358] In conventional methods for creating sales negotiation materials, a series of tasks from data collection to analysis and document creation are performed manually, resulting in a significant burden in terms of time and effort. It is also difficult to objectively evaluate the operational status of an agency and make appropriate improvement proposals based on that evaluation. The present invention aims to solve these problems by providing a system that automatically provides efficient and objective evaluations and proposals.

[0359] 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.

[0360] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using a generative AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, and means for providing the generated negotiation materials to a terminal. This makes it possible to quickly and accurately evaluate the agent data and automatically generate negotiation materials based on the evaluation.

[0361] A "database" is a system for efficiently storing, managing, and searching various types of data.

[0362] "Agency Data" means a collection of data including information such as agency sales, customer satisfaction, marketing spend, and performance scores.

[0363] "Generative AI Model" refers to an artificial intelligence model used to analyze agency data and predict specific outcomes.

[0364] The "condition score" is a numerical representation of the operating condition of an agency, calculated based on various indicators.

[0365] "Negotiation Materials" means documents to be used in negotiation activities, which include an Agent's Condition Score and improvement actions.

[0366] "Terminal" refers to a device used by a user, such as a computer or smartphone.

[0367] The present invention is a system that uses agent data to predict condition scores using a generative AI model and generates sales negotiation materials based on the results. This system consists of multiple steps involving a server, terminals, and users.

[0368] The server first retrieves agency data from a database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundation for a detailed understanding of the agency's operational status. SQL (Structured Query Language) is used to retrieve data from the database.

[0369] The server then inputs the acquired agency data into a generative AI model to predict a condition score. This process uses the Python language and TensorFlow library. A linear regression model is used as the generative AI model. This model can be used to analyze agency data and quantify the operating condition of each agency.

[0370] Based on the predicted condition scores, the server generates sales documents. These documents include each agent's condition score and improvement actions based on that score. For example, for agents with low condition scores, the server suggests improvement actions such as "improving customer satisfaction is necessary," while for agents with high condition scores, it includes recommendations such as "strengthening sales activities would be effective." The Python-docx library is used to generate sales documents. Using this library, it is possible to automatically generate documents in Word format.

[0371] The user conducts sales negotiations using the sales negotiation materials generated by the server. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. This is expected to improve the quality of sales negotiations and the performance of agencies.

[0372] As a concrete example, let's say an agency's data looks like this:

[0373] Sales: 1000

[0374] Customer Satisfaction Rating: 70

[0375] Marketing expenditure: 200

[0376] Performance score: 80

[0377] The server inputs this data into the model and calculates a predicted condition score of 80. Based on this score, the server generates a sales document stating, "Strengthening sales activities would be effective." Based on this document, the user can propose specific measures to the agent during sales negotiations, such as "Strengthening sales activities is important."

[0378] Here are some example prompts to input to a generative AI model:

[0379] Agency A's data:

[0380] Sales: 1000

[0381] Customer Satisfaction Rating: 70

[0382] Marketing expenditure: 200

[0383] Performance score: 80

[0384] Use this data to predict your condition score.

[0385] In this way, the present invention makes it possible to efficiently and objectively evaluate agent data and automatically generate sales negotiation materials based on the results. This process reduces the user's workload and improves the effectiveness of sales negotiations.

[0386] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0387] Step 1:

[0388] The server retrieves agency data from the database. The server executes an SQL query to retrieve "Sales", "Customer Satisfaction", "Marketing Spend", and "Performance Score" data from the database. The input is the agency ID, and the output is a set of corresponding agency data. Specifically, the server sends the following SQL query:

[0389] sql

[0390] SELECT sales, customer_satisfaction, marketing_spend, performance_score FROM agency_data WHERE agency_id = 'A';

[0391] Step 2:

[0392] The server inputs the acquired agency data into a generative AI model to predict a condition score. The server uses Python and TensorFlow to input data into a linear regression model to predict a condition score. The input is the agency data acquired in step 1, and the output is the condition score. Specifically, the server supplies data to the model as follows:

[0393] python

[0394] data = [[1000, 70, 200, 80]] Agency data

[0395] predicted_score = model.predict(data) Predicted condition score

[0396] Step 3:

[0397] The server generates sales documents using the predicted condition scores. The server uses the Python-docx library to generate sales documents in document format. The input is the condition score obtained in step 2, and the output is the sales documents. Specifically, the server creates the documents as follows:

[0398] python

[0399] doc = Document()

[0400] doc.add_heading('Opportunity materials', 0)

[0401] doc.add_paragraph(f'Agent A's condition score: {predicted_score[0][0]}')

[0402] if predicted_score[0][0] < 50:

[0403] doc.add_paragraph('We need to improve customer satisfaction.')

[0404] else:

[0405] doc.add_paragraph('Strengthening sales activities will be effective.')

[0406] doc.save('Business negotiation material_Agency A.docx')

[0407] Step 4:

[0408] The server provides the generated sales documents to the terminal. The terminal provides an interface for the user to access, allowing them to view or download the sales documents sent from the server. The input is the file path of the sales documents generated in step 3, and the output is the sales documents displayed on the user's terminal. Specifically, the server sends the path to the generated file to the terminal, which receives and displays it.

[0409] Through this series of processes, the user can efficiently evaluate the operating status of the agency and make improvement proposals based on appropriate business negotiation materials.

[0410] (Application example 1)

[0411] 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."

[0412] While there are improvement proposals based on data analysis by agents to improve the efficiency of traditional sales activities, there is a lack of effective performance evaluations and improvement proposals for brick-and-mortar store operations. In particular, there is a lack of detailed performance evaluations using brick-and-mortar store operation data and concrete action plans based on those evaluations. This makes it difficult for brick-and-mortar store operators to quickly implement appropriate improvement measures.

[0413] 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.

[0414] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using an AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, and means for acquiring store operation data, predicting a store's condition score using the data, and proposing improvement actions for the store operation based on the predicted score. This makes it possible to evaluate the operation status of each agent and physical store in detail and objectively, and to propose effective improvement proposals based on the evaluation.

[0415] Definitions of important words

[0416] “Agency Data” means data used to gain insight into the operations of an Agency, including sales, customer satisfaction, marketing spend, and performance scores.

[0417] "Database" refers to a data storage system that stores agency data and store operation data and can be accessed as needed.

[0418] An "AI model" is a mathematical and statistical tool that uses artificial intelligence techniques to analyze data and predict a particular outcome, such as a condition score.

[0419] The "condition score" is a numerical indicator of the operating status of an agency or store, and is predicted by an AI model based on various data.

[0420] A "sales deck" is a document generated based on the predicted condition score, including improvement actions and recommendations.

[0421] "Sales" means the total income earned through sales activities during a given period.

[0422] "Customer satisfaction" is a survey and evaluation of the degree of satisfaction that customers have with products and services.

[0423] "Marketing expenditure" is the total amount spent on marketing activities.

[0424] "Performance Score" is a comprehensive score that evaluates the performance of an agency or store based on multiple indicators.

[0425] "Store Operations Data" means data relating to the operation of physical stores, including sales, customer satisfaction, marketing expenditures, and performance scores.

[0426] "Improvement Action" is a specific action plan proposed based on the predicted condition score to improve the operating condition of the agency or store.

[0427] MODE FOR CARRYING OUT THE INVENTION

[0428] The present invention is a system that evaluates the operational status of agencies and brick-and-mortar stores and automatically generates improvement proposals. This system is composed of multiple steps involving a server, terminals, and users.

[0429] The server first retrieves agent and store operation data from the database. This data includes sales, customer satisfaction, marketing expenditures, and performance scores. Based on this data, the server uses an AI model to predict the condition scores of agents and stores. Specifically, it implements a linear regression model using Python and the Scikit-learn library to analyze the data and calculate the condition scores.

[0430] On the user device side, a front-end application is developed using JavaScript and React Native. The condition score predicted by the server and the improvement actions based on it are sent to the front-end application, where users can view them and take appropriate improvement actions.

[0431] The server then automatically generates sales materials based on the predicted condition scores. These sales materials include the condition scores for each store and specific improvement actions based on those scores. For example, if the condition score is low, the suggestion may be, "You need to improve customer satisfaction," while if the score is high, the recommendation may be, "Strengthening sales activities would be effective."

[0432] For example, if a store's sales are 1000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server will predict the condition score to be 75 based on this data. In this case, the sales materials will include a statement such as "Strengthening sales activities would be effective." The following prompt sentence will also be generated:

[0433] If a store has sales of 1000, customer satisfaction of 70, marketing spend of 200, and a performance score of 80, the predicted condition score is 75. Increased sales efforts would be beneficial.

[0434] This allows the server and terminal to analyze data efficiently and objectively, and provide users with specific actions based on the results. By using this system, the operational status of agencies and physical stores can be properly evaluated, and actionable improvement proposals can be quickly received.

[0435] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0436] Program processing steps

[0437] Step 1: Data Acquisition

[0438] The server retrieves agency data and store operations data from the database, including sales, customer satisfaction, marketing expenditures, and performance scores.

[0439] Input: Database connection information

[0440] Output: Agency data and store operation data

[0441] What happens: The server connects to the MySQL database and retrieves the required data.

[0442] Step 2: Data analysis

[0443] The server inputs the acquired data into an AI model to predict a condition score. Specifically, it analyzes the data using a linear regression model.

[0444] Input: Agency data and store operation data

[0445] Output: Condition score

[0446] How it works: The server runs a linear regression model using Python and Scikit-learn to calculate a condition score based on the input data.

[0447] Step 3: Generate sales documents

[0448] The server generates sales documents based on the predicted condition scores, which include the condition scores of each agency and store and the improvement actions based on the scores.

[0449] Input: Condition Score

[0450] Output: Sales documents

[0451] What it does: The server generates a sales deck in HTML or PDF format, including the appropriate content.

[0452] Step 4: Send data

[0453] The server transmits the generated business negotiation materials and condition scores to the user terminal.

[0454] Input: Sales documents, condition score

[0455] Output: Sending data to the user's terminal

[0456] How it works: The server sends data using the HTTP protocol and displays it on the user's terminal.

[0457] Step 5: User Views and Actions

[0458] The user terminal displays the received business negotiation materials and condition score, and the user takes improvement action based on this.

[0459] Input: Sales documents, condition score

[0460] Output: Displayed sales documents, user actions

[0461] How it works: The front-end application (React Native) displays the data, and the user can view and interact with it.

[0462] Step 6: Improvement Action Feedback

[0463] Based on the improvement actions taken by the user, new data is acquired and fed back to the server, which uses this data for future analysis and to improve the accuracy of predictions.

[0464] Input: Improvement action result

[0465] Output: Feedback data

[0466] How it works: A user inputs feedback data through a smartphone application and sends it to a server.

[0467] This allows the server and terminal to exchange data with each other, enabling detailed evaluation of the operational status of agencies and physical stores and providing appropriate improvement proposals.

[0468] 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.

[0469] This system uses agent data to predict condition scores using an AI model and generates sales documents based on the results. It also provides a function to adjust the content of sales documents based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user.

[0470] The server first retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundational data for a detailed understanding of the agency's operating condition. The server then inputs the retrieved agency data into an AI model to predict a condition score. Specifically, the server uses a linear regression model to analyze the data and quantify each agency's operating condition.

[0471] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0472] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. The emotion engine runs on the device and recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine identifies various emotional states, such as when the user is stressed or relaxed. The server uses the emotion data obtained from the emotion engine to adjust the content of sales documents. For example, if the user is stressed, the server generates sales documents using softer expressions, and if the user is relaxed, the server provides sales documents with detailed action plans.

[0473] The user uses the sales documents generated by the server to conduct sales negotiations. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. In addition, the sales documents provided correspond to the user's emotional state, enabling more effective communication.

[0474] As a concrete example, let's say an agency's data looks like this:

[0475] If Agent A's sales are 1,000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server uses an AI model based on this data to predict a condition score. In this case, the condition score is predicted to be 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0476] Furthermore, if the user's emotion engine determines that the user is relaxed as a result of its analysis, the server provides negotiation materials including a detailed action plan. Conversely, if the server determines that the user is stressed, the server generates negotiation materials with simpler, more positive content. In this way, the present invention enables efficient and objective evaluation of agent data and the provision of negotiation materials that correspond to the user's emotional state. This reduces the user's workload and improves the effectiveness of negotiations.

[0477] The processing flow will be explained below.

[0478] Step 1:

[0479] The server retrieves agency data from the database. The server connects to the database and loads data including agency sales, customer satisfaction, marketing expenditures, and performance scores, thereby obtaining detailed operational information for the agency.

[0480] Step 2:

[0481] The server preprocesses the acquired agency data and formats it into a format suitable for the AI ​​model. The server extracts necessary items from the loaded data and sets sales, customer satisfaction, and marketing expenditures as features. It also sets performance scores as targets.

[0482] Step 3:

[0483] The server uses the shaped data to train the AI ​​model. In this step, the server instantiates a linear regression model and trains it using features and targets. The model learns patterns from the agency's data and uses them to make future predictions.

[0484] Step 4:

[0485] The server uses the trained model to predict the condition score of each agent. The server inputs the features of each agent into the model and calculates the condition score. The predicted condition score is a numerical representation of the operating condition of each agent.

[0486] Step 5:

[0487] The server generates sales documents based on the predicted condition scores. Based on each agent's condition score, the server creates sales documents that include improvement actions. For example, if the condition score is low, the server suggests "improving customer satisfaction is necessary," and if the score is high, the server suggests "strengthening sales activities would be effective."

[0488] Step 6:

[0489] The device runs an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice and facial expressions to determine their emotional state. For example, it detects whether the user is relaxed or stressed.

[0490] Step 7:

[0491] The server uses the emotion data obtained from the emotion engine to adjust the content of the sales materials. The server takes into account the user's emotional state and generates materials with detailed action plans if the user is relaxed, and materials with simple, positive content if the user is stressed.

[0492] Step 8:

[0493] The user obtains the sales negotiation materials generated by the server and uses them in sales negotiation activities. The user can use the sales negotiation materials to evaluate the operating status of each agency and propose appropriate improvement actions. In addition, the sales negotiation materials are provided according to the user's emotional state, allowing for more effective communication.

[0494] In this way, the embodiment divided into processing steps realizes efficient evaluation of agent data and provision of negotiation materials based on the user's emotions, thereby reducing the user's workload and improving the effectiveness of negotiations.

[0495] Example 2

[0496] 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."

[0497] Conventional sales negotiation materials generation systems only generate static materials based on agency data, making it difficult to maximize the efficiency and effectiveness of sales negotiations. Furthermore, they provide uniform materials without considering the user's emotional state, which can cause stress and reduce efficiency. Therefore, there is a growing need for a system that can flexibly adjust the content of sales negotiations according to the agency's operational status and the user's emotions.

[0498] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0499] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using a generative AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, means for acquiring emotion data from a terminal including an emotion engine for analyzing a user's emotion, and means for adjusting the content of the negotiation materials based on the emotion data. This makes it possible to flexibly adjust the negotiation materials according to the operating status of the agent and the emotional state of the user, thereby maximizing the efficiency and effectiveness of negotiations.

[0500] "Agency Data" means data including agency sales, customer satisfaction, marketing spend, and performance scores.

[0501] "Generative AI Model" means an artificial intelligence model used to predict a Condition Score based on acquired agency data, and specifically includes a linear regression model.

[0502] "Condition Score" is a numerical value that indicates the operating condition of an agency, predicted using a generative AI model.

[0503] "Sales Decision Document" means a document containing improvement actions and recommendations to an agency that is generated based on a predicted condition score.

[0504] An "emotion engine" is an engine installed in a terminal that analyzes the user's voice and facial expressions to analyze emotional data.

[0505] A "terminal" is a device that collects user emotion data and runs an emotion engine, and provides business negotiation materials in cooperation with a server.

[0506] "Emotion data" is data that indicates the user's emotional state, analyzed using an emotion engine.

[0507] MODE FOR CARRYING OUT THE INVENTION

[0508] This system uses agent data to predict condition scores using an AI model and generates sales documents based on the results. It also provides a function to adjust the content of sales documents based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user.

[0509] Data acquisition and analysis

[0510] The server first retrieves agency data from a database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. Specifically, the data is retrieved using database software such as MySQL or PostgreSQL. This data provides the basis for evaluating performance. The server then formats the retrieved agency data and converts it into a format that can be input into the AI ​​model. This task is typically performed using the Python pandas library.

[0511] Condition score prediction by AI model

[0512] The server inputs the formatted data into a generative AI model to predict a condition score. A linear regression model is used as the generative AI model. For example, a pre-trained model can be used using a machine learning library such as scikit-learn. The model quantifies the operating condition of the agency based on the acquired data.

[0513] Generate sales documents

[0514] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0515] Acquiring emotion data

[0516] The device recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine uses libraries such as TensorFlow and OpenCV to analyze audio and video data. The device uses this hardware and software to identify emotional states in real time. When the user is in front of the device, their facial expressions and speech are captured by the camera and microphone, and analyzed by the emotion engine.

[0517] Adjustment of business documents

[0518] The server receives the emotion data sent from the device and adjusts the content of the sales meeting materials. For example, if the user is feeling stressed, the server generates sales meeting materials using softer expressions, and if the user is relaxed, the server provides sales meeting materials including a detailed action plan. In this way, the sales meeting materials are dynamically adjusted according to the user's current emotional state.

[0519] User Use

[0520] The user uses the sales documents generated by the server to conduct sales negotiations. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. In addition, the sales documents provided correspond to the user's emotional state, enabling more effective communication.

[0521] Specific examples

[0522] For example, suppose Agency A's data looks like this:

[0523] If sales are 1,000, customer satisfaction is 70, marketing expenditures are 200, and the performance score is 80, the server uses this data to predict a condition score using a generative AI model. In this case, the predicted condition score is 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0524] Furthermore, if the user's emotion engine determines that the user is relaxed, the server will provide sales materials with detailed action plans. Conversely, if the server determines that the user is stressed, the server will generate simpler, more positive sales materials.

[0525] Prompt Sentence Examples

[0526] Here are some examples of prompts to input to a generative AI model:

[0527] Data for Agent A: Sales = 1000, Customer Satisfaction = 70, Marketing Expenditure = 200, Performance Score = 80. Based on this data, predict the condition score and generate sales materials. Also, adjust the content of the materials based on the user's emotional state as "Relaxed."

[0528] conclusion

[0529] As a result, the present invention can efficiently and objectively evaluate agent data and provide negotiation materials that correspond to the user's emotional state, thereby reducing the user's workload and improving the effectiveness of negotiations.

[0530] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0531] Step 1: Data Acquisition

[0532] The server retrieves agency data from a database. This data includes agency sales, customer satisfaction, marketing spend, and performance scores. It uses database software such as MySQL or PostgreSQL. As input, it takes a specific agency ID and as output, it gets the corresponding agency data. The specific operation is to execute an SQL query to retrieve the data.

[0533] ...

[0534] sql

[0535] SELECT sales, customer_satisfaction, marketing_spend, performance_score FROM agencies WHERE agency_id = 'A';

[0536] Step 2: Data analysis

[0537] The server formats the acquired agency data and converts it into a format suitable for input to the generative AI model. This is done using the Python pandas library. The acquired agency data is used as input, and the output is data that has been formatted in a format suitable for input to the AI ​​model. For example, the data is converted into a data frame and appropriately scaled.

[0538] The specific operation is to create a data frame using pandas and scale the data using a standard scaler.

[0539] ...

[0540] python

[0541] import pandas as pd

[0542] from sklearn.preprocessing import StandardScaler

[0543] data = {'sales':

[1000] , 'customer_satisfaction':

[70] , 'marketing_spend':

[0200] , 'performance_score':

[80] }

[0544] df = pd.DataFrame(data)

[0545] scaler = StandardScaler()

[0546] scaled_data = scaler.fit_transform(df)

[0547] Step 3: Condition Score Prediction

[0548] The server inputs the formatted data into a generative AI model to predict a condition score. A linear regression model is used as the generative AI model. The scaled data is used as input, and the predicted condition score is obtained as output. The specific operation is to make a prediction using a pre-trained linear regression model.

[0549] ...

[0550] python

[0551] from sklearn.linear_model import LinearRegression

[0552] Use a pre-trained model (training steps omitted)

[0553] model = LinearRegression()

[0554] model.fit(training_data, target) Model training part (example)

[0555] condition_score = model.predict(scaled_data)

[0556] Step 4: Generate sales documents

[0557] The server generates sales materials based on the predicted condition scores. The materials include each agent's condition score and improvement actions based on the condition scores. The predicted condition scores are used as input, and the generated sales materials are obtained as output. The specific operation is to implement logic that generates different messages based on the condition scores.

[0558] ...

[0559] python

[0560] if condition_score >= 75:

[0561] suggestion = "Strengthening sales activities would be effective"

[0562] else:

[0563] suggestion = "Customer satisfaction needs to be improved"

[0564] document = f"Agency A's condition score is {condition_score}. {suggestion}"

[0565] Step 5: Acquire emotion data

[0566] The device recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine uses libraries such as TensorFlow and OpenCV to analyze audio and video data. The user's audio and video data are used as input, and the identified user's emotion data is obtained as output. Specifically, data is acquired using a camera or microphone, and the emotion engine analyzes it.

[0567] ...

[0568] python

[0569] import cv2

[0570] import tensorflow as tf

[0571] cap = cv2.VideoCapture(0)

[0572] _, frame = cap.read()

[0573] emotion_model = tf.keras.models.load_model('emotion_model.h5')

[0574] emotion_prediction = emotion_model.predict(frame)

[0575] Step 6: Adjust the sales materials

[0576] The server adjusts the content of the sales documents based on the emotion data received from the device. It uses emotion data and existing sales documents as input, and obtains adjusted sales documents as output. Specifically, it softens the expressions in the documents or adds details depending on the emotion data.

[0577] ...

[0578] python

[0579] if emotion_prediction == 'stress':

[0580] document = f"Agency A's condition score is {condition_score}. Trimmed to be simple: {suggestion}"

[0581] else:

[0582] document = f"Agency A's condition score is {condition_score}. Includes detailed action plan: {suggestion}"

[0583] Step 7: Provide business documents

[0584] The user checks the sales negotiation materials generated by the server and uses them in sales negotiation activities. The adjusted sales negotiation materials are used as input, and the sales negotiation is conducted as output. The specific operation is to check the materials provided by the server on the terminal.

[0585] ...

[0586] python

[0587] print(document) Display the generated sales document

[0588] (Application example 2)

[0589] 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."

[0590] Conventional sales negotiation systems using agency data can evaluate the operational status of each agency, but they do not support the generation of sales negotiation materials that take the user's emotional state into account, making effective communication difficult. Furthermore, real-time information based on the user's emotional state is required for quick business decisions. To solve this problem, a system is needed that can comprehensively evaluate operational status based on agency data and generate sales negotiation materials that correspond to the user's emotional state.

[0591] 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.

[0592] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using an AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, means for recognizing a user's emotion from voice data, and means for adjusting the content of the negotiation materials based on the recognized emotion, thereby enabling efficient and objective evaluation of the agent data and provision of negotiation materials according to the user's emotional state.

[0593] "Agency Data" means data such as sales, customer satisfaction, marketing spend, and performance scores used to evaluate the operations of an agency.

[0594] A "database" is a system for systematically storing and managing information such as agency data.

[0595] An "AI model" is a mathematical and computational model that uses artificial intelligence technology to analyze and predict data.

[0596] The "condition score" is a numerical indicator of the operating condition of an agency, and is calculated based on various data.

[0597] "Negotiation Materials" means materials that include an agency's condition score and improvement actions and recommendations based thereon.

[0598] "Voice data" is digital data that records voice and is used to recognize the user's emotions.

[0599] An "emotion engine" is software that analyzes voice data, facial expression data, etc. to recognize the user's emotional state.

[0600] A "means" is a method or device for achieving a specific function or purpose.

[0601] The present invention is a system that uses agency data to predict condition scores using an AI model and generates sales materials based on the results. It also includes a function that adjusts the content of sales materials based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user. The server generates and adjusts sales materials using agency data and user emotion data obtained from a database.

[0602] First, the server retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores, providing basic data for a detailed understanding of the agency's operating condition. Next, the server inputs the retrieved agency data into an AI model to predict a condition score. The AI ​​model uses a linear regression model, which quantifies the agency's operating condition.

[0603] The server then generates a sales document based on the predicted condition scores, which includes each agent's condition score and the associated improvement actions.

[0604] Furthermore, an emotion engine runs on the device and analyzes voice data to recognize the user's emotions. The Python library speech_recognition is used for voice recognition, and a transformers pipeline is used for emotion identification. It can identify various emotional states, such as whether the user is stressed or relaxed.

[0605] The server then adjusts the content of the sales presentation materials based on the emotion recognition results. For example, if the user is stressed, the presentation materials will use softer language. On the other hand, if the user is relaxed, the presentation materials will include a detailed action plan.

[0606] As a specific example, if a certain agency's data shows "shipping speed 800, misshipment rate 60, inventory status 150, and productivity score 85," the server predicts the condition score based on this data and calculates the result as "75." Based on this score, sales documents are generated that suggest improvement actions, such as "Improving shipping speed would be effective." Furthermore, if the user's voice data indicates that they are feeling stressed, the server adds the message, "Consider allocating personnel to reduce the workload."

[0607] In this way, the present invention realizes efficient and objective evaluation of agent data and provision of negotiation materials according to the user's emotional state, thereby reducing the user's workload and improving the effectiveness of negotiations.

[0608] An example prompt would be, "Predict the operational condition score for logistics center A based on its shipping speed, misshipment rate, inventory status, and productivity score, and generate improvement suggestions based on the manager's emotional state."

[0609] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0610] Step 1:

[0611] The server retrieves agency data from the database, including sales, customer satisfaction, marketing expenditures, and performance scores. The agency data is taken as input and used for subsequent analysis.

[0612] Step 2:

[0613] The server inputs the acquired agency data into an AI model to predict the agency's condition score. Here, a linear regression model is used to analyze the data. The input is the agency data, and the output is the condition score.

[0614] Step 3:

[0615] The server generates sales documents based on the predicted condition scores, which include improvement actions and recommendations for each agent depending on the condition score. The input is the condition score, and the sales documents are generated as the output.

[0616] Step 4:

[0617] The emotion engine installed on the device recognizes emotions from the user's voice data. Here, we use the speech_recognition and transformers pipeline. The input is the user's voice data, and the output is the user's recognized emotional state.

[0618] Step 5:

[0619] The server adjusts the content of the sales documents based on the recognized emotional state. For example, if the user is feeling stressed, the sales documents are adjusted to use softer expressions. The input is the emotional state and the sales documents, and the adjusted sales documents are obtained as the output.

[0620] Step 6:

[0621] The user conducts business negotiations using the business negotiation materials generated and adjusted by the server. Here, the user proceeds while checking proposals based on the operational status of each agency and business negotiation materials that correspond to the user's emotional state. The input is the business negotiation materials, and the user uses them to conduct business negotiations as the output.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] [Third embodiment]

[0626] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0627] 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.

[0628] 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).

[0629] 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.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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."

[0638] This system uses data from agents to predict condition scores using an AI model and generates sales negotiation materials based on the results. This system is composed of multiple steps involving a server, terminals, and users.

[0639] The server first retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundational data for a detailed understanding of the agency's operating condition. The server then inputs the retrieved agency data into an AI model to predict a condition score. Specifically, the server uses a linear regression model to analyze the data and quantify each agency's operating condition.

[0640] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0641] The user conducts sales negotiations using the sales negotiation materials generated by the server. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. This is expected to improve the quality of sales negotiations and the performance of agencies.

[0642] As a concrete example, let's say an agency's data looks like this:

[0643] If Agent A's sales are 1,000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server uses an AI model based on this data to predict a condition score. In this case, the condition score is predicted to be 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0644] In this way, the present invention makes it possible to efficiently and objectively evaluate agent data and automatically generate sales negotiation materials based on the results. This process reduces the user's workload and improves the effectiveness of sales negotiations.

[0645] The processing flow will be explained below.

[0646] Step 1:

[0647] The server retrieves agency data from the database: In this step, the server connects to the database and loads the agency data, which includes data such as sales, customer satisfaction, marketing spend, performance scores, etc. For example, it may load the data from a CSV file using the Pandas library.

[0648] Step 2:

[0649] The server preprocesses the acquired agency data and formats it into a format suitable for the AI ​​model. In this step, the server selects necessary columns from the loaded data and separates them into features (sales, customer satisfaction, marketing expenditures) and targets (performance scores).

[0650] Step 3:

[0651] The server uses the shaped data to train an AI model. Specifically, the server instantiates a linear regression model and trains it using features and targets. The goal of this step is to learn patterns from the data and use them to make future predictions.

[0652] Step 4:

[0653] The server uses the trained model to predict the condition score of each agent. In this step, the server inputs the features of each agent into the model and outputs a condition score. The predicted score is a numerical representation of each agent's performance.

[0654] Step 5:

[0655] The server generates sales materials based on the predicted condition scores. In this step, the server determines the content of the sales materials based on the condition scores of each agent. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high score, it includes a recommendation such as "strengthening sales activities would be effective."

[0656] Step 6:

[0657] The user can obtain the generated sales negotiation materials and use them in sales negotiations. By using the sales negotiation materials provided by the server, the user can objectively evaluate the performance of each agent and propose appropriate improvement actions, thereby effectively promoting sales negotiation activities.

[0658] Example 1

[0659] 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."

[0660] In conventional methods for creating sales negotiation materials, a series of tasks from data collection to analysis and document creation are performed manually, resulting in a significant burden in terms of time and effort. It is also difficult to objectively evaluate the operational status of an agency and make appropriate improvement proposals based on that evaluation. The present invention aims to solve these problems by providing a system that automatically provides efficient and objective evaluations and proposals.

[0661] 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.

[0662] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using a generative AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, and means for providing the generated negotiation materials to a terminal. This makes it possible to quickly and accurately evaluate the agent data and automatically generate negotiation materials based on the evaluation.

[0663] A "database" is a system for efficiently storing, managing, and searching various types of data.

[0664] "Agency Data" means a collection of data including information such as agency sales, customer satisfaction, marketing spend, and performance scores.

[0665] "Generative AI Model" refers to an artificial intelligence model used to analyze agency data and predict specific outcomes.

[0666] The "condition score" is a numerical representation of the operating condition of an agency, calculated based on various indicators.

[0667] "Negotiation Materials" means documents to be used in negotiation activities, which include an Agent's Condition Score and improvement actions.

[0668] "Terminal" refers to a device used by a user, such as a computer or smartphone.

[0669] The present invention is a system that uses agent data to predict condition scores using a generative AI model and generates sales negotiation materials based on the results. This system consists of multiple steps involving a server, terminals, and users.

[0670] The server first retrieves agency data from a database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundation for a detailed understanding of the agency's operational status. SQL (Structured Query Language) is used to retrieve data from the database.

[0671] The server then inputs the acquired agency data into a generative AI model to predict a condition score. This process uses the Python language and TensorFlow library. A linear regression model is used as the generative AI model. This model can be used to analyze agency data and quantify the operating condition of each agency.

[0672] Based on the predicted condition scores, the server generates sales documents. These documents include each agent's condition score and improvement actions based on that score. For example, for agents with low condition scores, the server suggests improvement actions such as "improving customer satisfaction is necessary," while for agents with high condition scores, it includes recommendations such as "strengthening sales activities would be effective." The Python-docx library is used to generate sales documents. Using this library, it is possible to automatically generate documents in Word format.

[0673] The user conducts sales negotiations using the sales negotiation materials generated by the server. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. This is expected to improve the quality of sales negotiations and the performance of agencies.

[0674] As a concrete example, let's say an agency's data looks like this:

[0675] Sales: 1000

[0676] Customer Satisfaction Rating: 70

[0677] Marketing expenditure: 200

[0678] Performance score: 80

[0679] The server inputs this data into the model and calculates a predicted condition score of 80. Based on this score, the server generates a sales document stating, "Strengthening sales activities would be effective." Based on this document, the user can propose specific measures to the agent during sales negotiations, such as "Strengthening sales activities is important."

[0680] Here are some example prompts to input to a generative AI model:

[0681] Agency A's data:

[0682] Sales: 1000

[0683] Customer Satisfaction Rating: 70

[0684] Marketing expenditure: 200

[0685] Performance score: 80

[0686] Use this data to predict your condition score.

[0687] In this way, the present invention makes it possible to efficiently and objectively evaluate agent data and automatically generate sales negotiation materials based on the results. This process reduces the user's workload and improves the effectiveness of sales negotiations.

[0688] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0689] Step 1:

[0690] The server retrieves agency data from the database. The server executes an SQL query to retrieve "Sales", "Customer Satisfaction", "Marketing Spend", and "Performance Score" data from the database. The input is the agency ID, and the output is a set of corresponding agency data. Specifically, the server sends the following SQL query:

[0691] sql

[0692] SELECT sales, customer_satisfaction, marketing_spend, performance_score FROM agency_data WHERE agency_id = 'A';

[0693] Step 2:

[0694] The server inputs the acquired agency data into a generative AI model to predict a condition score. The server uses Python and TensorFlow to input data into a linear regression model to predict a condition score. The input is the agency data acquired in step 1, and the output is the condition score. Specifically, the server supplies data to the model as follows:

[0695] python

[0696] data = [[1000, 70, 200, 80]] Agency data

[0697] predicted_score = model.predict(data) Predicted condition score

[0698] Step 3:

[0699] The server generates sales documents using the predicted condition scores. The server uses the Python-docx library to generate sales documents in document format. The input is the condition score obtained in step 2, and the output is the sales documents. Specifically, the server creates the documents as follows:

[0700] python

[0701] doc = Document()

[0702] doc.add_heading('Opportunity materials', 0)

[0703] doc.add_paragraph(f'Agent A's condition score: {predicted_score[0][0]}')

[0704] if predicted_score[0][0] < 50:

[0705] doc.add_paragraph('We need to improve customer satisfaction.')

[0706] else:

[0707] doc.add_paragraph('Strengthening sales activities will be effective.')

[0708] doc.save('Business negotiation material_Agency A.docx')

[0709] Step 4:

[0710] The server provides the generated sales documents to the terminal. The terminal provides an interface for the user to access, allowing them to view or download the sales documents sent from the server. The input is the file path of the sales documents generated in step 3, and the output is the sales documents displayed on the user's terminal. Specifically, the server sends the path to the generated file to the terminal, which receives and displays it.

[0711] Through this series of processes, the user can efficiently evaluate the operating status of the agency and make improvement proposals based on appropriate business negotiation materials.

[0712] (Application example 1)

[0713] 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."

[0714] While there are improvement proposals based on data analysis by agents to improve the efficiency of traditional sales activities, there is a lack of effective performance evaluations and improvement proposals for brick-and-mortar store operations. In particular, there is a lack of detailed performance evaluations using brick-and-mortar store operation data and concrete action plans based on those evaluations. This makes it difficult for brick-and-mortar store operators to quickly implement appropriate improvement measures.

[0715] 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.

[0716] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using an AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, and means for acquiring store operation data, predicting a store's condition score using the data, and proposing improvement actions for the store operation based on the predicted score. This makes it possible to evaluate the operation status of each agent and physical store in detail and objectively, and to propose effective improvement proposals based on the evaluation.

[0717] Definitions of important words

[0718] “Agency Data” means data used to gain insight into the operations of an Agency, including sales, customer satisfaction, marketing spend, and performance scores.

[0719] "Database" refers to a data storage system that stores agency data and store operation data and can be accessed as needed.

[0720] An "AI model" is a mathematical and statistical tool that uses artificial intelligence techniques to analyze data and predict a particular outcome, such as a condition score.

[0721] The "condition score" is a numerical indicator of the operating status of an agency or store, and is predicted by an AI model based on various data.

[0722] A "sales deck" is a document generated based on the predicted condition score, including improvement actions and recommendations.

[0723] "Sales" means the total income earned through sales activities during a given period.

[0724] "Customer satisfaction" is a survey and evaluation of the degree of satisfaction that customers have with products and services.

[0725] "Marketing expenditure" is the total amount spent on marketing activities.

[0726] "Performance Score" is a comprehensive score that evaluates the performance of an agency or store based on multiple indicators.

[0727] "Store Operations Data" means data relating to the operation of physical stores, including sales, customer satisfaction, marketing expenditures, and performance scores.

[0728] "Improvement Action" is a specific action plan proposed based on the predicted condition score to improve the operating condition of the agency or store.

[0729] MODE FOR CARRYING OUT THE INVENTION

[0730] The present invention is a system that evaluates the operational status of agencies and brick-and-mortar stores and automatically generates improvement proposals. This system is composed of multiple steps involving a server, terminals, and users.

[0731] The server first retrieves agent and store operation data from the database. This data includes sales, customer satisfaction, marketing expenditures, and performance scores. Based on this data, the server uses an AI model to predict the condition scores of agents and stores. Specifically, it implements a linear regression model using Python and the Scikit-learn library to analyze the data and calculate the condition scores.

[0732] On the user device side, a front-end application is developed using JavaScript and React Native. The condition score predicted by the server and the improvement actions based on it are sent to the front-end application, where users can view them and take appropriate improvement actions.

[0733] The server then automatically generates sales materials based on the predicted condition scores. These sales materials include the condition scores for each store and specific improvement actions based on those scores. For example, if the condition score is low, the suggestion may be, "You need to improve customer satisfaction," while if the score is high, the recommendation may be, "Strengthening sales activities would be effective."

[0734] For example, if a store's sales are 1000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server will predict the condition score to be 75 based on this data. In this case, the sales materials will include a statement such as "Strengthening sales activities would be effective." The following prompt sentence will also be generated:

[0735] If a store has sales of 1000, customer satisfaction of 70, marketing spend of 200, and a performance score of 80, the predicted condition score is 75. Increased sales efforts would be beneficial.

[0736] This allows the server and terminal to analyze data efficiently and objectively, and provide users with specific actions based on the results. By using this system, the operational status of agencies and physical stores can be properly evaluated, and actionable improvement proposals can be quickly received.

[0737] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0738] Program processing steps

[0739] Step 1: Data Acquisition

[0740] The server retrieves agency data and store operations data from the database, including sales, customer satisfaction, marketing expenditures, and performance scores.

[0741] Input: Database connection information

[0742] Output: Agency data and store operation data

[0743] What happens: The server connects to the MySQL database and retrieves the required data.

[0744] Step 2: Data analysis

[0745] The server inputs the acquired data into an AI model to predict a condition score. Specifically, it analyzes the data using a linear regression model.

[0746] Input: Agency data and store operation data

[0747] Output: Condition score

[0748] How it works: The server runs a linear regression model using Python and Scikit-learn to calculate a condition score based on the input data.

[0749] Step 3: Generate sales documents

[0750] The server generates sales documents based on the predicted condition scores, which include the condition scores of each agency and store and the improvement actions based on the scores.

[0751] Input: Condition Score

[0752] Output: Sales documents

[0753] What it does: The server generates a sales deck in HTML or PDF format, including the appropriate content.

[0754] Step 4: Send data

[0755] The server transmits the generated business negotiation materials and condition scores to the user terminal.

[0756] Input: Sales documents, condition score

[0757] Output: Sending data to the user's terminal

[0758] How it works: The server sends data using the HTTP protocol and displays it on the user's terminal.

[0759] Step 5: User Views and Actions

[0760] The user terminal displays the received business negotiation materials and condition score, and the user takes improvement action based on this.

[0761] Input: Sales documents, condition score

[0762] Output: Displayed sales documents, user actions

[0763] How it works: The front-end application (React Native) displays the data, and the user can view and interact with it.

[0764] Step 6: Improvement Action Feedback

[0765] Based on the improvement actions taken by the user, new data is acquired and fed back to the server, which uses this data for future analysis and to improve the accuracy of predictions.

[0766] Input: Improvement action result

[0767] Output: Feedback data

[0768] How it works: A user inputs feedback data through a smartphone application and sends it to a server.

[0769] This allows the server and terminal to exchange data with each other, enabling detailed evaluation of the operational status of agencies and physical stores and providing appropriate improvement proposals.

[0770] 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.

[0771] This system uses agent data to predict condition scores using an AI model and generates sales documents based on the results. It also provides a function to adjust the content of sales documents based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user.

[0772] The server first retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundational data for a detailed understanding of the agency's operating condition. The server then inputs the retrieved agency data into an AI model to predict a condition score. Specifically, the server uses a linear regression model to analyze the data and quantify each agency's operating condition.

[0773] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0774] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. The emotion engine runs on the device and recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine identifies various emotional states, such as when the user is stressed or relaxed. The server uses the emotion data obtained from the emotion engine to adjust the content of sales documents. For example, if the user is stressed, the server generates sales documents using softer expressions, and if the user is relaxed, the server provides sales documents with detailed action plans.

[0775] The user uses the sales documents generated by the server to conduct sales negotiations. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. In addition, the sales documents provided correspond to the user's emotional state, enabling more effective communication.

[0776] As a concrete example, let's say an agency's data looks like this:

[0777] If Agent A's sales are 1,000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server uses an AI model based on this data to predict a condition score. In this case, the condition score is predicted to be 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0778] Furthermore, if the user's emotion engine determines that the user is relaxed as a result of its analysis, the server provides negotiation materials including a detailed action plan. Conversely, if the server determines that the user is stressed, the server generates negotiation materials with simpler, more positive content. In this way, the present invention enables efficient and objective evaluation of agent data and the provision of negotiation materials that correspond to the user's emotional state. This reduces the user's workload and improves the effectiveness of negotiations.

[0779] The processing flow will be explained below.

[0780] Step 1:

[0781] The server retrieves agency data from the database. The server connects to the database and loads data including agency sales, customer satisfaction, marketing expenditures, and performance scores, thereby obtaining detailed operational information for the agency.

[0782] Step 2:

[0783] The server preprocesses the acquired agency data and formats it into a format suitable for the AI ​​model. The server extracts necessary items from the loaded data and sets sales, customer satisfaction, and marketing expenditures as features. It also sets performance scores as targets.

[0784] Step 3:

[0785] The server uses the shaped data to train the AI ​​model. In this step, the server instantiates a linear regression model and trains it using features and targets. The model learns patterns from the agency's data and uses them to make future predictions.

[0786] Step 4:

[0787] The server uses the trained model to predict the condition score of each agent. The server inputs the features of each agent into the model and calculates the condition score. The predicted condition score is a numerical representation of the operating condition of each agent.

[0788] Step 5:

[0789] The server generates sales documents based on the predicted condition scores. Based on each agent's condition score, the server creates sales documents that include improvement actions. For example, if the condition score is low, the server suggests "improving customer satisfaction is necessary," and if the score is high, the server suggests "strengthening sales activities would be effective."

[0790] Step 6:

[0791] The device runs an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice and facial expressions to determine their emotional state. For example, it detects whether the user is relaxed or stressed.

[0792] Step 7:

[0793] The server uses the emotion data obtained from the emotion engine to adjust the content of the sales materials. The server takes into account the user's emotional state and generates materials with detailed action plans if the user is relaxed, and materials with simple, positive content if the user is stressed.

[0794] Step 8:

[0795] The user obtains the sales negotiation materials generated by the server and uses them in sales negotiation activities. The user can use the sales negotiation materials to evaluate the operating status of each agency and propose appropriate improvement actions. In addition, the sales negotiation materials are provided according to the user's emotional state, allowing for more effective communication.

[0796] In this way, the embodiment divided into processing steps realizes efficient evaluation of agent data and provision of negotiation materials based on the user's emotions, thereby reducing the user's workload and improving the effectiveness of negotiations.

[0797] Example 2

[0798] 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."

[0799] Conventional sales negotiation materials generation systems only generate static materials based on agency data, making it difficult to maximize the efficiency and effectiveness of sales negotiations. Furthermore, they provide uniform materials without considering the user's emotional state, which can cause stress and reduce efficiency. Therefore, there is a growing need for a system that can flexibly adjust the content of sales negotiations according to the agency's operational status and the user's emotions.

[0800] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0801] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using a generative AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, means for acquiring emotion data from a terminal including an emotion engine for analyzing a user's emotion, and means for adjusting the content of the negotiation materials based on the emotion data. This makes it possible to flexibly adjust the negotiation materials according to the operating status of the agent and the emotional state of the user, thereby maximizing the efficiency and effectiveness of negotiations.

[0802] "Agency Data" means data including agency sales, customer satisfaction, marketing spend, and performance scores.

[0803] "Generative AI Model" means an artificial intelligence model used to predict a Condition Score based on acquired agency data, and specifically includes a linear regression model.

[0804] "Condition Score" is a numerical value that indicates the operating condition of an agency, predicted using a generative AI model.

[0805] "Sales Decision Document" means a document containing improvement actions and recommendations to an agency that is generated based on a predicted condition score.

[0806] An "emotion engine" is an engine installed in a terminal that analyzes the user's voice and facial expressions to analyze emotional data.

[0807] A "terminal" is a device that collects user emotion data and runs an emotion engine, and provides business negotiation materials in cooperation with a server.

[0808] "Emotion data" is data that indicates the user's emotional state, analyzed using an emotion engine.

[0809] MODE FOR CARRYING OUT THE INVENTION

[0810] This system uses agent data to predict condition scores using an AI model and generates sales documents based on the results. It also provides a function to adjust the content of sales documents based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user.

[0811] Data acquisition and analysis

[0812] The server first retrieves agency data from a database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. Specifically, the data is retrieved using database software such as MySQL or PostgreSQL. This data provides the basis for evaluating performance. The server then formats the retrieved agency data and converts it into a format that can be input into the AI ​​model. This task is typically performed using the Python pandas library.

[0813] Condition score prediction by AI model

[0814] The server inputs the formatted data into a generative AI model to predict a condition score. A linear regression model is used as the generative AI model. For example, a pre-trained model can be used using a machine learning library such as scikit-learn. The model quantifies the operating condition of the agency based on the acquired data.

[0815] Generate sales documents

[0816] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0817] Acquiring emotion data

[0818] The device recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine uses libraries such as TensorFlow and OpenCV to analyze audio and video data. The device uses this hardware and software to identify emotional states in real time. When the user is in front of the device, their facial expressions and speech are captured by the camera and microphone, and analyzed by the emotion engine.

[0819] Adjustment of business documents

[0820] The server receives the emotion data sent from the device and adjusts the content of the sales meeting materials. For example, if the user is feeling stressed, the server generates sales meeting materials using softer expressions, and if the user is relaxed, the server provides sales meeting materials including a detailed action plan. In this way, the sales meeting materials are dynamically adjusted according to the user's current emotional state.

[0821] User Use

[0822] The user uses the sales documents generated by the server to conduct sales negotiations. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. In addition, the sales documents provided correspond to the user's emotional state, enabling more effective communication.

[0823] Specific examples

[0824] For example, suppose Agency A's data looks like this:

[0825] If sales are 1,000, customer satisfaction is 70, marketing expenditures are 200, and the performance score is 80, the server uses this data to predict a condition score using a generative AI model. In this case, the predicted condition score is 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0826] Furthermore, if the user's emotion engine determines that the user is relaxed, the server will provide sales materials with detailed action plans. Conversely, if the server determines that the user is stressed, the server will generate simpler, more positive sales materials.

[0827] Prompt Sentence Examples

[0828] Here are some examples of prompts to input to a generative AI model:

[0829] Data for Agent A: Sales = 1000, Customer Satisfaction = 70, Marketing Expenditure = 200, Performance Score = 80. Based on this data, predict the condition score and generate sales materials. Also, adjust the content of the materials based on the user's emotional state as "Relaxed."

[0830] conclusion

[0831] As a result, the present invention can efficiently and objectively evaluate agent data and provide negotiation materials that correspond to the user's emotional state, thereby reducing the user's workload and improving the effectiveness of negotiations.

[0832] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0833] Step 1: Data Acquisition

[0834] The server retrieves agency data from a database. This data includes agency sales, customer satisfaction, marketing spend, and performance scores. It uses database software such as MySQL or PostgreSQL. As input, it takes a specific agency ID and as output, it gets the corresponding agency data. The specific operation is to execute an SQL query to retrieve the data.

[0835] ...

[0836] sql

[0837] SELECT sales, customer_satisfaction, marketing_spend, performance_score FROM agencies WHERE agency_id = 'A';

[0838] Step 2: Data analysis

[0839] The server formats the acquired agency data and converts it into a format suitable for input to the generative AI model. This is done using the Python pandas library. The acquired agency data is used as input, and the output is data that has been formatted in a format suitable for input to the AI ​​model. For example, the data is converted into a data frame and appropriately scaled.

[0840] The specific operation is to create a data frame using pandas and scale the data using a standard scaler.

[0841] ...

[0842] python

[0843] import pandas as pd

[0844] from sklearn.preprocessing import StandardScaler

[0845] data = {'sales':

[1000] , 'customer_satisfaction':

[70] , 'marketing_spend':

[0200] , 'performance_score':

[80] }

[0846] df = pd.DataFrame(data)

[0847] scaler = StandardScaler()

[0848] scaled_data = scaler.fit_transform(df)

[0849] Step 3: Condition Score Prediction

[0850] The server inputs the formatted data into a generative AI model to predict a condition score. A linear regression model is used as the generative AI model. The scaled data is used as input, and the predicted condition score is obtained as output. The specific operation is to make a prediction using a pre-trained linear regression model.

[0851] ...

[0852] python

[0853] from sklearn.linear_model import LinearRegression

[0854] Use a pre-trained model (training steps omitted)

[0855] model = LinearRegression()

[0856] model.fit(training_data, target) Model training part (example)

[0857] condition_score = model.predict(scaled_data)

[0858] Step 4: Generate sales documents

[0859] The server generates sales materials based on the predicted condition scores. The materials include each agent's condition score and improvement actions based on the condition scores. The predicted condition scores are used as input, and the generated sales materials are obtained as output. The specific operation is to implement logic that generates different messages based on the condition scores.

[0860] ...

[0861] python

[0862] if condition_score >= 75:

[0863] suggestion = "Strengthening sales activities would be effective"

[0864] else:

[0865] suggestion = "Customer satisfaction needs to be improved"

[0866] document = f"Agency A's condition score is {condition_score}. {suggestion}"

[0867] Step 5: Acquire emotion data

[0868] The device recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine uses libraries such as TensorFlow and OpenCV to analyze audio and video data. The user's audio and video data are used as input, and the identified user's emotion data is obtained as output. Specifically, data is acquired using a camera or microphone, and the emotion engine analyzes it.

[0869] ...

[0870] python

[0871] import cv2

[0872] import tensorflow as tf

[0873] cap = cv2.VideoCapture(0)

[0874] _, frame = cap.read()

[0875] emotion_model = tf.keras.models.load_model('emotion_model.h5')

[0876] emotion_prediction = emotion_model.predict(frame)

[0877] Step 6: Adjust the sales materials

[0878] The server adjusts the content of the sales documents based on the emotion data received from the device. It uses emotion data and existing sales documents as input, and obtains adjusted sales documents as output. Specifically, it softens the expressions in the documents or adds details depending on the emotion data.

[0879] ...

[0880] python

[0881] if emotion_prediction == 'stress':

[0882] document = f"Agency A's condition score is {condition_score}. Trimmed to be simple: {suggestion}"

[0883] else:

[0884] document = f"Agency A's condition score is {condition_score}. Includes detailed action plan: {suggestion}"

[0885] Step 7: Provide business documents

[0886] The user checks the sales negotiation materials generated by the server and uses them in sales negotiation activities. The adjusted sales negotiation materials are used as input, and the sales negotiation is conducted as output. The specific operation is to check the materials provided by the server on the terminal.

[0887] ...

[0888] python

[0889] print(document) Display the generated sales document

[0890] (Application example 2)

[0891] 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."

[0892] Conventional sales negotiation systems using agency data can evaluate the operational status of each agency, but they do not support the generation of sales negotiation materials that take the user's emotional state into account, making effective communication difficult. Furthermore, real-time information based on the user's emotional state is required for quick business decisions. To solve this problem, a system is needed that can comprehensively evaluate operational status based on agency data and generate sales negotiation materials that correspond to the user's emotional state.

[0893] 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.

[0894] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using an AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, means for recognizing a user's emotion from voice data, and means for adjusting the content of the negotiation materials based on the recognized emotion, thereby enabling efficient and objective evaluation of the agent data and provision of negotiation materials according to the user's emotional state.

[0895] "Agency Data" means data such as sales, customer satisfaction, marketing spend, and performance scores used to evaluate the operations of an agency.

[0896] A "database" is a system for systematically storing and managing information such as agency data.

[0897] An "AI model" is a mathematical and computational model that uses artificial intelligence technology to analyze and predict data.

[0898] The "condition score" is a numerical indicator of the operating condition of an agency, and is calculated based on various data.

[0899] "Negotiation Materials" means materials that include an agency's condition score and improvement actions and recommendations based thereon.

[0900] "Voice data" is digital data that records voice and is used to recognize the user's emotions.

[0901] An "emotion engine" is software that analyzes voice data, facial expression data, etc. to recognize the user's emotional state.

[0902] A "means" is a method or device for achieving a specific function or purpose.

[0903] The present invention is a system that uses agency data to predict condition scores using an AI model and generates sales materials based on the results. It also includes a function that adjusts the content of sales materials based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user. The server generates and adjusts sales materials using agency data and user emotion data obtained from a database.

[0904] First, the server retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores, providing basic data for a detailed understanding of the agency's operating condition. Next, the server inputs the retrieved agency data into an AI model to predict a condition score. The AI ​​model uses a linear regression model, which quantifies the agency's operating condition.

[0905] The server then generates a sales document based on the predicted condition scores, which includes each agent's condition score and the associated improvement actions.

[0906] Furthermore, an emotion engine runs on the device and analyzes voice data to recognize the user's emotions. The Python library speech_recognition is used for voice recognition, and a transformers pipeline is used for emotion identification. It can identify various emotional states, such as whether the user is stressed or relaxed.

[0907] The server then adjusts the content of the sales presentation materials based on the emotion recognition results. For example, if the user is stressed, the presentation materials will use softer language. On the other hand, if the user is relaxed, the presentation materials will include a detailed action plan.

[0908] As a specific example, if a certain agency's data shows "shipping speed 800, misshipment rate 60, inventory status 150, and productivity score 85," the server predicts the condition score based on this data and calculates the result as "75." Based on this score, sales documents are generated that suggest improvement actions, such as "Improving shipping speed would be effective." Furthermore, if the user's voice data indicates that they are feeling stressed, the server adds the message, "Consider allocating personnel to reduce the workload."

[0909] In this way, the present invention realizes efficient and objective evaluation of agent data and provision of negotiation materials according to the user's emotional state, thereby reducing the user's workload and improving the effectiveness of negotiations.

[0910] An example prompt would be, "Predict the operational condition score for logistics center A based on its shipping speed, misshipment rate, inventory status, and productivity score, and generate improvement suggestions based on the manager's emotional state."

[0911] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0912] Step 1:

[0913] The server retrieves agency data from the database, including sales, customer satisfaction, marketing expenditures, and performance scores. The agency data is taken as input and used for subsequent analysis.

[0914] Step 2:

[0915] The server inputs the acquired agency data into an AI model to predict the agency's condition score. Here, a linear regression model is used to analyze the data. The input is the agency data, and the output is the condition score.

[0916] Step 3:

[0917] The server generates sales documents based on the predicted condition scores, which include improvement actions and recommendations for each agent depending on the condition score. The input is the condition score, and the sales documents are generated as the output.

[0918] Step 4:

[0919] The emotion engine installed on the device recognizes emotions from the user's voice data. Here, we use the speech_recognition and transformers pipeline. The input is the user's voice data, and the output is the user's recognized emotional state.

[0920] Step 5:

[0921] The server adjusts the content of the sales documents based on the recognized emotional state. For example, if the user is feeling stressed, the sales documents are adjusted to use softer expressions. The input is the emotional state and the sales documents, and the adjusted sales documents are obtained as the output.

[0922] Step 6:

[0923] The user conducts business negotiations using the business negotiation materials generated and adjusted by the server. Here, the user proceeds while checking proposals based on the operational status of each agency and business negotiation materials that correspond to the user's emotional state. The input is the business negotiation materials, and the user uses them to conduct business negotiations as the output.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] [Fourth embodiment]

[0928] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0929] 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.

[0930] 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).

[0931] 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.

[0932] 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.

[0933] 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).

[0934] 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.

[0935] 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.

[0936] 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.

[0937] 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.

[0938] 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.

[0939] 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.

[0940] 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."

[0941] This system uses data from agents to predict condition scores using an AI model and generates sales negotiation materials based on the results. This system is composed of multiple steps involving a server, terminals, and users.

[0942] The server first retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundational data for a detailed understanding of the agency's operating condition. The server then inputs the retrieved agency data into an AI model to predict a condition score. Specifically, the server uses a linear regression model to analyze the data and quantify each agency's operating condition.

[0943] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[0944] The user conducts sales negotiations using the sales negotiation materials generated by the server. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. This is expected to improve the quality of sales negotiations and the performance of agencies.

[0945] As a concrete example, let's say an agency's data looks like this:

[0946] If Agent A's sales are 1,000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server uses an AI model based on this data to predict a condition score. In this case, the condition score is predicted to be 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[0947] In this way, the present invention makes it possible to efficiently and objectively evaluate agent data and automatically generate sales negotiation materials based on the results. This process reduces the user's workload and improves the effectiveness of sales negotiations.

[0948] The processing flow will be explained below.

[0949] Step 1:

[0950] The server retrieves agency data from the database: In this step, the server connects to the database and loads the agency data, which includes data such as sales, customer satisfaction, marketing spend, performance scores, etc. For example, it may load the data from a CSV file using the Pandas library.

[0951] Step 2:

[0952] The server preprocesses the acquired agency data and formats it into a format suitable for the AI ​​model. In this step, the server selects necessary columns from the loaded data and separates them into features (sales, customer satisfaction, marketing expenditures) and targets (performance scores).

[0953] Step 3:

[0954] The server uses the shaped data to train an AI model. Specifically, the server instantiates a linear regression model and trains it using features and targets. The goal of this step is to learn patterns from the data and use them to make future predictions.

[0955] Step 4:

[0956] The server uses the trained model to predict the condition score of each agent. In this step, the server inputs the features of each agent into the model and outputs a condition score. The predicted score is a numerical representation of each agent's performance.

[0957] Step 5:

[0958] The server generates sales materials based on the predicted condition scores. In this step, the server determines the content of the sales materials based on the condition scores of each agent. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high score, it includes a recommendation such as "strengthening sales activities would be effective."

[0959] Step 6:

[0960] The user can obtain the generated sales negotiation materials and use them in sales negotiations. By using the sales negotiation materials provided by the server, the user can objectively evaluate the performance of each agent and propose appropriate improvement actions, thereby effectively promoting sales negotiation activities.

[0961] Example 1

[0962] 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."

[0963] In conventional methods for creating sales negotiation materials, a series of tasks from data collection to analysis and document creation are performed manually, resulting in a significant burden in terms of time and effort. It is also difficult to objectively evaluate the operational status of an agency and make appropriate improvement proposals based on that evaluation. The present invention aims to solve these problems by providing a system that automatically provides efficient and objective evaluations and proposals.

[0964] 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.

[0965] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using a generative AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, and means for providing the generated negotiation materials to a terminal. This makes it possible to quickly and accurately evaluate the agent data and automatically generate negotiation materials based on the evaluation.

[0966] A "database" is a system for efficiently storing, managing, and searching various types of data.

[0967] "Agency Data" means a collection of data including information such as agency sales, customer satisfaction, marketing spend, and performance scores.

[0968] "Generative AI Model" refers to an artificial intelligence model used to analyze agency data and predict specific outcomes.

[0969] The "condition score" is a numerical representation of the operating condition of an agency, calculated based on various indicators.

[0970] "Negotiation Materials" means documents to be used in negotiation activities, which include an Agent's Condition Score and improvement actions.

[0971] "Terminal" refers to a device used by a user, such as a computer or smartphone.

[0972] The present invention is a system that uses agent data to predict condition scores using a generative AI model and generates sales negotiation materials based on the results. This system consists of multiple steps involving a server, terminals, and users.

[0973] The server first retrieves agency data from a database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundation for a detailed understanding of the agency's operational status. SQL (Structured Query Language) is used to retrieve data from the database.

[0974] The server then inputs the acquired agency data into a generative AI model to predict a condition score. This process uses the Python language and TensorFlow library. A linear regression model is used as the generative AI model. This model can be used to analyze agency data and quantify the operating condition of each agency.

[0975] Based on the predicted condition scores, the server generates sales documents. These documents include each agent's condition score and improvement actions based on that score. For example, for agents with low condition scores, the server suggests improvement actions such as "improving customer satisfaction is necessary," while for agents with high condition scores, it includes recommendations such as "strengthening sales activities would be effective." The Python-docx library is used to generate sales documents. Using this library, it is possible to automatically generate documents in Word format.

[0976] The user conducts sales negotiations using the sales negotiation materials generated by the server. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. This is expected to improve the quality of sales negotiations and the performance of agencies.

[0977] As a concrete example, let's say an agency's data looks like this:

[0978] Sales: 1000

[0979] Customer Satisfaction Rating: 70

[0980] Marketing expenditure: 200

[0981] Performance score: 80

[0982] The server inputs this data into the model and calculates a predicted condition score of 80. Based on this score, the server generates a sales document stating, "Strengthening sales activities would be effective." Based on this document, the user can propose specific measures to the agent during sales negotiations, such as "Strengthening sales activities is important."

[0983] Here are some example prompts to input to a generative AI model:

[0984] Agency A's data:

[0985] Sales: 1000

[0986] Customer Satisfaction Rating: 70

[0987] Marketing expenditure: 200

[0988] Performance score: 80

[0989] Use this data to predict your condition score.

[0990] In this way, the present invention makes it possible to efficiently and objectively evaluate agent data and automatically generate sales negotiation materials based on the results. This process reduces the user's workload and improves the effectiveness of sales negotiations.

[0991] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0992] Step 1:

[0993] The server retrieves agency data from the database. The server executes an SQL query to retrieve "Sales", "Customer Satisfaction", "Marketing Spend", and "Performance Score" data from the database. The input is the agency ID, and the output is a set of corresponding agency data. Specifically, the server sends the following SQL query:

[0994] sql

[0995] SELECT sales, customer_satisfaction, marketing_spend, performance_score FROM agency_data WHERE agency_id = 'A';

[0996] Step 2:

[0997] The server inputs the acquired agency data into a generative AI model to predict a condition score. The server uses Python and TensorFlow to input data into a linear regression model to predict a condition score. The input is the agency data acquired in step 1, and the output is the condition score. Specifically, the server supplies data to the model as follows:

[0998] python

[0999] data = [[1000, 70, 200, 80]] Agency data

[1000] predicted_score = model.predict(data) Predicted condition score

[1001] Step 3:

[1002] The server generates sales documents using the predicted condition scores. The server uses the Python-docx library to generate sales documents in document format. The input is the condition score obtained in step 2, and the output is the sales documents. Specifically, the server creates the documents as follows:

[1003] python

[1004] doc = Document()

[1005] doc.add_heading('Opportunity materials', 0)

[1006] doc.add_paragraph(f'Agent A's condition score: {predicted_score[0][0]}')

[1007] if predicted_score[0][0] < 50:

[1008] doc.add_paragraph('We need to improve customer satisfaction.')

[1009] else:

[1010] doc.add_paragraph('Strengthening sales activities will be effective.')

[1011] doc.save('Business negotiation material_Agency A.docx')

[1012] Step 4:

[1013] The server provides the generated sales documents to the terminal. The terminal provides an interface for the user to access, allowing them to view or download the sales documents sent from the server. The input is the file path of the sales documents generated in step 3, and the output is the sales documents displayed on the user's terminal. Specifically, the server sends the path to the generated file to the terminal, which receives and displays it.

[1014] Through this series of processes, the user can efficiently evaluate the operating status of the agency and make improvement proposals based on appropriate business negotiation materials.

[1015] (Application example 1)

[1016] 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."

[1017] While there are improvement proposals based on data analysis by agents to improve the efficiency of traditional sales activities, there is a lack of effective performance evaluations and improvement proposals for brick-and-mortar store operations. In particular, there is a lack of detailed performance evaluations using brick-and-mortar store operation data and concrete action plans based on those evaluations. This makes it difficult for brick-and-mortar store operators to quickly implement appropriate improvement measures.

[1018] 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.

[1019] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using an AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, and means for acquiring store operation data, predicting a store's condition score using the data, and proposing improvement actions for the store operation based on the predicted score. This makes it possible to evaluate the operation status of each agent and physical store in detail and objectively, and to propose effective improvement proposals based on the evaluation.

[1020] Definitions of important words

[1021] “Agency Data” means data used to gain insight into the operations of an Agency, including sales, customer satisfaction, marketing spend, and performance scores.

[1022] "Database" refers to a data storage system that stores agency data and store operation data and can be accessed as needed.

[1023] An "AI model" is a mathematical and statistical tool that uses artificial intelligence techniques to analyze data and predict a particular outcome, such as a condition score.

[1024] The "condition score" is a numerical indicator of the operating status of an agency or store, and is predicted by an AI model based on various data.

[1025] A "sales deck" is a document generated based on the predicted condition score, including improvement actions and recommendations.

[1026] "Sales" means the total income earned through sales activities during a given period.

[1027] "Customer satisfaction" is a survey and evaluation of the degree of satisfaction that customers have with products and services.

[1028] "Marketing expenditure" is the total amount spent on marketing activities.

[1029] "Performance Score" is a comprehensive score that evaluates the performance of an agency or store based on multiple indicators.

[1030] "Store Operations Data" means data relating to the operation of physical stores, including sales, customer satisfaction, marketing expenditures, and performance scores.

[1031] "Improvement Action" is a specific action plan proposed based on the predicted condition score to improve the operating condition of the agency or store.

[1032] MODE FOR CARRYING OUT THE INVENTION

[1033] The present invention is a system that evaluates the operational status of agencies and brick-and-mortar stores and automatically generates improvement proposals. This system is composed of multiple steps involving a server, terminals, and users.

[1034] The server first retrieves agent and store operation data from the database. This data includes sales, customer satisfaction, marketing expenditures, and performance scores. Based on this data, the server uses an AI model to predict the condition scores of agents and stores. Specifically, it implements a linear regression model using Python and the Scikit-learn library to analyze the data and calculate the condition scores.

[1035] On the user device side, a front-end application is developed using JavaScript and React Native. The condition score predicted by the server and the improvement actions based on it are sent to the front-end application, where users can view them and take appropriate improvement actions.

[1036] The server then automatically generates sales materials based on the predicted condition scores. These sales materials include the condition scores for each store and specific improvement actions based on those scores. For example, if the condition score is low, the suggestion may be, "You need to improve customer satisfaction," while if the score is high, the recommendation may be, "Strengthening sales activities would be effective."

[1037] For example, if a store's sales are 1000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server will predict the condition score to be 75 based on this data. In this case, the sales materials will include a statement such as "Strengthening sales activities would be effective." The following prompt sentence will also be generated:

[1038] If a store has sales of 1000, customer satisfaction of 70, marketing spend of 200, and a performance score of 80, the predicted condition score is 75. Increased sales efforts would be beneficial.

[1039] This allows the server and terminal to analyze data efficiently and objectively, and provide users with specific actions based on the results. By using this system, the operational status of agencies and physical stores can be properly evaluated, and actionable improvement proposals can be quickly received.

[1040] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1041] Program processing steps

[1042] Step 1: Data Acquisition

[1043] The server retrieves agency data and store operations data from the database, including sales, customer satisfaction, marketing expenditures, and performance scores.

[1044] Input: Database connection information

[1045] Output: Agency data and store operation data

[1046] What happens: The server connects to the MySQL database and retrieves the required data.

[1047] Step 2: Data analysis

[1048] The server inputs the acquired data into an AI model to predict a condition score. Specifically, it analyzes the data using a linear regression model.

[1049] Input: Agency data and store operation data

[1050] Output: Condition score

[1051] How it works: The server runs a linear regression model using Python and Scikit-learn to calculate a condition score based on the input data.

[1052] Step 3: Generate sales documents

[1053] The server generates sales documents based on the predicted condition scores, which include the condition scores of each agency and store and the improvement actions based on the scores.

[1054] Input: Condition Score

[1055] Output: Sales documents

[1056] What it does: The server generates a sales deck in HTML or PDF format, including the appropriate content.

[1057] Step 4: Send data

[1058] The server transmits the generated business negotiation materials and condition scores to the user terminal.

[1059] Input: Sales documents, condition score

[1060] Output: Sending data to the user's terminal

[1061] How it works: The server sends data using the HTTP protocol and displays it on the user's terminal.

[1062] Step 5: User Views and Actions

[1063] The user terminal displays the received business negotiation materials and condition score, and the user takes improvement action based on this.

[1064] Input: Sales documents, condition score

[1065] Output: Displayed sales documents, user actions

[1066] How it works: The front-end application (React Native) displays the data, and the user can view and interact with it.

[1067] Step 6: Improvement Action Feedback

[1068] Based on the improvement actions taken by the user, new data is acquired and fed back to the server, which uses this data for future analysis and to improve the accuracy of predictions.

[1069] Input: Improvement action result

[1070] Output: Feedback data

[1071] How it works: A user inputs feedback data through a smartphone application and sends it to a server.

[1072] This allows the server and terminal to exchange data with each other, enabling detailed evaluation of the operational status of agencies and physical stores and providing appropriate improvement proposals.

[1073] 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.

[1074] This system uses agent data to predict condition scores using an AI model and generates sales documents based on the results. It also provides a function to adjust the content of sales documents based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user.

[1075] The server first retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. This provides the foundational data for a detailed understanding of the agency's operating condition. The server then inputs the retrieved agency data into an AI model to predict a condition score. Specifically, the server uses a linear regression model to analyze the data and quantify each agency's operating condition.

[1076] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[1077] Furthermore, the system incorporates an emotion engine that recognizes the user's emotions. The emotion engine runs on the device and recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine identifies various emotional states, such as when the user is stressed or relaxed. The server uses the emotion data obtained from the emotion engine to adjust the content of sales documents. For example, if the user is stressed, the server generates sales documents using softer expressions, and if the user is relaxed, the server provides sales documents with detailed action plans.

[1078] The user uses the sales documents generated by the server to conduct sales negotiations. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. In addition, the sales documents provided correspond to the user's emotional state, enabling more effective communication.

[1079] As a concrete example, let's say an agency's data looks like this:

[1080] If Agent A's sales are 1,000, customer satisfaction is 70, marketing expenditure is 200, and the performance score is 80, the server uses an AI model based on this data to predict a condition score. In this case, the condition score is predicted to be 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[1081] Furthermore, if the user's emotion engine determines that the user is relaxed as a result of its analysis, the server provides negotiation materials including a detailed action plan. Conversely, if the server determines that the user is stressed, the server generates negotiation materials with simpler, more positive content. In this way, the present invention enables efficient and objective evaluation of agent data and the provision of negotiation materials that correspond to the user's emotional state. This reduces the user's workload and improves the effectiveness of negotiations.

[1082] The processing flow will be explained below.

[1083] Step 1:

[1084] The server retrieves agency data from the database. The server connects to the database and loads data including agency sales, customer satisfaction, marketing expenditures, and performance scores, thereby obtaining detailed operational information for the agency.

[1085] Step 2:

[1086] The server preprocesses the acquired agency data and formats it into a format suitable for the AI ​​model. The server extracts necessary items from the loaded data and sets sales, customer satisfaction, and marketing expenditures as features. It also sets performance scores as targets.

[1087] Step 3:

[1088] The server uses the shaped data to train the AI ​​model. In this step, the server instantiates a linear regression model and trains it using features and targets. The model learns patterns from the agency's data and uses them to make future predictions.

[1089] Step 4:

[1090] The server uses the trained model to predict the condition score of each agent. The server inputs the features of each agent into the model and calculates the condition score. The predicted condition score is a numerical representation of the operating condition of each agent.

[1091] Step 5:

[1092] The server generates sales documents based on the predicted condition scores. Based on each agent's condition score, the server creates sales documents that include improvement actions. For example, if the condition score is low, the server suggests "improving customer satisfaction is necessary," and if the score is high, the server suggests "strengthening sales activities would be effective."

[1093] Step 6:

[1094] The device runs an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's voice and facial expressions to determine their emotional state. For example, it detects whether the user is relaxed or stressed.

[1095] Step 7:

[1096] The server uses the emotion data obtained from the emotion engine to adjust the content of the sales materials. The server takes into account the user's emotional state and generates materials with detailed action plans if the user is relaxed, and materials with simple, positive content if the user is stressed.

[1097] Step 8:

[1098] The user obtains the sales negotiation materials generated by the server and uses them in sales negotiation activities. The user can use the sales negotiation materials to evaluate the operating status of each agency and propose appropriate improvement actions. In addition, the sales negotiation materials are provided according to the user's emotional state, allowing for more effective communication.

[1099] In this way, the embodiment divided into processing steps realizes efficient evaluation of agent data and provision of negotiation materials based on the user's emotions, thereby reducing the user's workload and improving the effectiveness of negotiations.

[1100] Example 2

[1101] 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."

[1102] Conventional sales negotiation materials generation systems only generate static materials based on agency data, making it difficult to maximize the efficiency and effectiveness of sales negotiations. Furthermore, they provide uniform materials without considering the user's emotional state, which can cause stress and reduce efficiency. Therefore, there is a growing need for a system that can flexibly adjust the content of sales negotiations according to the agency's operational status and the user's emotions.

[1103] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1104] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using a generative AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, means for acquiring emotion data from a terminal including an emotion engine for analyzing a user's emotion, and means for adjusting the content of the negotiation materials based on the emotion data. This makes it possible to flexibly adjust the negotiation materials according to the operating status of the agent and the emotional state of the user, thereby maximizing the efficiency and effectiveness of negotiations.

[1105] "Agency Data" means data including agency sales, customer satisfaction, marketing spend, and performance scores.

[1106] "Generative AI Model" means an artificial intelligence model used to predict a Condition Score based on acquired agency data, and specifically includes a linear regression model.

[1107] "Condition Score" is a numerical value that indicates the operating condition of an agency, predicted using a generative AI model.

[1108] "Sales Decision Document" means a document containing improvement actions and recommendations to an agency that is generated based on a predicted condition score.

[1109] An "emotion engine" is an engine installed in a terminal that analyzes the user's voice and facial expressions to analyze emotional data.

[1110] A "terminal" is a device that collects user emotion data and runs an emotion engine, and provides business negotiation materials in cooperation with a server.

[1111] "Emotion data" is data that indicates the user's emotional state, analyzed using an emotion engine.

[1112] MODE FOR CARRYING OUT THE INVENTION

[1113] This system uses agent data to predict condition scores using an AI model and generates sales documents based on the results. It also provides a function to adjust the content of sales documents based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user.

[1114] Data acquisition and analysis

[1115] The server first retrieves agency data from a database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. Specifically, the data is retrieved using database software such as MySQL or PostgreSQL. This data provides the basis for evaluating performance. The server then formats the retrieved agency data and converts it into a format that can be input into the AI ​​model. This task is typically performed using the Python pandas library.

[1116] Condition score prediction by AI model

[1117] The server inputs the formatted data into a generative AI model to predict a condition score. A linear regression model is used as the generative AI model. For example, a pre-trained model can be used using a machine learning library such as scikit-learn. The model quantifies the operating condition of the agency based on the acquired data.

[1118] Generate sales documents

[1119] Next, the server generates sales documents based on the predicted condition scores. These sales documents include each agent's condition score and improvement actions based on the condition score. For example, for an agent with a low condition score, it suggests an improvement action such as "improving customer satisfaction is necessary," and for an agent with a high condition score, it includes a recommendation such as "strengthening sales activities would be effective."

[1120] Acquiring emotion data

[1121] The device recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine uses libraries such as TensorFlow and OpenCV to analyze audio and video data. The device uses this hardware and software to identify emotional states in real time. When the user is in front of the device, their facial expressions and speech are captured by the camera and microphone, and analyzed by the emotion engine.

[1122] Adjustment of business documents

[1123] The server receives the emotion data sent from the device and adjusts the content of the sales meeting materials. For example, if the user is feeling stressed, the server generates sales meeting materials using softer expressions, and if the user is relaxed, the server provides sales meeting materials including a detailed action plan. In this way, the sales meeting materials are dynamically adjusted according to the user's current emotional state.

[1124] User Use

[1125] The user uses the sales documents generated by the server to conduct sales negotiations. This allows the user to objectively evaluate the operational status of each agency and propose appropriate improvement actions. In addition, the sales documents provided correspond to the user's emotional state, enabling more effective communication.

[1126] Specific examples

[1127] For example, suppose Agency A's data looks like this:

[1128] If sales are 1,000, customer satisfaction is 70, marketing expenditures are 200, and the performance score is 80, the server uses this data to predict a condition score using a generative AI model. In this case, the predicted condition score is 80. Based on this condition score, the server generates sales documents that include content such as "Strengthening sales activities would be effective."

[1129] Furthermore, if the user's emotion engine determines that the user is relaxed, the server will provide sales materials with detailed action plans. Conversely, if the server determines that the user is stressed, the server will generate simpler, more positive sales materials.

[1130] Prompt Sentence Examples

[1131] Here are some examples of prompts to input to a generative AI model:

[1132] Data for Agent A: Sales = 1000, Customer Satisfaction = 70, Marketing Expenditure = 200, Performance Score = 80. Based on this data, predict the condition score and generate sales materials. Also, adjust the content of the materials based on the user's emotional state as "Relaxed."

[1133] conclusion

[1134] As a result, the present invention can efficiently and objectively evaluate agent data and provide negotiation materials that correspond to the user's emotional state, thereby reducing the user's workload and improving the effectiveness of negotiations.

[1135] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1136] Step 1: Data Acquisition

[1137] The server retrieves agency data from a database. This data includes agency sales, customer satisfaction, marketing spend, and performance scores. It uses database software such as MySQL or PostgreSQL. As input, it takes a specific agency ID and as output, it gets the corresponding agency data. The specific operation is to execute an SQL query to retrieve the data.

[1138] ...

[1139] sql

[1140] SELECT sales, customer_satisfaction, marketing_spend, performance_score FROM agencies WHERE agency_id = 'A';

[1141] Step 2: Data analysis

[1142] The server formats the acquired agency data and converts it into a format suitable for input to the generative AI model. This is done using the Python pandas library. The acquired agency data is used as input, and the output is data that has been formatted in a format suitable for input to the AI ​​model. For example, the data is converted into a data frame and appropriately scaled.

[1143] The specific operation is to create a data frame using pandas and scale the data using a standard scaler.

[1144] ...

[1145] python

[1146] import pandas as pd

[1147] from sklearn.preprocessing import StandardScaler

[1148] data = {'sales':

[1000] , 'customer_satisfaction':

[70] , 'marketing_spend':

[0200] , 'performance_score':

[80] }

[1149] df = pd.DataFrame(data)

[1150] scaler = StandardScaler()

[1151] scaled_data = scaler.fit_transform(df)

[1152] Step 3: Condition Score Prediction

[1153] The server inputs the formatted data into a generative AI model to predict a condition score. A linear regression model is used as the generative AI model. The scaled data is used as input, and the predicted condition score is obtained as output. The specific operation is to make a prediction using a pre-trained linear regression model.

[1154] ...

[1155] python

[1156] from sklearn.linear_model import LinearRegression

[1157] Use a pre-trained model (training steps omitted)

[1158] model = LinearRegression()

[1159] model.fit(training_data, target) Model training part (example)

[1160] condition_score = model.predict(scaled_data)

[1161] Step 4: Generate sales documents

[1162] The server generates sales materials based on the predicted condition scores. The materials include each agent's condition score and improvement actions based on the condition scores. The predicted condition scores are used as input, and the generated sales materials are obtained as output. The specific operation is to implement logic that generates different messages based on the condition scores.

[1163] ...

[1164] python

[1165] if condition_score >= 75:

[1166] suggestion = "Strengthening sales activities would be effective"

[1167] else:

[1168] suggestion = "Customer satisfaction needs to be improved"

[1169] document = f"Agency A's condition score is {condition_score}. {suggestion}"

[1170] Step 5: Acquire emotion data

[1171] The device recognizes emotions by analyzing the user's voice and facial expressions. The emotion engine uses libraries such as TensorFlow and OpenCV to analyze audio and video data. The user's audio and video data are used as input, and the identified user's emotion data is obtained as output. Specifically, data is acquired using a camera or microphone, and the emotion engine analyzes it.

[1172] ...

[1173] python

[1174] import cv2

[1175] import tensorflow as tf

[1176] cap = cv2.VideoCapture(0)

[1177] _, frame = cap.read()

[1178] emotion_model = tf.keras.models.load_model('emotion_model.h5')

[1179] emotion_prediction = emotion_model.predict(frame)

[1180] Step 6: Adjust the sales materials

[1181] The server adjusts the content of the sales documents based on the emotion data received from the device. It uses emotion data and existing sales documents as input, and obtains adjusted sales documents as output. Specifically, it softens the expressions in the documents or adds details depending on the emotion data.

[1182] ...

[1183] python

[1184] if emotion_prediction == 'stress':

[1185] document = f"Agency A's condition score is {condition_score}. Trimmed to be simple: {suggestion}"

[1186] else:

[1187] document = f"Agency A's condition score is {condition_score}. Includes detailed action plan: {suggestion}"

[1188] Step 7: Provide business documents

[1189] The user checks the sales negotiation materials generated by the server and uses them in sales negotiation activities. The adjusted sales negotiation materials are used as input, and the sales negotiation is conducted as output. The specific operation is to check the materials provided by the server on the terminal.

[1190] ...

[1191] python

[1192] print(document) Display the generated sales document

[1193] (Application example 2)

[1194] 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."

[1195] Conventional sales negotiation systems using agency data can evaluate the operational status of each agency, but they do not support the generation of sales negotiation materials that take the user's emotional state into account, making effective communication difficult. Furthermore, real-time information based on the user's emotional state is required for quick business decisions. To solve this problem, a system is needed that can comprehensively evaluate operational status based on agency data and generate sales negotiation materials that correspond to the user's emotional state.

[1196] 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.

[1197] In this invention, the server includes means for acquiring agent data from a database, means for predicting an agent's condition score using an AI model based on the agent data, means for generating negotiation materials based on the predicted condition score, means for recognizing a user's emotion from voice data, and means for adjusting the content of the negotiation materials based on the recognized emotion, thereby enabling efficient and objective evaluation of the agent data and provision of negotiation materials according to the user's emotional state.

[1198] "Agency Data" means data such as sales, customer satisfaction, marketing spend, and performance scores used to evaluate the operations of an agency.

[1199] A "database" is a system for systematically storing and managing information such as agency data.

[1200] An "AI model" is a mathematical and computational model that uses artificial intelligence technology to analyze and predict data.

[1201] The "condition score" is a numerical indicator of the operating condition of an agency, and is calculated based on various data.

[1202] "Negotiation Materials" means materials that include an agency's condition score and improvement actions and recommendations based thereon.

[1203] "Voice data" is digital data that records voice and is used to recognize the user's emotions.

[1204] An "emotion engine" is software that analyzes voice data, facial expression data, etc. to recognize the user's emotional state.

[1205] A "means" is a method or device for achieving a specific function or purpose.

[1206] The present invention is a system that uses agency data to predict condition scores using an AI model and generates sales materials based on the results. It also includes a function that adjusts the content of sales materials based on the user's emotions by combining it with an emotion engine that recognizes the user's emotions. This system consists of multiple steps involving a server, a terminal, and a user. The server generates and adjusts sales materials using agency data and user emotion data obtained from a database.

[1207] First, the server retrieves agency data from the database. This agency data includes sales, customer satisfaction, marketing expenditures, and performance scores, providing basic data for a detailed understanding of the agency's operating condition. Next, the server inputs the retrieved agency data into an AI model to predict a condition score. The AI ​​model uses a linear regression model, which quantifies the agency's operating condition.

[1208] The server then generates a sales document based on the predicted condition scores, which includes each agent's condition score and the associated improvement actions.

[1209] Furthermore, an emotion engine runs on the device and analyzes voice data to recognize the user's emotions. The Python library speech_recognition is used for voice recognition, and a transformers pipeline is used for emotion identification. It can identify various emotional states, such as whether the user is stressed or relaxed.

[1210] The server then adjusts the content of the sales presentation materials based on the emotion recognition results. For example, if the user is stressed, the presentation materials will use softer language. On the other hand, if the user is relaxed, the presentation materials will include a detailed action plan.

[1211] As a specific example, if a certain agency's data shows "shipping speed 800, misshipment rate 60, inventory status 150, and productivity score 85," the server predicts the condition score based on this data and calculates the result as "75." Based on this score, sales documents are generated that suggest improvement actions, such as "Improving shipping speed would be effective." Furthermore, if the user's voice data indicates that they are feeling stressed, the server adds the message, "Consider allocating personnel to reduce the workload."

[1212] In this way, the present invention realizes efficient and objective evaluation of agent data and provision of negotiation materials according to the user's emotional state, thereby reducing the user's workload and improving the effectiveness of negotiations.

[1213] An example prompt would be, "Predict the operational condition score for logistics center A based on its shipping speed, misshipment rate, inventory status, and productivity score, and generate improvement suggestions based on the manager's emotional state."

[1214] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1215] Step 1:

[1216] The server retrieves agency data from the database, including sales, customer satisfaction, marketing expenditures, and performance scores. The agency data is taken as input and used for subsequent analysis.

[1217] Step 2:

[1218] The server inputs the acquired agency data into an AI model to predict the agency's condition score. Here, a linear regression model is used to analyze the data. The input is the agency data, and the output is the condition score.

[1219] Step 3:

[1220] The server generates sales documents based on the predicted condition scores, which include improvement actions and recommendations for each agent depending on the condition score. The input is the condition score, and the sales documents are generated as the output.

[1221] Step 4:

[1222] The emotion engine installed on the device recognizes emotions from the user's voice data. Here, we use the speech_recognition and transformers pipeline. The input is the user's voice data, and the output is the user's recognized emotional state.

[1223] Step 5:

[1224] The server adjusts the content of the sales documents based on the recognized emotional state. For example, if the user is feeling stressed, the sales documents are adjusted to use softer expressions. The input is the emotional state and the sales documents, and the adjusted sales documents are obtained as the output.

[1225] Step 6:

[1226] The user conducts business negotiations using the business negotiation materials generated and adjusted by the server. Here, the user proceeds while checking proposals based on the operational status of each agency and business negotiation materials that correspond to the user's emotional state. The input is the business negotiation materials, and the user uses them to conduct business negotiations as the output.

[1227] 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.

[1228] 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.

[1229] 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.

[1230] 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.

[1231] 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.

[1232] 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.

[1233] 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).

[1234] 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.

[1235] 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."

[1236] 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.

[1237] 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).

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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.

[1242] 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.

[1243] 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.

[1244] 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.

[1245] 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.

[1246] 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.

[1247] 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.

[1248] The following is further disclosed regarding the above embodiment.

[1249] (Claim 1)

[1250] a means for retrieving agency data from a database;

[1251] A means to predict agent condition scores using an AI model based on agent data; and

[1252] means for generating sales documents based on the predicted condition scores;

[1253] A system including:

[1254] (Claim 2)

[1255] 10. The system of claim 1, wherein the AI ​​model comprises a linear regression model.

[1256] (Claim 3)

[1257] 10. The system of claim 1, wherein the agency data includes sales, customer satisfaction, marketing expenditures, and performance scores.

[1258] "Example 1"

[1259] (Claim 1)

[1260] a means for retrieving agency data from a database;

[1261] a means for predicting an agent's condition score using a generative AI model based on agent data; and

[1262] means for generating sales documents based on the predicted condition scores;

[1263] means for providing the generated business negotiation materials to a terminal;

[1264] A system including:

[1265] (Claim 2)

[1266] 10. The system of claim 1, wherein the generative AI model comprises a linear regression model.

[1267] (Claim 3)

[1268] 10. The system of claim 1, wherein the agency data includes sales, customer satisfaction, marketing expenditures, and performance scores.

[1269] "Application Example 1"

[1270] (Claim 1)

[1271] a means for retrieving agency data from a database;

[1272] A means to predict agent condition scores using an AI model based on agent data; and

[1273] means for generating sales documents based on the predicted condition scores;

[1274] a means for acquiring store operation data, predicting a store condition score using the data, and proposing store operation improvement actions based on the predicted score;

[1275] A system including:

[1276] (Claim 2)

[1277] 10. The system of claim 1, wherein the AI ​​model comprises a linear regression model.

[1278] (Claim 3)

[1279] 10. The system of claim 1, wherein the agency data and store operations data includes sales, customer satisfaction, marketing expenditures, and performance scores.

[1280] "Example 2: Combining Emotion Engines"

[1281] (Claim 1)

[1282] a means for retrieving agency data from a database;

[1283] a means for predicting an agent's condition score using a generative AI model based on agent data; and

[1284] means for generating sales documents based on the predicted condition scores;

[1285] means for acquiring emotion data from a terminal including an emotion engine for analyzing a user's emotion;

[1286] a means for adjusting the content of the sales materials based on the emotion data;

[1287] A system including:

[1288] (Claim 2)

[1289] 10. The system of claim 1, wherein the generative AI model comprises a linear regression model.

[1290] (Claim 3)

[1291] 10. The system of claim 1, wherein the agency data includes sales, customer satisfaction, marketing expenditures, and performance scores.

[1292] "Application example 2 when combining emotion engines"

[1293] (Claim 1)

[1294] a means for retrieving agency data from a database;

[1295] A means to predict agent condition scores using an AI model based on agent data; and

[1296] means for generating sales documents based on the predicted condition scores;

[1297] means for recognizing a user's emotion from voice data;

[1298] a means for adjusting the content of sales pitch materials based on the perceived sentiment;

[1299] A system including:

[1300] (Claim 2)

[1301] 10. The system of claim 1, wherein the AI ​​model comprises a linear regression model.

[1302] (Claim 3)

[1303] 10. The system of claim 1, wherein the agency data includes sales, customer satisfaction, marketing expenditures, and performance scores. [Explanation of symbols]

[1304] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for retrieving agency data from a database; A means to predict agent condition scores using an AI model based on agent data; and means for generating sales documents based on the predicted condition scores; A system including:

2. 10. The system of claim 1, wherein the AI ​​model comprises a linear regression model.

3. 10. The system of claim 1, wherein the agency data includes sales, customer satisfaction, marketing expenditures, and performance scores.

Images