System

Abstract

A system is provided.SOLUTION: The system includes a means for acquiring customer data, a means for pre-processing the acquired customer data, a means for matching the optimum corporation based on the attribute information of the merchandise and the acquired customer data, a means for giving a score to each corporation and creating a ranking, and a means for generating a report including a ranking result and outputting the report in a user-browsable format.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] Conventional corporate product introduction support systems have had the problem of making it difficult to effectively identify suitable corporations, limiting the effectiveness of sales strategies. In particular, they lacked a means to properly preprocess large amounts of customer data and quickly identify corporations that were most suitable for the product. As a result, sales representatives spent a great deal of time analyzing the vast amount of data, hindering effective sales activities. The present invention aims to solve these problems and improve the success rate of product introduction. [Means for solving the problem]

[0005] In the present invention, the problems are solved by the following means.

[0006] First, a means for acquiring customer data is provided, thereby collecting all necessary customer data related to the product. Next, a means for preprocessing the acquired customer data, including cleaning and deleting duplicate data, is provided to organize the data and improve its accuracy for analysis. Furthermore, a means for matching the optimal company based on the product's attribute information and the preprocessed customer data is provided. This matching means analyzes customer purchase history and extracts patterns related to the product. Furthermore, a means for assigning scores to each company and creating rankings is introduced, thereby visualizing the suitability and priority of the company for the product. Finally, a means for generating a report including the ranking results and outputting it in a format that users can easily view is provided to support the planning and execution of sales strategies. These means enable effective company identification and improved sales efficiency.

[0007] "Customer data" includes information about corporations and individual customers, specifically data such as company name, industry, size, location, and purchase history.

[0008] "Preprocessing" is the process of cleaning the acquired customer data, removing duplicate data, standardizing data formats, etc. before analyzing it.

[0009] "Merchandise" refers to the goods and services provided by a company and sold to specific customers or markets.

[0010] "Product attribute information" refers to information relating to the characteristics and specifications of a particular product, as well as information relating to the target market and customer demographic.

[0011] "Matching" is the process of comparing the product's attribute information with customer data to find the corporation that is most suitable for the product.

[0012] The "score" is an evaluation value that quantifies the suitability and priority of each company based on customer data.

[0013] A "ranking" is a list of companies ranked based on their scores, in order of priority.

[0014] A "report" is a report summarizing the analysis results and ranking results, and is provided in a format that is easy for users to understand.

[0015] "Users" refers to sales and marketing personnel who use this system to develop product introduction strategies.

[0016] A "server" is a computer system that performs back-end processing such as data processing, analysis, and report generation.

[0017] A "terminal" is a device through which a user accesses the server, inputs data, and views results. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention relates to a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. This system mainly comprises the following components: data acquisition means, data preprocessing means, corporation matching means, ranking means, and report generation means.

[0040] The program for this system is described below.

[0041] Data Acquisition Method

[0042] The server first receives a request from the terminal. The request includes the conditions for acquiring customer data and attribute information for the product. Based on the applicable conditions, the server accesses the database and acquires the necessary customer data.

[0043] Data preprocessing measures

[0044] The server performs preprocessing on the acquired customer data. Specifically, it cleans the data and removes duplicate data. For example, it deletes records containing NULL values ​​and standardizes data with different formats. It also performs complementation processing on incomplete data to optimize it.

[0045] Corporate matching method

[0046] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. Product attributes include information such as industry, company size, and location. The server extracts suitable corporations from the customer data based on this attribute information. It also analyzes past purchase history and evaluates the applicability of the corporation to the product.

[0047] Ranking methods

[0048] The server assigns scores to matched companies and generates a ranking. Scoring is based on the suitability of the product and purchase history. For example, if the product attributes and customer attributes show a high match, a high score is assigned. The list of companies is sorted in descending order based on the score to create a ranking list.

[0049] Report Generation Method

[0050] Finally, the server creates a report based on the generated ranking results. The report includes a list of the companies that are most suitable for the product, their scores, etc. The server sends this report to the terminal so that the user can easily view it. The report is provided in the format requested by the user, such as PDF or HTML.

[0051] Specific examples

[0052] As a specific example, let's say a user wants to sell a new cloud service. The user makes a request from their device to the server to "extract companies suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from a customer database and performs data cleaning. Next, it matches companies that have used similar services in the past based on the attributes of the cloud service. The resulting list of candidate companies is scored and ranked in order of priority. Finally, the ranking list is generated as a report and sent to the user's device. The user can use this report to efficiently conduct their sales activities.

[0053] As described above, the present invention is a system that realizes effective corporate extraction and sales support through a series of processes from data acquisition to processing, matching, ranking, and report generation.

[0054] The processing flow will be explained below.

[0055] Step 1: Receiving a request

[0056] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal then sends this request to the server.

[0057] Step 2: Database Access

[0058] The server accesses the customer database based on the request received from the terminal, and retrieves the required data using SQL queries under specific filter conditions (e.g., specific industry or region).

[0059] Step 3: Data Acquisition

[0060] The server receives customer data returned from a database query, including demographic information such as company name, industry, size, location, and purchase history.

[0061] Step 4: Data Cleaning

[0062] The server cleans the acquired customer data, for example, removing records containing NULL values ​​and converting data with inconsistent formats into a unified format. Missing data is also imputed during this process.

[0063] Step 5: Remove duplicates

[0064] The server detects and removes duplicate records from the cleaned data, identifying duplicates based on company name or ID and merging them into a single record.

[0065] Step 6: Processing product attribute information

[0066] The server analyzes the product's attribute information and extracts its characteristics, including the product's industry, company size, location, etc.

[0067] Step 7: Corporate Matching

[0068] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. It analyzes past purchase history and corporate attributes to extract the corporation that is most suitable for the product.

[0069] Step 8: Scoring

[0070] The server assigns a score to each matched company. This score is calculated based on the product compatibility and purchasing history. For example, a company that shows a high compatibility is assigned a high score.

[0071] Step 9: Ranking Generation

[0072] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[0073] Step 10: Generate reports

[0074] The server generates a report based on the ranking results. This report includes the score for each company and an explanation of the reasons. The generated report is available in PDF format, HTML format, etc.

[0075] Step 11: Submit report

[0076] The server sends the generated report to the terminal, which receives the report and displays it for the user to view.

[0077] Based on the reports sent from the server, users can use their terminals to identify corporations that are suitable for specific products and efficiently conduct sales activities.

[0078] Example 1

[0079] 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."

[0080] In the past, there was no established method for effectively utilizing customer data to identify the most suitable companies. This resulted in inefficient sales activities and made it difficult to approach the right companies. In addition, data preprocessing and company scoring / ranking were done manually, which was time-consuming and labor-intensive, and lacked accuracy.

[0081] 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.

[0082] In this invention, the server includes means for receiving a prompt sentence entered by a user, means for acquiring customer data, means for preprocessing the acquired customer data, means for matching the optimal corporation based on the attribute information of the product and the preprocessed customer data, means for assigning a score to each corporation and creating a ranking, and means for generating a report including the ranking results and outputting it in a format that can be viewed by the user. This enables the system to efficiently and accurately extract corporations and improve the efficiency of sales activities based on the results.

[0083] A "prompt sentence" refers to a sentence that allows a user to input specific instructions or conditions to a system.

[0084] "Customer data" is a dataset that contains information about companies and individuals, including information about industry, company size, purchasing history, and more.

[0085] "Preprocessing" refers to a series of steps taken to prepare raw data for analysis, including cleaning the data and removing duplicate data.

[0086] "Product attribute information" refers to information that indicates the characteristics and conditions of a specific product or service, including the type of industry, company size, and service content.

[0087] "Matching" refers to the process of combining customer data and product attribute information based on specific conditions to select the most suitable corporation.

[0088] "Scoring" refers to the process of assigning a rating to each entity based on specific criteria.

[0089] A "ranking" is a list of scored corporations arranged in order of their evaluation scores, and is ranked based on specific criteria.

[0090] "Report" means any document or digital data containing the system-generated list of optimal corporations, their scores, rankings, etc.

[0091] A "process" is a series of steps or procedures that are carried out to achieve a particular purpose.

[0092] The present invention is a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. This system receives prompts entered by the user, acquires customer data, and provides the user with a list of optimal corporations through preprocessing, matching, ranking, and report generation.

[0093] Hardware and Software Configuration

[0094] server

[0095] The server processes user requests, performs complex data analysis, and generates rankings. Specifically, it is responsible for the following:

[0096] Receiving a prompt

[0097] Customer data retrieval and database access

[0098] Data preprocessing (cleaning, de-duplicating data)

[0099] Applying a matching algorithm

[0100] Scoring and ranking generation

[0101] Creating and sending reports

[0102] Terminal

[0103] The terminal provides an interface for users to input prompts and also has the functionality to receive and display reports. A typical computer, tablet, or smartphone can be used as the terminal.

[0104] Data acquisition and preprocessing

[0105] The server retrieves customer data from the database based on the prompt entered by the user. This data includes information such as industry, company size, purchasing history, etc. The retrieved data undergoes the following preprocessing steps to prepare it for analysis:

[0106] Cleaning: Filling and removing records containing null values ​​and incomplete data.

[0107] Remove duplicate data: If the same information appears in multiple records, remove it.

[0108] Format unification: Standardize date formats and text formats.

[0109] Matching and Scoring

[0110] The server matches the appropriate company based on the pre-processed data and product attribute information, using machine learning algorithms to take into account past purchase history and company characteristics.

[0111] The server then assigns scores to the matched businesses and generates rankings. Scoring criteria include the degree to which the product attributes match the business's needs and its purchasing history.

[0112] Report generation and delivery

[0113] The server creates a report based on the ranking results. The report includes a list of the most suitable companies and their respective scores, and is generated in a format (PDF, HTML, etc.) according to the user's request. Finally, the report is sent to the terminal so that the user can easily view it.

[0114] Specific examples

[0115] As a concrete example, consider a user who wants to sell a new cloud service. The user sends a request to the server from their device saying, "I want to sell a new cloud service, so please extract suitable companies targeting small and medium-sized businesses in the IT industry and generate a report." In response, the server performs the following steps:

[0116] 1. Obtain customer data on the IT industry and small and medium-sized businesses from the database

[0117] 2. Preprocessing the acquired data (cleaning, deleting duplicate data)

[0118] 3. Matching with companies that have used similar services in the past based on cloud service attribute information

[0119] 4. Scores are assigned to candidate companies and a ranking is generated.

[0120] 5. Finally, the ranking list is generated as a report and sent to the user's device.

[0121] This system allows users to efficiently conduct sales activities.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1: Receiving the prompt

[0124] The server receives the prompt text entered by the user from the terminal. This prompt text includes attribute information about the product and the conditions for the target corporations. For example, a user might enter something like, "I want to sell a new cloud service, so please extract suitable corporations targeting small and medium-sized enterprises in the IT industry and generate a report." The input is in text format, and the server analyzes it to extract the information needed for the next step.

[0125] Step 2: Obtain customer data

[0126] The server retrieves relevant customer data from the database based on the information extracted from the prompt. For example, it searches for and retrieves customer data that corresponds to the "IT industry" and "small and medium-sized enterprises." In this case, it uses an SQL query to efficiently extract the required data. The input is the condition set by the prompt, and the output is a list of matching customer data.

[0127] Step 3: Data Preprocessing

[0128] The server performs pre-processing on the acquired customer data, specifically including the following operations:

[0129] Data cleaning: Remove records containing null values ​​and impute incomplete data.

[0130] De-duplicate data: Detect and delete duplicates of identical customer data.

[0131] Standardize formats: Standardize date and text formats.

[0132] The input is the acquired customer data, and the output is a pre-processed, clean dataset.

[0133] Step 4: Matching Companies

[0134] The server matches the most suitable company based on the pre-processed customer data and product attribute information. Specifically, it performs the following operations:

[0135] The preprocessed customer data is analyzed to search for corporations that match the product attributes (e.g., cloud services).

[0136] Evaluate the applicability of products taking into account past purchasing history and company characteristics.

[0137] The input is a preprocessed clean dataset and product attribute information, and the output is a list of matching corporations.

[0138] Step 5: Scoring and Ranking

[0139] The server assigns scores to the matched companies and generates a ranking. Specifically, it performs the following operations:

[0140] A score is assigned based on the degree to which the product's attributes match the company's needs.

[0141] Scores are set taking into consideration past purchasing history and interest in the product.

[0142] The list of corporations is sorted in descending order based on the scores to create a ranking list.

[0143] The input is a list of matched entities and the output is a ranked list of entities.

[0144] Step 6: Generate and send the report

[0145] The server creates a report based on the ranking results and sends it to the user's device. Specifically, it performs the following operations:

[0146] The ranking list is formatted in a format such as PDF or HTML according to the user's request.

[0147] The report will include a list of the best companies and their scores.

[0148] The completed report is sent to the user's terminal so that the user can easily view it.

[0149] The input is a ranked list of companies, and the output is a report in a user-viewable format.

[0150] (Application example 1)

[0151] 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."

[0152] Effective target selection is essential in modern advertising campaigns. However, extracting optimal targets from large amounts of customer data and delivering appropriate advertisements to them remains a difficult challenge. Conventional methods often require manual data preprocessing and target scoring, which is labor-intensive and time-consuming, and has the problem of low accuracy. Furthermore, there is a lack of systems that allow end users to easily use this series of processes.

[0153] 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.

[0154] In this invention, the server includes a means for acquiring customer data, a means for preprocessing the acquired customer data, a means for matching optimal corporations based on product attribute information and the acquired customer data, a means for assigning scores to each corporation and creating rankings, a means for generating a report including the ranking results and outputting it in a format viewable by users, and a means for inputting advertising campaign conditions, extracting targets based on target customer data, scoring them, generating a ranking list, and outputting it in report format. This enables quick and accurate target selection for advertising campaigns and supports sales activities. Furthermore, scoring and ranking are automated, allowing users to efficiently reach optimal targets.

[0155] "Customer data" refers to data containing information about a specific customer, including customer attributes and purchasing history.

[0156] "Preprocessing" is the process of preparing acquired data for analysis, and includes cleaning the data and deleting duplicate data.

[0157] "Product attribute information" is information that indicates characteristics related to a specific product, and includes the industry, company size, location, and the like.

[0158] "Matching" is the process of selecting the most suitable target based on specific criteria.

[0159] "Scoring" is the process of assigning an evaluation criterion to an object based on specific criteria, thereby quantifying the object's suitability.

[0160] "Ranking" is the process of ordering objects based on the scoring results, listing them in order from highest to lowest rating.

[0161] A "report" is a document summarizing the results of analysis and evaluation, and is provided to users in PDF or HTML format.

[0162] "Ad campaign conditions" are setting information related to a particular ad campaign, including target attributes, ad content, and the like.

[0163] "Targeted Customer Data" means data about customers selected based on the terms of an advertising campaign.

[0164] "Filtering" is a process of removing unnecessary parts from data based on specific conditions.

[0165] "Click history" is data on when users have clicked on ads in the past, and is used to evaluate the effectiveness of advertising.

[0166] The present invention is a system that utilizes customer data to extract targets suitable for advertising campaigns and support effective advertising activities. This system includes the following main components: data acquisition means, data preprocessing means, target matching means, scoring means, ranking creation means, report generation means, and advertising campaign condition input means.

[0167] System Program

[0168] The server includes the following means:

[0169] 1. Data acquisition method

[0170] The user inputs the conditions of the advertising campaign (target attributes, ad content, etc.) from the terminal. Based on this, the server accesses the database and retrieves customer data. This database includes customer attributes, purchase history, click history, etc.

[0171] 2. Data preprocessing methods

[0172] The server performs data cleaning on the acquired customer data, specifically deleting records containing NULL values, deleting duplicate data, standardizing data formats, and completing incomplete data.

[0173] 3. Target Matching Methods

[0174] The server extracts suitable targets from customer data based on the conditions of the ad campaign, filtering them based on target attributes and past ad click history.

[0175] 4. Scoring Methods

[0176] The server then scores the filtered targets based on the degree of match with the target attributes and past ad click history.

[0177] 5. Ranking Creation Method

[0178] Based on the scoring results, targets are ranked in descending order of score, making it clear which targets have higher priority.

[0179] 6. Report Generation Methods

[0180] The server generates a report based on the ranking results. The report is exported in PDF or HTML format and sent to the device. Users can view this report and use it for advertising activities.

[0181] Hardware and software used

[0182] Hardware: Smartphones, servers

[0183] Software: Python 3.x, Pandas, scikit-learn, FPDF

[0184] Specific examples

[0185] For example, suppose a user wants to run an advertising campaign for "technology" and "small and medium-sized" businesses. The following prompts can be used to drive the system:

[0186] Please create a Python program to obtain target customer data suitable for the "Technology Industry" and "Small and Medium-sized Business" advertising campaign, clean the data, perform target matching, score, rank, and generate a report.

[0187] Using this prompt, the server accesses the database, retrieves target customer data, preprocesses it, filters it, and scores it, and finally generates a ranking list that can be exported as a report, allowing users to efficiently develop their advertising activities.

[0188] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0189] Step 1:

[0190] The user inputs the conditions of the advertising campaign from the terminal.

[0191] Specifically, target attributes (industry, size) and advertising content are entered. This input data is sent to the server. The input data includes the campaign name, target industry, company size, etc. A prompt sentence is generated to acquire the data.

[0192] Step 2:

[0193] The server accesses the database based on the entered advertising campaign conditions to retrieve customer data.

[0194] The customer data acquired includes basic customer attributes (industry, company size, location), past purchase history, click history, etc. A database query is executed to extract data that matches the conditions. The extracted data is stored in temporary memory.

[0195] Step 3:

[0196] The server performs data preprocessing on the acquired customer data.

[0197] Specifically, the data is cleaned, records containing NULL values ​​and duplicate data are deleted, the format of customer attributes is standardized, and incomplete data is supplemented. After preprocessing, the data is formatted and ready for high-precision analysis.

[0198] Step 4:

[0199] The server performs target matching based on the pre-processed customer data.

[0200] Filter customer data that matches campaign criteria to identify suitable customers for advertising, using a condition-based SQL filtering query.

[0201] Step 5:

[0202] The server scores the matched targets.

[0203] Scores are assigned based on the degree of match with the target's attributes and past ad click history. Scoring is performed using a standardized scaling algorithm (e.g., MinMaxScaler). Evaluation indicators include the degree of match with industry, suitability with company size, and relevance of past click history.

[0204] Step 6:

[0205] The server ranks the targets based on the scoring results.

[0206] The targets are sorted in descending order of score to generate a ranking list, which is used to determine the priority of sales activities. The generated list is stored in temporary memory.

[0207] Step 7:

[0208] The server generates a report based on the ranking results.

[0209] The report includes the target name, score, ranking, etc. The report can be generated in PDF or HTML format and sent to the device, and the report is provided in a format that users can easily view and download.

[0210] Through the above processing steps, target selection in an advertising campaign is automated, and a system that supports effective advertising activities is realized.

[0211] 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.

[0212] This invention relates to a system that utilizes customer data to extract effective corporations for the introduction of products currently handled by the team. This system includes processes for acquiring, preprocessing, matching, scoring, and generating reports on customer data, and further improves the user experience by combining it with an emotion engine that recognizes user emotions.

[0213] System Components

[0214] The system mainly has the following components:

[0215] Data Acquisition Method

[0216] Data preprocessing measures

[0217] Corporate matching method

[0218] Scoring Instrument

[0219] Ranking methods

[0220] Report Generation Method

[0221] Emotion Engine

[0222] Data Acquisition Method

[0223] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal sends this request to the server, which then accesses the customer database to retrieve the required data.

[0224] Data preprocessing measures

[0225] The server then cleans the acquired customer data and removes duplicates, removing records containing NULL values, converting data with inconsistent formats into a unified format, and filling in missing data.

[0226] Corporate matching method

[0227] The server matches the optimal corporation based on the product's attribute information (industry, company size, location, etc.) and pre-processed customer data. Past purchase history is also analyzed to extract the corporation that is most suitable for the product.

[0228] Scoring Instrument

[0229] The server assigns a score to each matched company. This score is calculated based on the suitability of the product and the purchase history. For example, a company that shows a high suitability is assigned a high score.

[0230] Ranking methods

[0231] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[0232] Report Generation Method

[0233] The server generates a report based on the ranking results, which includes the score for each company and an explanation of the reasons, and is provided in PDF, HTML, and other formats.

[0234] Emotion Engine

[0235] The emotion engine has the ability to recognize emotions from user reactions and input data. The emotion engine is used to perform the following processes:

[0236] Adjusting report display based on user sentiment

[0237] Adjusting the scoring algorithm based on user sentiment

[0238] Adjusting ranking priorities based on user sentiment

[0239] Specific examples

[0240] As a specific example, consider a situation where a user who wants to sell a new cloud service requests the server from their device to "extract corporations suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from its customer database and performs data cleaning. Next, it matches the cloud service attributes with companies that have used similar services in the past. The resulting list of candidate corporations is scored and ranked in order of priority. The server then generates a report based on this and sends it to the device. The user can use this report to efficiently conduct sales activities.

[0241] Furthermore, by utilizing an emotion engine to recognize the user's emotions, the report display format is adjusted according to the user's state. For example, if the user is feeling stressed, the report will be displayed in an easy-to-understand and concise format. Furthermore, the scoring algorithm and ranking priority are also adjusted based on the user's emotions, enabling more appropriate proposals to be made to the user. In this way, the user experience is improved, resulting in more effective corporate identification and more efficient sales activities.

[0242] The processing flow will be explained below.

[0243] Step 1: Receiving a request

[0244] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal then sends this request to the server.

[0245] Step 2: Database Access

[0246] The server accesses the customer database based on the request received from the terminal, and retrieves the required data based on specific filter conditions (e.g., specific industry or region) using an SQL query.

[0247] Step 3: Data Acquisition

[0248] The server receives customer data returned from a database query, including demographic information such as company name, industry, size, location, and purchase history.

[0249] Step 4: Data Cleaning

[0250] The server cleans the customer data it retrieves. For example, it deletes records containing NULL values ​​and converts data with inconsistent formats into a unified format. It also performs complementation processing on incomplete data to optimize it.

[0251] Step 5: Remove duplicates

[0252] The server detects and removes duplicate records from the cleaned data, identifying duplicates based on company name or ID and merging them into a single record.

[0253] Step 6: Processing product attribute information

[0254] The server analyzes the product's attribute information and extracts its characteristics, including the type of business, company size, and location.

[0255] Step 7: Corporate Matching

[0256] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. It also analyzes past purchase history and other data to identify the corporation that is most suitable for the product.

[0257] Step 8: Scoring

[0258] The server assigns a score to each matched company. This score is calculated based on the product compatibility and purchasing history. For example, a company that shows a high compatibility is assigned a high score.

[0259] Step 9: Ranking Generation

[0260] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[0261] Step 10: Generate reports

[0262] The server generates a report based on the ranking results. This report includes the score for each company and an explanation of the reasons. The generated report is available in PDF, HTML, and other formats.

[0263] Step 11: Emotion Recognition

[0264] The server uses an emotion engine to recognize the user's emotions. It evaluates the user's emotional state based on their reactions and input data, and identifies their current emotion.

[0265] Step 12: Adjusting the report display

[0266] Based on the results of emotion recognition, the server adjusts the report display format. For example, if the user is feeling stressed, the report will be displayed in a simple and easy-to-understand manner.

[0267] Step 13: Adjust the scoring algorithm

[0268] Based on the emotion recognition results, the server adjusts the scoring algorithm, for example, presenting a more detailed analysis if the user is excited.

[0269] Step 14: Adjusting Ranking Priority

[0270] Based on the results of emotion recognition, the server adjusts the ranking priority. For example, if the user is calm, the ranking is displayed with normal priority.

[0271] Step 15: Report Submission

[0272] The server generates and adjusts the report and sends it to the terminal, which receives it and displays it to the user.

[0273] These are the processing steps of this system. Based on the reports provided, users can efficiently identify companies that are suitable for their products and conduct sales activities. Adjustments made by the emotion engine also aim to improve the user experience.

[0274] Example 2

[0275] 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."

[0276] Conventional systems that utilize customer data often perform data acquisition, preprocessing, and even corporate matching and scoring individually, without adjusting to the user's experience or emotions. This results in problems such as the information users receive being suboptimal, and insufficient efficiency in sales activities. Furthermore, the lack of a mechanism for adjusting the report content and display format based on the user's current emotions and state makes it difficult to provide information that is easy for users to understand. Given this background, there is a need for the development of a system that utilizes customer data and dynamically provides information based on the user's emotions.

[0277] 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.

[0278] In this invention, the server includes means for acquiring customer data, means for preprocessing the acquired customer data, means for matching the most suitable corporation based on the attribute information of the product and the acquired customer data, means for assigning a score to each corporation and creating a ranking, and means for recognizing the user's emotions and adjusting the report display format and scoring algorithm based on the emotions. This allows the user to receive the information they need in the most suitable format and conduct sales activities more efficiently.

[0279] "Customer data" refers to a dataset that includes all information about customers, and is used to develop sales strategies for products and to respond to customers.

[0280] "Preprocessing" refers to a series of processes such as data cleaning, deleting duplicate data, and standardizing data formats that are carried out to improve the quality of acquired data.

[0281] "Product attribute information" refers to information about the features and characteristics associated with a specific product, such as the industry, company size, and location.

[0282] "Corporate matching" refers to the process of identifying the most suitable business partners and client companies based on product attribute information and pre-processed customer data.

[0283] "Scoring" refers to the process of assigning an evaluation score to matched businesses based on suitability, purchasing history, etc.

[0284] "Ranking" refers to ranking corporations based on the scoring results and creating a list according to importance and suitability.

[0285] A "report" is a document generated based on the ranking results, which includes scores for each corporation and explanations of the reasons, and is provided in PDF or HTML format.

[0286] An "emotion engine" is an engine that has the ability to recognize emotions from user reactions and input data and adjust the system's behavior based on that.

[0287] The present invention relates to a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. The system includes a data acquisition means, a data preprocessing means, a corporation matching means, a scoring means, a ranking means, a report generation means, and an emotion engine.

[0288] System program generation

[0289] The program of this system is realized by the cooperation of the server, terminals, and user operations. The server mainly processes and analyzes data, and the terminals provide an interface with the user. The program includes the following main software libraries:

[0290] MySQL (registered trademark) (database management)

[0291] pandas (data preprocessing)

[0292] scikit-learn (machine learning model)

[0293] Fpdf (PDF report generator)

[0294] Transformers (emotion recognition)

[0295] Process Overview

[0296] The user uses a terminal to send a request to extract corporations suitable for introducing a product. This request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal sends this request to the server, which then accesses the MySQL database to retrieve the required customer data.

[0297] The server uses the pandas library to clean the acquired customer data. Specifically, it deletes records containing NULL values, converts data with inconsistent formats into a unified format, and fills in missing data. The server then uses a scikit-learn machine learning model to match the optimal company based on the product attribute information and preprocessed customer data. It analyzes past purchase history and other factors to extract companies that are suitable for the product.

[0298] For each matched company, the server assigns a score using a random forest regression model. This score is calculated based on the product's suitability and past purchase history. Based on the scoring results, the server generates a ranking of companies in descending order of score.

[0299] Based on the generated ranking results, the server uses the Fpdf library to generate a report, which includes scores for each company and explanations of the results, and is provided to the terminal in PDF or HTML format.

[0300] Additionally, the server recognizes the user's emotions through an emotion engine and adjusts the report presentation and scoring algorithms accordingly. Emotion recognition is performed using the Transformers library, and if the user is feeling stressed, the report will be presented in a clearer and more concise format.

[0301] Specific examples

[0302] Consider the case where a user who wants to sell a new cloud service requests the server from a device to "extract corporations suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from a customer database and performs data cleaning. Next, it matches companies that have used similar services in the past based on the attributes of the cloud service. The resulting list of candidate corporations is scored and ranked in order of priority. The server generates a report based on this and sends it to the device. The user can use this report to efficiently conduct sales activities. Furthermore, an emotion engine is used to recognize the user's emotions, and the display format of the report is adjusted according to the user's state.

[0303] Prompt Sentence Examples

[0304] We would like to use customer data to identify companies suitable for the cloud services we currently offer. First, we would like you to acquire and cleanse the data based on the following criteria: industry is IT, company size is small and medium-sized enterprises. Next, we would like you to match the most suitable companies based on the attributes of the cloud services, score and rank them, and generate a report. We would also like you to adjust the report display format and scoring algorithm based on user sentiment.

[0305] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0306] Program processing flow

[0307] Step 1: User submits request

[0308] Input: User inputs product information and customer data filter criteria

[0309] Process: The user uses the terminal to enter the "Request to extract legal entities suitable for cloud services" in the interface and clicks the submit button.

[0310] Output: The device forwards this request data to the server.

[0311] Step 2: Data Acquisition

[0312] Input: Request data sent from the terminal

[0313] Process: The server connects to the customer database and executes a SQL query such as "SELECT FROM customer table WHERE industry='IT' AND company size='Small / Medium Business'" to extract the relevant data.

[0314] Output: Obtain the required customer data and pass it on to the next processing step

[0315] Step 3: Data Preprocessing

[0316] Input: Customer data retrieved by the server

[0317] Processing: The server uses the pandas library to create a data frame, remove records containing NULL values, convert data with different formats to a unified format, and impute missing data.

[0318] Specific behavior: Execute code such as "df.dropna(inplace=True)" or "df.fillna("Unknown", inplace=True)".

[0319] Output: Preprocessed, clean data passed to the next processing step

[0320] Step 4: Corporate Matching

[0321] Input: Preprocessed clean customer data and product attribute information

[0322] Processing: The server uses scikit-learn's KNN (k-nearest neighbor) algorithm to identify corporations with high similarity based on past product usage history.

[0323] Specific operations: Perform operations such as "model.fit(data)" and "model.predict(new data)".

[0324] Output: Pass the list of matched entities to the next processing step

[0325] Step 5: Scoring

[0326] Input: Matched legal entity list

[0327] Processing: The server calculates the fitness of each legal entity using a random forest regression model and assigns a high score to legal entities that show a high fitness.

[0328] Specific operation: Execute code such as "model.fit(X_train, y_train)" or "model.predict(X_test)".

[0329] Output: Pass the scored list of legal entities to the next processing step

[0330] Step 6: Ranking

[0331] Input: List of scored legal entities

[0332] Processing: The server sorts the list of corporations using pandas' "df.sort_values(by='score', ascending=False)" and arranges them in order of highest score.

[0333] Output: Pass the ranked list of companies to the next processing step

[0334] Step 7: Generate reports

[0335] Input: Ranked corporate list

[0336] Processing: The server uses the Fpdf library to generate a report that includes the scores for each company and an explanation of the reasons.

[0337] Specific operation: Execute code such as "pdf.cell(200, 10, txt="Corporate List", ln=True)" and "pdf.output("report.pdf")".

[0338] Output: Generate reports in PDF and HTML format and send them to your device.

[0339] Step 8: Emotional Engine Alignment

[0340] Input: User reactions and input data

[0341] Processing: The server uses the Transformers library to analyze the user's emotions. It executes code like "emotion_analyzer = pipeline('sentiment-analysis')" and "result = emotion_analyzer("text")" to adjust the report display format and scoring algorithm based on the emotions.

[0342] Output: Providing tailored reports and algorithms to users

[0343] (Application example 2)

[0344] 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."

[0345] Conventional corporate matching systems have basic functions such as data cleaning, matching, scoring, and report generation to effectively identify product applications, but they are unable to adjust the report display content or matching algorithms to take user emotions into account. This prevents the system from providing optimal information based on the user's emotional state, limiting the improvement of user experience and efficient sales activities. Furthermore, the system lacks a function to automatically generate report content from input prompts using a generative AI model, resulting in low report creation efficiency.

[0346] 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.

[0347] In this invention, the server includes means for acquiring customer data, means for preprocessing the acquired customer data, means for matching optimal corporations based on product attribute information and the acquired customer data, means for assigning scores to each corporation and creating rankings, means for generating a report including the ranking results and outputting it in a format viewable by the user, means for recognizing user emotions and adjusting the report display, means for adjusting the scoring algorithm and ranking priority based on the user emotions, means for detecting user emotions through video input, and means for automatically generating report content from input prompt sentences using a generative AI model. This enables the provision of more optimal information according to the user's emotional state, improving the user experience and enabling more efficient sales activities.

[0348] "Customer data" refers to information about the corporation to which the product is applied, and includes data such as the customer's name, industry, purchase history, and location.

[0349] "Preprocessing" refers to a series of processes to improve the quality of data, such as cleaning the acquired data, deleting duplicate data, standardizing formats, and filling in missing data.

[0350] "Product attribute information" refers to unique information related to a product, such as its characteristics and functions, target industry, company size, and geographical conditions.

[0351] "Matching" is the process of selecting the most suitable corporation based on the product's attribute information and pre-processed customer data, taking into consideration the customer's industry, purchasing history, company size, etc.

[0352] "Scoring" is the process of quantifying the suitability of products for each matched corporation and assigning them a score.

[0353] "Ranking" refers to arranging corporations in descending order of score based on the scoring results.

[0354] A "report" is a document containing ranking results and an explanation of the reasons for the scores, which is provided to users in a format that can be viewed by them.

[0355] "User emotion" refers to the current emotional state of the user using the system, and includes emotions such as joy, anger, sadness, and stress.

[0356] "Emotion recognition" is a technology that analyzes user input data, primarily video input, to detect the user's emotional state.

[0357] A "scoring algorithm" refers to the calculation method and rules for assigning scores to corporations, and quantifies the suitability of products.

[0358] "Priority" refers to the importance or position of a company in the ranking, and is adjusted based on user sentiment.

[0359] "Video input" refers to input data for recognizing a user's emotions, and includes video footage capturing the user's facial expressions and movements.

[0360] A "generative AI model" is an artificial intelligence model for automated report generation and data analysis that provides appropriate output based on input data.

[0361] A "prompt" is an instruction for operating a generative AI model, and specifically describes the instructions for report generation and data analysis.

[0362] This invention is a system that utilizes customer data to identify the most suitable corporations for product introduction. This system encompasses a series of processes from customer data acquisition to preprocessing, corporation matching, scoring, ranking, report generation, and user emotion recognition.

[0363] Hardware and Software

[0364] The system is built using the following hardware and software:

[0365] Hardware: Smartphones, tablets

[0366] Software: Python, pandas, scikit-learn, FPDF, emotion_recognition (provisional package)

[0367] Data acquisition and preprocessing

[0368] The server receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. Based on this, the server retrieves customer data from the database. The retrieved data is then cleaned, duplicate data is removed, the format is standardized, and missing data is filled in.

[0369] Corporate Matching and Scoring

[0370] The server uses cosine similarity calculations to match the optimal company based on the product's attribute information and pre-processed customer data. It then assigns a score to each company according to a scoring algorithm. This score quantifies the product's suitability.

[0371] Ranking and Report Generation

[0372] Based on the scoring results, the companies are ranked in order of highest score and a report is generated. The generated report is output in PDF format and provided in a format that can be viewed by users.

[0373] Emotion Recognition and Report Adjustment

[0374] The server recognizes the user's emotions through video input. Based on this emotional data, it adjusts the report display format and changes the scoring algorithm and ranking priority. If the user is feeling stressed, the report will be adjusted to be more clear and concise.

[0375] Generative AI model usage example

[0376] The server automatically generates report content using a generative AI model. The generative AI model generates an appropriate report based on the input of a prompt sentence. The following is an example of a prompt sentence:

[0377] user_request = {

[0378] "ad_attributes": [0.8, 0.2, 0.3],

[0379] "user_video": "path / to / user_video.mp4"

[0380] }

[0381] Specific examples

[0382] For example, if a user wants to find target corporations for a new advertising campaign, they provide the system with product attribute information and a user's video input. The server retrieves and preprocesses the customer data to match the corporations that best suit the product. Next, after scoring and ranking, a report based on emotion recognition is generated. This report is automatically generated using a generative AI model and presented in a format that users can view.

[0383] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0384] Step 1:

[0385] The user sends a request from their device. The request includes information about the product to be analyzed (e.g., advertising campaign attribute information) and filter conditions for the required customer data. Based on this input data, the server determines which customer data to retrieve.

[0386] Step 2:

[0387] The server accesses the customer database and retrieves customer data that matches the specified product information and filter criteria. This process involves executing a database query to extract the required records. The retrieved customer data is output in raw data format.

[0388] Step 3:

[0389] The server preprocesses the customer data it acquires. Specifically, it cleans the data (removing NULL values, standardizing formats, and filling in missing data) and removes duplicate data. This process improves the quality of the data and makes it suitable for analysis. The preprocessed data is then output.

[0390] Step 4:

[0391] The server matches the optimal company based on the product's attribute information and pre-processed customer data. It calculates the compatibility between each company and product using cosine similarity calculations. It generates a compatibility score based on this input data, which becomes the output.

[0392] Step 5:

[0393] The server assigns a score to each matched company based on the generated compatibility score. This score assignment process is quantified (e.g., in the range of 0 to 100) based on the compatibility of the product. This score data is output.

[0394] Step 6:

[0395] The server ranks the corporations in descending order based on the scoring results. In this ranking process, the score data is sorted in descending order to create a ranking list. This ranking list is output.

[0396] Step 7:

[0397] The server generates a report based on the ranking list. The report includes scores for each company and an explanation of the reasons. The report is generated and output in PDF format.

[0398] Step 8:

[0399] The server performs emotion recognition based on the video input data provided by the user. It analyzes facial expressions from the video data and detects the user's emotional state (e.g., joy, anger, sadness, stress, etc.). This emotional data is output.

[0400] Step 9:

[0401] The server adjusts the report display format, scoring algorithm, and ranking priority based on the emotion data. For example, if the user is feeling stressed, the report will be adjusted to be more clear and concise. The adjusted report is then output.

[0402] Step 10:

[0403] The server automatically generates report content using a generative AI model. Based on the prompt input (e.g., "user_request = { "ad_attributes": [0.8, 0.2, 0.3], "user_video": "path / to / user_video.mp4"}"), the generative AI model creates an appropriate report. The generated report based on this prompt is output.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] [Second embodiment]

[0408] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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."

[0420] The present invention relates to a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. This system mainly comprises the following components: data acquisition means, data preprocessing means, corporation matching means, ranking means, and report generation means.

[0421] The program for this system is described below.

[0422] Data Acquisition Method

[0423] The server first receives a request from the terminal. The request includes the conditions for acquiring customer data and attribute information for the product. Based on the applicable conditions, the server accesses the database and acquires the necessary customer data.

[0424] Data preprocessing measures

[0425] The server performs preprocessing on the acquired customer data. Specifically, it cleans the data and removes duplicate data. For example, it deletes records containing NULL values ​​and standardizes data with different formats. It also performs complementation processing on incomplete data to optimize it.

[0426] Corporate matching method

[0427] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. Product attributes include information such as industry, company size, and location. The server extracts suitable corporations from the customer data based on this attribute information. It also analyzes past purchase history and evaluates the applicability of the corporation to the product.

[0428] Ranking methods

[0429] The server assigns scores to matched companies and generates a ranking. Scoring is based on the suitability of the product and purchase history. For example, if the product attributes and customer attributes show a high match, a high score is assigned. The list of companies is sorted in descending order based on the score to create a ranking list.

[0430] Report Generation Method

[0431] Finally, the server creates a report based on the generated ranking results. The report includes a list of the companies that are most suitable for the product, their scores, etc. The server sends this report to the terminal so that the user can easily view it. The report is provided in the format requested by the user, such as PDF or HTML.

[0432] Specific examples

[0433] As a specific example, let's say a user wants to sell a new cloud service. The user makes a request from their device to the server to "extract companies suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from a customer database and performs data cleaning. Next, it matches companies that have used similar services in the past based on the attributes of the cloud service. The resulting list of candidate companies is scored and ranked in order of priority. Finally, the ranking list is generated as a report and sent to the user's device. The user can use this report to efficiently conduct their sales activities.

[0434] As described above, the present invention is a system that realizes effective corporate extraction and sales support through a series of processes from data acquisition to processing, matching, ranking, and report generation.

[0435] The processing flow will be explained below.

[0436] Step 1: Receiving a request

[0437] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal then sends this request to the server.

[0438] Step 2: Database Access

[0439] The server accesses the customer database based on the request received from the terminal, and retrieves the required data using SQL queries under specific filter conditions (e.g., specific industry or region).

[0440] Step 3: Data Acquisition

[0441] The server receives customer data returned from a database query, including demographic information such as company name, industry, size, location, and purchase history.

[0442] Step 4: Data Cleaning

[0443] The server cleans the acquired customer data, for example, removing records containing NULL values ​​and converting data with inconsistent formats into a unified format. Missing data is also imputed during this process.

[0444] Step 5: Remove duplicates

[0445] The server detects and removes duplicate records from the cleaned data, identifying duplicates based on company name or ID and merging them into a single record.

[0446] Step 6: Processing product attribute information

[0447] The server analyzes the product's attribute information and extracts its characteristics, including the product's industry, company size, location, etc.

[0448] Step 7: Corporate Matching

[0449] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. It analyzes past purchase history and corporate attributes to extract the corporation that is most suitable for the product.

[0450] Step 8: Scoring

[0451] The server assigns a score to each matched company. This score is calculated based on the product compatibility and purchasing history. For example, a company that shows a high compatibility is assigned a high score.

[0452] Step 9: Ranking Generation

[0453] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[0454] Step 10: Generate reports

[0455] The server generates a report based on the ranking results. This report includes the score for each company and an explanation of the reasons. The generated report is available in PDF format, HTML format, etc.

[0456] Step 11: Submit report

[0457] The server sends the generated report to the terminal, which receives the report and displays it for the user to view.

[0458] Based on the reports sent from the server, users can use their terminals to identify corporations that are suitable for specific products and efficiently conduct sales activities.

[0459] Example 1

[0460] 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."

[0461] In the past, there was no established method for effectively utilizing customer data to identify the most suitable companies. This resulted in inefficient sales activities and made it difficult to approach the right companies. In addition, data preprocessing and company scoring / ranking were done manually, which was time-consuming and labor-intensive, and lacked accuracy.

[0462] 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.

[0463] In this invention, the server includes means for receiving a prompt sentence entered by a user, means for acquiring customer data, means for preprocessing the acquired customer data, means for matching the optimal corporation based on the attribute information of the product and the preprocessed customer data, means for assigning a score to each corporation and creating a ranking, and means for generating a report including the ranking results and outputting it in a format that can be viewed by the user. This enables the system to efficiently and accurately extract corporations and improve the efficiency of sales activities based on the results.

[0464] A "prompt sentence" refers to a sentence that allows a user to input specific instructions or conditions to a system.

[0465] "Customer data" is a dataset that contains information about companies and individuals, including information about industry, company size, purchasing history, and more.

[0466] "Preprocessing" refers to a series of steps taken to prepare raw data for analysis, including cleaning the data and removing duplicate data.

[0467] "Product attribute information" refers to information that indicates the characteristics and conditions of a specific product or service, including the type of industry, company size, and service content.

[0468] "Matching" refers to the process of combining customer data and product attribute information based on specific conditions to select the most suitable corporation.

[0469] "Scoring" refers to the process of assigning a rating to each entity based on specific criteria.

[0470] A "ranking" is a list of scored corporations arranged in order of their evaluation scores, and is ranked based on specific criteria.

[0471] "Report" means any document or digital data containing the system-generated list of optimal corporations, their scores, rankings, etc.

[0472] A "process" is a series of steps or procedures that are carried out to achieve a particular purpose.

[0473] The present invention is a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. This system receives prompts entered by the user, acquires customer data, and provides the user with a list of optimal corporations through preprocessing, matching, ranking, and report generation.

[0474] Hardware and Software Configuration

[0475] server

[0476] The server processes user requests, performs complex data analysis, and generates rankings. Specifically, it is responsible for the following:

[0477] Receiving a prompt

[0478] Customer data retrieval and database access

[0479] Data preprocessing (cleaning, de-duplicating data)

[0480] Applying a matching algorithm

[0481] Scoring and ranking generation

[0482] Creating and sending reports

[0483] Terminal

[0484] The terminal provides an interface for users to input prompts and also has the functionality to receive and display reports. A typical computer, tablet, or smartphone can be used as the terminal.

[0485] Data acquisition and preprocessing

[0486] The server retrieves customer data from the database based on the prompt entered by the user. This data includes information such as industry, company size, purchasing history, etc. The retrieved data undergoes the following preprocessing steps to prepare it for analysis:

[0487] Cleaning: Filling and removing records containing null values ​​and incomplete data.

[0488] Remove duplicate data: If the same information appears in multiple records, remove it.

[0489] Format unification: Standardize date formats and text formats.

[0490] Matching and Scoring

[0491] The server matches the appropriate company based on the pre-processed data and product attribute information, using machine learning algorithms to take into account past purchase history and company characteristics.

[0492] The server then assigns scores to the matched businesses and generates rankings. Scoring criteria include the degree to which the product attributes match the business's needs and its purchasing history.

[0493] Report generation and delivery

[0494] The server creates a report based on the ranking results. The report includes a list of the most suitable companies and their respective scores, and is generated in a format (PDF, HTML, etc.) according to the user's request. Finally, the report is sent to the terminal so that the user can easily view it.

[0495] Specific examples

[0496] As a concrete example, consider a user who wants to sell a new cloud service. The user sends a request to the server from their device saying, "I want to sell a new cloud service, so please extract suitable companies targeting small and medium-sized businesses in the IT industry and generate a report." In response, the server performs the following steps:

[0497] 1. Obtain customer data on the IT industry and small and medium-sized businesses from the database

[0498] 2. Preprocessing the acquired data (cleaning, deleting duplicate data)

[0499] 3. Matching with companies that have used similar services in the past based on cloud service attribute information

[0500] 4. Scores are assigned to candidate companies and a ranking is generated.

[0501] 5. Finally, the ranking list is generated as a report and sent to the user's device.

[0502] This system allows users to efficiently conduct sales activities.

[0503] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0504] Step 1: Receiving the prompt

[0505] The server receives the prompt text entered by the user from the terminal. This prompt text includes attribute information about the product and the conditions for the target corporations. For example, a user might enter something like, "I want to sell a new cloud service, so please extract suitable corporations targeting small and medium-sized enterprises in the IT industry and generate a report." The input is in text format, and the server analyzes it to extract the information needed for the next step.

[0506] Step 2: Obtain customer data

[0507] The server retrieves relevant customer data from the database based on the information extracted from the prompt. For example, it searches for and retrieves customer data that corresponds to the "IT industry" and "small and medium-sized enterprises." In this case, it uses an SQL query to efficiently extract the required data. The input is the condition set by the prompt, and the output is a list of matching customer data.

[0508] Step 3: Data Preprocessing

[0509] The server performs pre-processing on the acquired customer data, specifically including the following operations:

[0510] Data cleaning: Remove records containing null values ​​and impute incomplete data.

[0511] De-duplicate data: Detect and delete duplicates of identical customer data.

[0512] Standardize formats: Standardize date and text formats.

[0513] The input is the acquired customer data, and the output is a pre-processed, clean dataset.

[0514] Step 4: Matching Companies

[0515] The server matches the most suitable company based on the pre-processed customer data and product attribute information. Specifically, it performs the following operations:

[0516] The preprocessed customer data is analyzed to search for corporations that match the product attributes (e.g., cloud services).

[0517] Evaluate the applicability of products taking into account past purchasing history and company characteristics.

[0518] The input is a preprocessed clean dataset and product attribute information, and the output is a list of matching corporations.

[0519] Step 5: Scoring and Ranking

[0520] The server assigns scores to the matched companies and generates a ranking. Specifically, it performs the following operations:

[0521] A score is assigned based on the degree to which the product's attributes match the company's needs.

[0522] Scores are set taking into consideration past purchasing history and interest in the product.

[0523] The list of corporations is sorted in descending order based on the scores to create a ranking list.

[0524] The input is a list of matched entities and the output is a ranked list of entities.

[0525] Step 6: Generate and send the report

[0526] The server creates a report based on the ranking results and sends it to the user's device. Specifically, it performs the following operations:

[0527] The ranking list is formatted in a format such as PDF or HTML according to the user's request.

[0528] The report will include a list of the best companies and their scores.

[0529] The completed report is sent to the user's terminal so that the user can easily view it.

[0530] The input is a ranked list of companies, and the output is a report in a user-viewable format.

[0531] (Application example 1)

[0532] 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."

[0533] Effective target selection is essential in modern advertising campaigns. However, extracting optimal targets from large amounts of customer data and delivering appropriate advertisements to them remains a difficult challenge. Conventional methods often require manual data preprocessing and target scoring, which is labor-intensive and time-consuming, and has the problem of low accuracy. Furthermore, there is a lack of systems that allow end users to easily use this series of processes.

[0534] 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.

[0535] In this invention, the server includes a means for acquiring customer data, a means for preprocessing the acquired customer data, a means for matching optimal corporations based on product attribute information and the acquired customer data, a means for assigning scores to each corporation and creating rankings, a means for generating a report including the ranking results and outputting it in a format viewable by users, and a means for inputting advertising campaign conditions, extracting targets based on target customer data, scoring them, generating a ranking list, and outputting it in report format. This enables quick and accurate target selection for advertising campaigns and supports sales activities. Furthermore, scoring and ranking are automated, allowing users to efficiently reach optimal targets.

[0536] "Customer data" refers to data containing information about a specific customer, including customer attributes and purchasing history.

[0537] "Preprocessing" is the process of preparing acquired data for analysis, and includes cleaning the data and deleting duplicate data.

[0538] "Product attribute information" is information that indicates characteristics related to a specific product, and includes the industry, company size, location, and the like.

[0539] "Matching" is the process of selecting the most suitable target based on specific criteria.

[0540] "Scoring" is the process of assigning an evaluation criterion to an object based on specific criteria, thereby quantifying the object's suitability.

[0541] "Ranking" is the process of ordering objects based on the scoring results, listing them in order from highest to lowest rating.

[0542] A "report" is a document summarizing the results of analysis and evaluation, and is provided to users in PDF or HTML format.

[0543] "Ad campaign conditions" are setting information related to a particular ad campaign, including target attributes, ad content, and the like.

[0544] "Targeted Customer Data" means data about customers selected based on the terms of an advertising campaign.

[0545] "Filtering" is a process of removing unnecessary parts from data based on specific conditions.

[0546] "Click history" is data on when users have clicked on ads in the past, and is used to evaluate the effectiveness of advertising.

[0547] The present invention is a system that utilizes customer data to extract targets suitable for advertising campaigns and support effective advertising activities. This system includes the following main components: data acquisition means, data preprocessing means, target matching means, scoring means, ranking creation means, report generation means, and advertising campaign condition input means.

[0548] System Program

[0549] The server includes the following means:

[0550] 1. Data acquisition method

[0551] The user inputs the conditions of the advertising campaign (target attributes, ad content, etc.) from the terminal. Based on this, the server accesses the database and retrieves customer data. This database includes customer attributes, purchase history, click history, etc.

[0552] 2. Data preprocessing methods

[0553] The server performs data cleaning on the acquired customer data, specifically deleting records containing NULL values, deleting duplicate data, standardizing data formats, and completing incomplete data.

[0554] 3. Target Matching Methods

[0555] The server extracts suitable targets from customer data based on the conditions of the ad campaign, filtering them based on target attributes and past ad click history.

[0556] 4. Scoring Methods

[0557] The server then scores the filtered targets based on the degree of match with the target attributes and past ad click history.

[0558] 5. Ranking Creation Method

[0559] Based on the scoring results, targets are ranked in descending order of score, making it clear which targets have higher priority.

[0560] 6. Report Generation Methods

[0561] The server generates a report based on the ranking results. The report is exported in PDF or HTML format and sent to the device. Users can view this report and use it for advertising activities.

[0562] Hardware and software used

[0563] Hardware: Smartphones, servers

[0564] Software: Python 3.x, Pandas, scikit-learn, FPDF

[0565] Specific examples

[0566] For example, suppose a user wants to run an advertising campaign for "technology" and "small and medium-sized" businesses. The following prompts can be used to drive the system:

[0567] Please create a Python program to obtain target customer data suitable for the "Technology Industry" and "Small and Medium-sized Business" advertising campaign, clean the data, perform target matching, score, rank, and generate a report.

[0568] Using this prompt, the server accesses the database, retrieves target customer data, preprocesses it, filters it, and scores it, and finally generates a ranking list that can be exported as a report, allowing users to efficiently develop their advertising activities.

[0569] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0570] Step 1:

[0571] The user inputs the conditions of the advertising campaign from the terminal.

[0572] Specifically, target attributes (industry, size) and advertising content are entered. This input data is sent to the server. The input data includes the campaign name, target industry, company size, etc. A prompt sentence is generated to acquire the data.

[0573] Step 2:

[0574] The server accesses the database based on the entered advertising campaign conditions to retrieve customer data.

[0575] The customer data acquired includes basic customer attributes (industry, company size, location), past purchase history, click history, etc. A database query is executed to extract data that matches the conditions. The extracted data is stored in temporary memory.

[0576] Step 3:

[0577] The server performs data preprocessing on the acquired customer data.

[0578] Specifically, the data is cleaned, records containing NULL values ​​and duplicate data are deleted, the format of customer attributes is standardized, and incomplete data is supplemented. After preprocessing, the data is formatted and ready for high-precision analysis.

[0579] Step 4:

[0580] The server performs target matching based on the pre-processed customer data.

[0581] Filter customer data that matches campaign criteria to identify suitable customers for advertising, using a condition-based SQL filtering query.

[0582] Step 5:

[0583] The server scores the matched targets.

[0584] Scores are assigned based on the degree of match with the target's attributes and past ad click history. Scoring is performed using a standardized scaling algorithm (e.g., MinMaxScaler). Evaluation indicators include the degree of match with industry, suitability with company size, and relevance of past click history.

[0585] Step 6:

[0586] The server ranks the targets based on the scoring results.

[0587] The targets are sorted in descending order of score to generate a ranking list, which is used to determine the priority of sales activities. The generated list is stored in temporary memory.

[0588] Step 7:

[0589] The server generates a report based on the ranking results.

[0590] The report includes the target name, score, ranking, etc. The report can be generated in PDF or HTML format and sent to the device, and the report is provided in a format that users can easily view and download.

[0591] Through the above processing steps, target selection in an advertising campaign is automated, and a system that supports effective advertising activities is realized.

[0592] 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.

[0593] This invention relates to a system that utilizes customer data to extract effective corporations for the introduction of products currently handled by the team. This system includes processes for acquiring, preprocessing, matching, scoring, and generating reports on customer data, and further improves the user experience by combining it with an emotion engine that recognizes user emotions.

[0594] System Components

[0595] The system mainly has the following components:

[0596] Data Acquisition Method

[0597] Data preprocessing measures

[0598] Corporate matching method

[0599] Scoring Instrument

[0600] Ranking methods

[0601] Report Generation Method

[0602] Emotion Engine

[0603] Data Acquisition Method

[0604] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal sends this request to the server, which then accesses the customer database to retrieve the required data.

[0605] Data preprocessing measures

[0606] The server then cleans the acquired customer data and removes duplicates, removing records containing NULL values, converting data with inconsistent formats into a unified format, and filling in missing data.

[0607] Corporate matching method

[0608] The server matches the optimal corporation based on the product's attribute information (industry, company size, location, etc.) and pre-processed customer data. Past purchase history is also analyzed to extract the corporation that is most suitable for the product.

[0609] Scoring Instrument

[0610] The server assigns a score to each matched company. This score is calculated based on the suitability of the product and the purchase history. For example, a company that shows a high suitability is assigned a high score.

[0611] Ranking methods

[0612] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[0613] Report Generation Method

[0614] The server generates a report based on the ranking results, which includes the score for each company and an explanation of the reasons, and is provided in PDF, HTML, and other formats.

[0615] Emotion Engine

[0616] The emotion engine has the ability to recognize emotions from user reactions and input data. The emotion engine is used to perform the following processes:

[0617] Adjusting report display based on user sentiment

[0618] Adjusting the scoring algorithm based on user sentiment

[0619] Adjusting ranking priorities based on user sentiment

[0620] Specific examples

[0621] As a specific example, consider a situation where a user who wants to sell a new cloud service requests the server from their device to "extract corporations suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from its customer database and performs data cleaning. Next, it matches the cloud service attributes with companies that have used similar services in the past. The resulting list of candidate corporations is scored and ranked in order of priority. The server then generates a report based on this and sends it to the device. The user can use this report to efficiently conduct sales activities.

[0622] Furthermore, by utilizing an emotion engine to recognize the user's emotions, the report display format is adjusted according to the user's state. For example, if the user is feeling stressed, the report will be displayed in an easy-to-understand and concise format. Furthermore, the scoring algorithm and ranking priority are also adjusted based on the user's emotions, enabling more appropriate proposals to be made to the user. In this way, the user experience is improved, resulting in more effective corporate identification and more efficient sales activities.

[0623] The processing flow will be explained below.

[0624] Step 1: Receiving a request

[0625] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal then sends this request to the server.

[0626] Step 2: Database Access

[0627] The server accesses the customer database based on the request received from the terminal, and retrieves the required data based on specific filter conditions (e.g., specific industry or region) using an SQL query.

[0628] Step 3: Data Acquisition

[0629] The server receives customer data returned from a database query, including demographic information such as company name, industry, size, location, and purchase history.

[0630] Step 4: Data Cleaning

[0631] The server cleans the customer data it retrieves. For example, it deletes records containing NULL values ​​and converts data with inconsistent formats into a unified format. It also performs complementation processing on incomplete data to optimize it.

[0632] Step 5: Remove duplicates

[0633] The server detects and removes duplicate records from the cleaned data, identifying duplicates based on company name or ID and merging them into a single record.

[0634] Step 6: Processing product attribute information

[0635] The server analyzes the product's attribute information and extracts its characteristics, including the type of business, company size, and location.

[0636] Step 7: Corporate Matching

[0637] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. It also analyzes past purchase history and other data to identify the corporation that is most suitable for the product.

[0638] Step 8: Scoring

[0639] The server assigns a score to each matched company. This score is calculated based on the product compatibility and purchasing history. For example, a company that shows a high compatibility is assigned a high score.

[0640] Step 9: Ranking Generation

[0641] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[0642] Step 10: Generate reports

[0643] The server generates a report based on the ranking results. This report includes the score for each company and an explanation of the reasons. The generated report is available in PDF, HTML, and other formats.

[0644] Step 11: Emotion Recognition

[0645] The server uses an emotion engine to recognize the user's emotions. It evaluates the user's emotional state based on their reactions and input data, and identifies their current emotion.

[0646] Step 12: Adjusting the report display

[0647] Based on the results of emotion recognition, the server adjusts the report display format. For example, if the user is feeling stressed, the report will be displayed in a simple and easy-to-understand manner.

[0648] Step 13: Adjust the scoring algorithm

[0649] Based on the emotion recognition results, the server adjusts the scoring algorithm, for example, presenting a more detailed analysis if the user is excited.

[0650] Step 14: Adjusting Ranking Priority

[0651] Based on the results of emotion recognition, the server adjusts the ranking priority. For example, if the user is calm, the ranking is displayed with normal priority.

[0652] Step 15: Report Submission

[0653] The server generates and adjusts the report and sends it to the terminal, which receives it and displays it to the user.

[0654] These are the processing steps of this system. Based on the reports provided, users can efficiently identify companies that are suitable for their products and conduct sales activities. Adjustments made by the emotion engine also aim to improve the user experience.

[0655] Example 2

[0656] 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."

[0657] Conventional systems that utilize customer data often perform data acquisition, preprocessing, and even corporate matching and scoring individually, without adjusting to the user's experience or emotions. This results in problems such as the information users receive being suboptimal, and insufficient efficiency in sales activities. Furthermore, the lack of a mechanism for adjusting the report content and display format based on the user's current emotions and state makes it difficult to provide information that is easy for users to understand. Given this background, there is a need for the development of a system that utilizes customer data and dynamically provides information based on the user's emotions.

[0658] 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.

[0659] In this invention, the server includes means for acquiring customer data, means for preprocessing the acquired customer data, means for matching the most suitable corporation based on the attribute information of the product and the acquired customer data, means for assigning a score to each corporation and creating a ranking, and means for recognizing the user's emotions and adjusting the report display format and scoring algorithm based on the emotions. This allows the user to receive the information they need in the most suitable format and conduct sales activities more efficiently.

[0660] "Customer data" refers to a dataset that includes all information about customers, and is used to develop sales strategies for products and to respond to customers.

[0661] "Preprocessing" refers to a series of processes such as data cleaning, deleting duplicate data, and standardizing data formats that are carried out to improve the quality of acquired data.

[0662] "Product attribute information" refers to information about the features and characteristics associated with a specific product, such as the industry, company size, and location.

[0663] "Corporate matching" refers to the process of identifying the most suitable business partners and client companies based on product attribute information and pre-processed customer data.

[0664] "Scoring" refers to the process of assigning an evaluation score to matched businesses based on suitability, purchasing history, etc.

[0665] "Ranking" refers to ranking corporations based on the scoring results and creating a list according to importance and suitability.

[0666] A "report" is a document generated based on the ranking results, which includes scores for each corporation and explanations of the reasons, and is provided in PDF or HTML format.

[0667] An "emotion engine" is an engine that has the ability to recognize emotions from user reactions and input data and adjust the system's behavior based on that.

[0668] The present invention relates to a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. The system includes a data acquisition means, a data preprocessing means, a corporation matching means, a scoring means, a ranking means, a report generation means, and an emotion engine.

[0669] System program generation

[0670] The program of this system is realized by the cooperation of the server, terminals, and user operations. The server mainly processes and analyzes data, and the terminals provide an interface with the user. The program includes the following main software libraries:

[0671] MySQL (database management)

[0672] pandas (data preprocessing)

[0673] scikit-learn (machine learning model)

[0674] Fpdf (PDF report generator)

[0675] Transformers (emotion recognition)

[0676] Process Overview

[0677] The user uses a terminal to send a request to extract corporations suitable for introducing a product. This request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal sends this request to the server, which then accesses the MySQL database to retrieve the required customer data.

[0678] The server uses the pandas library to clean the acquired customer data. Specifically, it deletes records containing NULL values, converts data with inconsistent formats into a unified format, and fills in missing data. The server then uses a scikit-learn machine learning model to match the optimal company based on the product attribute information and preprocessed customer data. It analyzes past purchase history and other factors to extract companies that are suitable for the product.

[0679] For each matched company, the server assigns a score using a random forest regression model. This score is calculated based on the product's suitability and past purchase history. Based on the scoring results, the server generates a ranking of companies in descending order of score.

[0680] Based on the generated ranking results, the server uses the Fpdf library to generate a report, which includes scores for each company and explanations of the results, and is provided to the terminal in PDF or HTML format.

[0681] Additionally, the server recognizes the user's emotions through an emotion engine and adjusts the report presentation and scoring algorithms accordingly. Emotion recognition is performed using the Transformers library, and if the user is feeling stressed, the report will be presented in a clearer and more concise format.

[0682] Specific examples

[0683] Consider the case where a user who wants to sell a new cloud service requests the server from a device to "extract corporations suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from a customer database and performs data cleaning. Next, it matches companies that have used similar services in the past based on the attributes of the cloud service. The resulting list of candidate corporations is scored and ranked in order of priority. The server generates a report based on this and sends it to the device. The user can use this report to efficiently conduct sales activities. Furthermore, an emotion engine is used to recognize the user's emotions, and the display format of the report is adjusted according to the user's state.

[0684] Prompt Sentence Examples

[0685] We would like to use customer data to identify companies suitable for the cloud services we currently offer. First, we would like you to acquire and cleanse the data based on the following criteria: industry is IT, company size is small and medium-sized enterprises. Next, we would like you to match the most suitable companies based on the attributes of the cloud services, score and rank them, and generate a report. We would also like you to adjust the report display format and scoring algorithm based on user sentiment.

[0686] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0687] Program processing flow

[0688] Step 1: User submits request

[0689] Input: User inputs product information and customer data filter criteria

[0690] Process: The user uses the terminal to enter the "Request to extract legal entities suitable for cloud services" in the interface and clicks the submit button.

[0691] Output: The device forwards this request data to the server.

[0692] Step 2: Data Acquisition

[0693] Input: Request data sent from the terminal

[0694] Process: The server connects to the customer database and executes a SQL query such as "SELECT FROM customer table WHERE industry='IT' AND company size='Small / Medium Business'" to extract the relevant data.

[0695] Output: Obtain the required customer data and pass it on to the next processing step

[0696] Step 3: Data Preprocessing

[0697] Input: Customer data retrieved by the server

[0698] Processing: The server uses the pandas library to create a data frame, remove records containing NULL values, convert data with different formats to a unified format, and impute missing data.

[0699] Specific behavior: Execute code such as "df.dropna(inplace=True)" or "df.fillna("Unknown", inplace=True)".

[0700] Output: Preprocessed, clean data passed to the next processing step

[0701] Step 4: Corporate Matching

[0702] Input: Preprocessed clean customer data and product attribute information

[0703] Processing: The server uses scikit-learn's KNN (k-nearest neighbor) algorithm to identify corporations with high similarity based on past product usage history.

[0704] Specific operations: Perform operations such as "model.fit(data)" and "model.predict(new data)".

[0705] Output: Pass the list of matched entities to the next processing step

[0706] Step 5: Scoring

[0707] Input: Matched legal entity list

[0708] Processing: The server calculates the fitness of each legal entity using a random forest regression model and assigns a high score to legal entities that show a high fitness.

[0709] Specific operation: Execute code such as "model.fit(X_train, y_train)" or "model.predict(X_test)".

[0710] Output: Pass the scored list of legal entities to the next processing step

[0711] Step 6: Ranking

[0712] Input: List of scored legal entities

[0713] Processing: The server sorts the list of corporations using pandas' "df.sort_values(by='score', ascending=False)" and arranges them in order of highest score.

[0714] Output: Pass the ranked list of companies to the next processing step

[0715] Step 7: Generate reports

[0716] Input: Ranked corporate list

[0717] Processing: The server uses the Fpdf library to generate a report that includes the scores for each company and an explanation of the reasons.

[0718] Specific operation: Execute code such as "pdf.cell(200, 10, txt="Corporate List", ln=True)" and "pdf.output("report.pdf")".

[0719] Output: Generate reports in PDF and HTML format and send them to your device.

[0720] Step 8: Emotional Engine Alignment

[0721] Input: User reactions and input data

[0722] Processing: The server uses the Transformers library to analyze the user's emotions. It executes code like "emotion_analyzer = pipeline('sentiment-analysis')" and "result = emotion_analyzer("text")" to adjust the report display format and scoring algorithm based on the emotions.

[0723] Output: Providing tailored reports and algorithms to users

[0724] (Application example 2)

[0725] 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."

[0726] Conventional corporate matching systems have basic functions such as data cleaning, matching, scoring, and report generation to effectively identify product applications, but they are unable to adjust the report display content or matching algorithms to take user emotions into account. This prevents the system from providing optimal information based on the user's emotional state, limiting the improvement of user experience and efficient sales activities. Furthermore, the system lacks a function to automatically generate report content from input prompts using a generative AI model, resulting in low report creation efficiency.

[0727] 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.

[0728] In this invention, the server includes means for acquiring customer data, means for preprocessing the acquired customer data, means for matching optimal corporations based on product attribute information and the acquired customer data, means for assigning scores to each corporation and creating rankings, means for generating a report including the ranking results and outputting it in a format viewable by the user, means for recognizing user emotions and adjusting the report display, means for adjusting the scoring algorithm and ranking priority based on the user emotions, means for detecting user emotions through video input, and means for automatically generating report content from input prompt sentences using a generative AI model. This enables the provision of more optimal information according to the user's emotional state, improving the user experience and enabling more efficient sales activities.

[0729] "Customer data" refers to information about the corporation to which the product is applied, and includes data such as the customer's name, industry, purchase history, and location.

[0730] "Preprocessing" refers to a series of processes to improve the quality of data, such as cleaning the acquired data, deleting duplicate data, standardizing formats, and filling in missing data.

[0731] "Product attribute information" refers to unique information related to a product, such as its characteristics and functions, target industry, company size, and geographical conditions.

[0732] "Matching" is the process of selecting the most suitable corporation based on the product's attribute information and pre-processed customer data, taking into consideration the customer's industry, purchasing history, company size, etc.

[0733] "Scoring" is the process of quantifying the suitability of products for each matched corporation and assigning them a score.

[0734] "Ranking" refers to arranging corporations in descending order of score based on the scoring results.

[0735] A "report" is a document containing ranking results and an explanation of the reasons for the scores, which is provided to users in a format that can be viewed by them.

[0736] "User emotion" refers to the current emotional state of the user using the system, and includes emotions such as joy, anger, sadness, and stress.

[0737] "Emotion recognition" is a technology that analyzes user input data, primarily video input, to detect the user's emotional state.

[0738] A "scoring algorithm" refers to the calculation method and rules for assigning scores to corporations, and quantifies the suitability of products.

[0739] "Priority" refers to the importance or position of a company in the ranking, and is adjusted based on user sentiment.

[0740] "Video input" refers to input data for recognizing a user's emotions, and includes video footage capturing the user's facial expressions and movements.

[0741] A "generative AI model" is an artificial intelligence model for automated report generation and data analysis that provides appropriate output based on input data.

[0742] A "prompt" is an instruction for operating a generative AI model, and specifically describes the instructions for report generation and data analysis.

[0743] This invention is a system that utilizes customer data to identify the most suitable corporations for product introduction. This system encompasses a series of processes from customer data acquisition to preprocessing, corporation matching, scoring, ranking, report generation, and user emotion recognition.

[0744] Hardware and Software

[0745] The system is built using the following hardware and software:

[0746] Hardware: Smartphones, tablets

[0747] Software: Python, pandas, scikit-learn, FPDF, emotion_recognition (provisional package)

[0748] Data acquisition and preprocessing

[0749] The server receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. Based on this, the server retrieves customer data from the database. The retrieved data is then cleaned, duplicate data is removed, the format is standardized, and missing data is filled in.

[0750] Corporate Matching and Scoring

[0751] The server uses cosine similarity calculations to match the optimal company based on the product's attribute information and pre-processed customer data. It then assigns a score to each company according to a scoring algorithm. This score quantifies the product's suitability.

[0752] Ranking and Report Generation

[0753] Based on the scoring results, the companies are ranked in order of highest score and a report is generated. The generated report is output in PDF format and provided in a format that can be viewed by users.

[0754] Emotion Recognition and Report Adjustment

[0755] The server recognizes the user's emotions through video input. Based on this emotional data, it adjusts the report display format and changes the scoring algorithm and ranking priority. If the user is feeling stressed, the report will be adjusted to be more clear and concise.

[0756] Generative AI model usage example

[0757] The server automatically generates report content using a generative AI model. The generative AI model generates an appropriate report based on the input of a prompt sentence. The following is an example of a prompt sentence:

[0758] user_request = {

[0759] "ad_attributes": [0.8, 0.2, 0.3],

[0760] "user_video": "path / to / user_video.mp4"

[0761] }

[0762] Specific examples

[0763] For example, if a user wants to find target corporations for a new advertising campaign, they provide the system with product attribute information and a user's video input. The server retrieves and preprocesses the customer data to match the corporations that best suit the product. Next, after scoring and ranking, a report based on emotion recognition is generated. This report is automatically generated using a generative AI model and presented in a format that users can view.

[0764] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0765] Step 1:

[0766] The user sends a request from their device. The request includes information about the product to be analyzed (e.g., advertising campaign attribute information) and filter conditions for the required customer data. Based on this input data, the server determines which customer data to retrieve.

[0767] Step 2:

[0768] The server accesses the customer database and retrieves customer data that matches the specified product information and filter criteria. This process involves executing a database query to extract the required records. The retrieved customer data is output in raw data format.

[0769] Step 3:

[0770] The server preprocesses the customer data it acquires. Specifically, it cleans the data (removing NULL values, standardizing formats, and filling in missing data) and removes duplicate data. This process improves the quality of the data and makes it suitable for analysis. The preprocessed data is then output.

[0771] Step 4:

[0772] The server matches the optimal company based on the product's attribute information and pre-processed customer data. It calculates the compatibility between each company and product using cosine similarity calculations. It generates a compatibility score based on this input data, which becomes the output.

[0773] Step 5:

[0774] The server assigns a score to each matched company based on the generated compatibility score. This score assignment process is quantified (e.g., in the range of 0 to 100) based on the compatibility of the product. This score data is output.

[0775] Step 6:

[0776] The server ranks the corporations in descending order based on the scoring results. In this ranking process, the score data is sorted in descending order to create a ranking list. This ranking list is output.

[0777] Step 7:

[0778] The server generates a report based on the ranking list. The report includes scores for each company and an explanation of the reasons. The report is generated and output in PDF format.

[0779] Step 8:

[0780] The server performs emotion recognition based on the video input data provided by the user. It analyzes facial expressions from the video data and detects the user's emotional state (e.g., joy, anger, sadness, stress, etc.). This emotional data is output.

[0781] Step 9:

[0782] The server adjusts the report display format, scoring algorithm, and ranking priority based on the emotion data. For example, if the user is feeling stressed, the report will be adjusted to be more clear and concise. The adjusted report is then output.

[0783] Step 10:

[0784] The server automatically generates report content using a generative AI model. Based on the prompt input (e.g., "user_request = { "ad_attributes": [0.8, 0.2, 0.3], "user_video": "path / to / user_video.mp4"}"), the generative AI model creates an appropriate report. The generated report based on this prompt is output.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] [Third embodiment]

[0789] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0790] 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.

[0791] 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).

[0792] 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.

[0793] 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.

[0794] 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).

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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."

[0801] The present invention relates to a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. This system mainly comprises the following components: data acquisition means, data preprocessing means, corporation matching means, ranking means, and report generation means.

[0802] The program for this system is described below.

[0803] Data Acquisition Method

[0804] The server first receives a request from the terminal. The request includes the conditions for acquiring customer data and attribute information for the product. Based on the applicable conditions, the server accesses the database and acquires the necessary customer data.

[0805] Data preprocessing measures

[0806] The server performs preprocessing on the acquired customer data. Specifically, it cleans the data and removes duplicate data. For example, it deletes records containing NULL values ​​and standardizes data with different formats. It also performs complementation processing on incomplete data to optimize it.

[0807] Corporate matching method

[0808] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. Product attributes include information such as industry, company size, and location. The server extracts suitable corporations from the customer data based on this attribute information. It also analyzes past purchase history and evaluates the applicability of the corporation to the product.

[0809] Ranking methods

[0810] The server assigns scores to matched companies and generates a ranking. Scoring is based on the suitability of the product and purchase history. For example, if the product attributes and customer attributes show a high match, a high score is assigned. The list of companies is sorted in descending order based on the score to create a ranking list.

[0811] Report Generation Method

[0812] Finally, the server creates a report based on the generated ranking results. The report includes a list of the companies that are most suitable for the product, their scores, etc. The server sends this report to the terminal so that the user can easily view it. The report is provided in the format requested by the user, such as PDF or HTML.

[0813] Specific examples

[0814] As a specific example, let's say a user wants to sell a new cloud service. The user makes a request from their device to the server to "extract companies suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from a customer database and performs data cleaning. Next, it matches companies that have used similar services in the past based on the attributes of the cloud service. The resulting list of candidate companies is scored and ranked in order of priority. Finally, the ranking list is generated as a report and sent to the user's device. The user can use this report to efficiently conduct their sales activities.

[0815] As described above, the present invention is a system that realizes effective corporate extraction and sales support through a series of processes from data acquisition to processing, matching, ranking, and report generation.

[0816] The processing flow will be explained below.

[0817] Step 1: Receiving a request

[0818] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal then sends this request to the server.

[0819] Step 2: Database Access

[0820] The server accesses the customer database based on the request received from the terminal, and retrieves the required data using SQL queries under specific filter conditions (e.g., specific industry or region).

[0821] Step 3: Data Acquisition

[0822] The server receives customer data returned from a database query, including demographic information such as company name, industry, size, location, and purchase history.

[0823] Step 4: Data Cleaning

[0824] The server cleans the acquired customer data, for example, removing records containing NULL values ​​and converting data with inconsistent formats into a unified format. Missing data is also imputed during this process.

[0825] Step 5: Remove duplicates

[0826] The server detects and removes duplicate records from the cleaned data, identifying duplicates based on company name or ID and merging them into a single record.

[0827] Step 6: Processing product attribute information

[0828] The server analyzes the product's attribute information and extracts its characteristics, including the product's industry, company size, location, etc.

[0829] Step 7: Corporate Matching

[0830] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. It analyzes past purchase history and corporate attributes to extract the corporation that is most suitable for the product.

[0831] Step 8: Scoring

[0832] The server assigns a score to each matched company. This score is calculated based on the product compatibility and purchasing history. For example, a company that shows a high compatibility is assigned a high score.

[0833] Step 9: Ranking Generation

[0834] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[0835] Step 10: Generate reports

[0836] The server generates a report based on the ranking results. This report includes the score for each company and an explanation of the reasons. The generated report is available in PDF format, HTML format, etc.

[0837] Step 11: Submit report

[0838] The server sends the generated report to the terminal, which receives the report and displays it for the user to view.

[0839] Based on the reports sent from the server, users can use their terminals to identify corporations that are suitable for specific products and efficiently conduct sales activities.

[0840] Example 1

[0841] 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."

[0842] In the past, there was no established method for effectively utilizing customer data to identify the most suitable companies. This resulted in inefficient sales activities and made it difficult to approach the right companies. In addition, data preprocessing and company scoring / ranking were done manually, which was time-consuming and labor-intensive, and lacked accuracy.

[0843] 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.

[0844] In this invention, the server includes means for receiving a prompt sentence entered by a user, means for acquiring customer data, means for preprocessing the acquired customer data, means for matching the optimal corporation based on the attribute information of the product and the preprocessed customer data, means for assigning a score to each corporation and creating a ranking, and means for generating a report including the ranking results and outputting it in a format that can be viewed by the user. This enables the system to efficiently and accurately extract corporations and improve the efficiency of sales activities based on the results.

[0845] A "prompt sentence" refers to a sentence that allows a user to input specific instructions or conditions to a system.

[0846] "Customer data" is a dataset that contains information about companies and individuals, including information about industry, company size, purchasing history, and more.

[0847] "Preprocessing" refers to a series of steps taken to prepare raw data for analysis, including cleaning the data and removing duplicate data.

[0848] "Product attribute information" refers to information that indicates the characteristics and conditions of a specific product or service, including the type of industry, company size, and service content.

[0849] "Matching" refers to the process of combining customer data and product attribute information based on specific conditions to select the most suitable corporation.

[0850] "Scoring" refers to the process of assigning a rating to each entity based on specific criteria.

[0851] A "ranking" is a list of scored corporations arranged in order of their evaluation scores, and is ranked based on specific criteria.

[0852] "Report" means any document or digital data containing the system-generated list of optimal corporations, their scores, rankings, etc.

[0853] A "process" is a series of steps or procedures that are carried out to achieve a particular purpose.

[0854] The present invention is a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. This system receives prompts entered by the user, acquires customer data, and provides the user with a list of optimal corporations through preprocessing, matching, ranking, and report generation.

[0855] Hardware and Software Configuration

[0856] server

[0857] The server processes user requests, performs complex data analysis, and generates rankings. Specifically, it is responsible for the following:

[0858] Receiving a prompt

[0859] Customer data retrieval and database access

[0860] Data preprocessing (cleaning, de-duplicating data)

[0861] Applying a matching algorithm

[0862] Scoring and ranking generation

[0863] Creating and sending reports

[0864] Terminal

[0865] The terminal provides an interface for users to input prompts and also has the functionality to receive and display reports. A typical computer, tablet, or smartphone can be used as the terminal.

[0866] Data acquisition and preprocessing

[0867] The server retrieves customer data from the database based on the prompt entered by the user. This data includes information such as industry, company size, purchasing history, etc. The retrieved data undergoes the following preprocessing steps to prepare it for analysis:

[0868] Cleaning: Filling and removing records containing null values ​​and incomplete data.

[0869] Remove duplicate data: If the same information appears in multiple records, remove it.

[0870] Format unification: Standardize date formats and text formats.

[0871] Matching and Scoring

[0872] The server matches the appropriate company based on the pre-processed data and product attribute information, using machine learning algorithms to take into account past purchase history and company characteristics.

[0873] The server then assigns scores to the matched businesses and generates rankings. Scoring criteria include the degree to which the product attributes match the business's needs and its purchasing history.

[0874] Report generation and delivery

[0875] The server creates a report based on the ranking results. The report includes a list of the most suitable companies and their respective scores, and is generated in a format (PDF, HTML, etc.) according to the user's request. Finally, the report is sent to the terminal so that the user can easily view it.

[0876] Specific examples

[0877] As a concrete example, consider a user who wants to sell a new cloud service. The user sends a request to the server from their device saying, "I want to sell a new cloud service, so please extract suitable companies targeting small and medium-sized businesses in the IT industry and generate a report." In response, the server performs the following steps:

[0878] 1. Obtain customer data on the IT industry and small and medium-sized businesses from the database

[0879] 2. Preprocessing the acquired data (cleaning, deleting duplicate data)

[0880] 3. Matching with companies that have used similar services in the past based on cloud service attribute information

[0881] 4. Scores are assigned to candidate companies and a ranking is generated.

[0882] 5. Finally, the ranking list is generated as a report and sent to the user's device.

[0883] This system allows users to efficiently conduct sales activities.

[0884] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0885] Step 1: Receiving the prompt

[0886] The server receives the prompt text entered by the user from the terminal. This prompt text includes attribute information about the product and the conditions for the target corporations. For example, a user might enter something like, "I want to sell a new cloud service, so please extract suitable corporations targeting small and medium-sized enterprises in the IT industry and generate a report." The input is in text format, and the server analyzes it to extract the information needed for the next step.

[0887] Step 2: Obtain customer data

[0888] The server retrieves relevant customer data from the database based on the information extracted from the prompt. For example, it searches for and retrieves customer data that corresponds to the "IT industry" and "small and medium-sized enterprises." In this case, it uses an SQL query to efficiently extract the required data. The input is the condition set by the prompt, and the output is a list of matching customer data.

[0889] Step 3: Data Preprocessing

[0890] The server performs pre-processing on the acquired customer data, specifically including the following operations:

[0891] Data cleaning: Remove records containing null values ​​and impute incomplete data.

[0892] De-duplicate data: Detect and delete duplicates of identical customer data.

[0893] Standardize formats: Standardize date and text formats.

[0894] The input is the acquired customer data, and the output is a pre-processed, clean dataset.

[0895] Step 4: Matching Companies

[0896] The server matches the most suitable company based on the pre-processed customer data and product attribute information. Specifically, it performs the following operations:

[0897] The preprocessed customer data is analyzed to search for corporations that match the product attributes (e.g., cloud services).

[0898] Evaluate the applicability of products taking into account past purchasing history and company characteristics.

[0899] The input is a preprocessed clean dataset and product attribute information, and the output is a list of matching corporations.

[0900] Step 5: Scoring and Ranking

[0901] The server assigns scores to the matched companies and generates a ranking. Specifically, it performs the following operations:

[0902] A score is assigned based on the degree to which the product's attributes match the company's needs.

[0903] Scores are set taking into consideration past purchasing history and interest in the product.

[0904] The list of corporations is sorted in descending order based on the scores to create a ranking list.

[0905] The input is a list of matched entities and the output is a ranked list of entities.

[0906] Step 6: Generate and send the report

[0907] The server creates a report based on the ranking results and sends it to the user's device. Specifically, it performs the following operations:

[0908] The ranking list is formatted in a format such as PDF or HTML according to the user's request.

[0909] The report will include a list of the best companies and their scores.

[0910] The completed report is sent to the user's terminal so that the user can easily view it.

[0911] The input is a ranked list of companies, and the output is a report in a user-viewable format.

[0912] (Application example 1)

[0913] 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."

[0914] Effective target selection is essential in modern advertising campaigns. However, extracting optimal targets from large amounts of customer data and delivering appropriate advertisements to them remains a difficult challenge. Conventional methods often require manual data preprocessing and target scoring, which is labor-intensive and time-consuming, and has the problem of low accuracy. Furthermore, there is a lack of systems that allow end users to easily use this series of processes.

[0915] 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.

[0916] In this invention, the server includes a means for acquiring customer data, a means for preprocessing the acquired customer data, a means for matching optimal corporations based on product attribute information and the acquired customer data, a means for assigning scores to each corporation and creating rankings, a means for generating a report including the ranking results and outputting it in a format viewable by users, and a means for inputting advertising campaign conditions, extracting targets based on target customer data, scoring them, generating a ranking list, and outputting it in report format. This enables quick and accurate target selection for advertising campaigns and supports sales activities. Furthermore, scoring and ranking are automated, allowing users to efficiently reach optimal targets.

[0917] "Customer data" refers to data containing information about a specific customer, including customer attributes and purchasing history.

[0918] "Preprocessing" is the process of preparing acquired data for analysis, and includes cleaning the data and deleting duplicate data.

[0919] "Product attribute information" is information that indicates characteristics related to a specific product, and includes the industry, company size, location, and the like.

[0920] "Matching" is the process of selecting the most suitable target based on specific criteria.

[0921] "Scoring" is the process of assigning an evaluation criterion to an object based on specific criteria, thereby quantifying the object's suitability.

[0922] "Ranking" is the process of ordering objects based on the scoring results, listing them in order from highest to lowest rating.

[0923] A "report" is a document summarizing the results of analysis and evaluation, and is provided to users in PDF or HTML format.

[0924] "Ad campaign conditions" are setting information related to a particular ad campaign, including target attributes, ad content, and the like.

[0925] "Targeted Customer Data" means data about customers selected based on the terms of an advertising campaign.

[0926] "Filtering" is a process of removing unnecessary parts from data based on specific conditions.

[0927] "Click history" is data on when users have clicked on ads in the past, and is used to evaluate the effectiveness of advertising.

[0928] The present invention is a system that utilizes customer data to extract targets suitable for advertising campaigns and support effective advertising activities. This system includes the following main components: data acquisition means, data preprocessing means, target matching means, scoring means, ranking creation means, report generation means, and advertising campaign condition input means.

[0929] System Program

[0930] The server includes the following means:

[0931] 1. Data acquisition method

[0932] The user inputs the conditions of the advertising campaign (target attributes, ad content, etc.) from the terminal. Based on this, the server accesses the database and retrieves customer data. This database includes customer attributes, purchase history, click history, etc.

[0933] 2. Data preprocessing methods

[0934] The server performs data cleaning on the acquired customer data, specifically deleting records containing NULL values, deleting duplicate data, standardizing data formats, and completing incomplete data.

[0935] 3. Target Matching Methods

[0936] The server extracts suitable targets from customer data based on the conditions of the ad campaign, filtering them based on target attributes and past ad click history.

[0937] 4. Scoring Methods

[0938] The server then scores the filtered targets based on the degree of match with the target attributes and past ad click history.

[0939] 5. Ranking Creation Method

[0940] Based on the scoring results, targets are ranked in descending order of score, making it clear which targets have higher priority.

[0941] 6. Report Generation Methods

[0942] The server generates a report based on the ranking results. The report is exported in PDF or HTML format and sent to the device. Users can view this report and use it for advertising activities.

[0943] Hardware and software used

[0944] Hardware: Smartphones, servers

[0945] Software: Python 3.x, Pandas, scikit-learn, FPDF

[0946] Specific examples

[0947] For example, suppose a user wants to run an advertising campaign for "technology" and "small and medium-sized" businesses. The following prompts can be used to drive the system:

[0948] Please create a Python program to obtain target customer data suitable for the "Technology Industry" and "Small and Medium-sized Business" advertising campaign, clean the data, perform target matching, score, rank, and generate a report.

[0949] Using this prompt, the server accesses the database, retrieves target customer data, preprocesses it, filters it, and scores it, and finally generates a ranking list that can be exported as a report, allowing users to efficiently develop their advertising activities.

[0950] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0951] Step 1:

[0952] The user inputs the conditions of the advertising campaign from the terminal.

[0953] Specifically, target attributes (industry, size) and advertising content are entered. This input data is sent to the server. The input data includes the campaign name, target industry, company size, etc. A prompt sentence is generated to acquire the data.

[0954] Step 2:

[0955] The server accesses the database based on the entered advertising campaign conditions to retrieve customer data.

[0956] The customer data acquired includes basic customer attributes (industry, company size, location), past purchase history, click history, etc. A database query is executed to extract data that matches the conditions. The extracted data is stored in temporary memory.

[0957] Step 3:

[0958] The server performs data preprocessing on the acquired customer data.

[0959] Specifically, the data is cleaned, records containing NULL values ​​and duplicate data are deleted, the format of customer attributes is standardized, and incomplete data is supplemented. After preprocessing, the data is formatted and ready for high-precision analysis.

[0960] Step 4:

[0961] The server performs target matching based on the pre-processed customer data.

[0962] Filter customer data that matches campaign criteria to identify suitable customers for advertising, using a condition-based SQL filtering query.

[0963] Step 5:

[0964] The server scores the matched targets.

[0965] Scores are assigned based on the degree of match with the target's attributes and past ad click history. Scoring is performed using a standardized scaling algorithm (e.g., MinMaxScaler). Evaluation indicators include the degree of match with industry, suitability with company size, and relevance of past click history.

[0966] Step 6:

[0967] The server ranks the targets based on the scoring results.

[0968] The targets are sorted in descending order of score to generate a ranking list, which is used to determine the priority of sales activities. The generated list is stored in temporary memory.

[0969] Step 7:

[0970] The server generates a report based on the ranking results.

[0971] The report includes the target name, score, ranking, etc. The report can be generated in PDF or HTML format and sent to the device, and the report is provided in a format that users can easily view and download.

[0972] Through the above processing steps, target selection in an advertising campaign is automated, and a system that supports effective advertising activities is realized.

[0973] 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.

[0974] This invention relates to a system that utilizes customer data to extract effective corporations for the introduction of products currently handled by the team. This system includes processes for acquiring, preprocessing, matching, scoring, and generating reports on customer data, and further improves the user experience by combining it with an emotion engine that recognizes user emotions.

[0975] System Components

[0976] The system mainly has the following components:

[0977] Data Acquisition Method

[0978] Data preprocessing measures

[0979] Corporate matching method

[0980] Scoring Instrument

[0981] Ranking methods

[0982] Report Generation Method

[0983] Emotion Engine

[0984] Data Acquisition Method

[0985] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal sends this request to the server, which then accesses the customer database to retrieve the required data.

[0986] Data preprocessing measures

[0987] The server then cleans the acquired customer data and removes duplicates, removing records containing NULL values, converting data with inconsistent formats into a unified format, and filling in missing data.

[0988] Corporate matching method

[0989] The server matches the optimal corporation based on the product's attribute information (industry, company size, location, etc.) and pre-processed customer data. Past purchase history is also analyzed to extract the corporation that is most suitable for the product.

[0990] Scoring Instrument

[0991] The server assigns a score to each matched company. This score is calculated based on the suitability of the product and the purchase history. For example, a company that shows a high suitability is assigned a high score.

[0992] Ranking methods

[0993] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[0994] Report Generation Method

[0995] The server generates a report based on the ranking results, which includes the score for each company and an explanation of the reasons, and is provided in PDF, HTML, and other formats.

[0996] Emotion Engine

[0997] The emotion engine has the ability to recognize emotions from user reactions and input data. The emotion engine is used to perform the following processes:

[0998] Adjusting report display based on user sentiment

[0999] Adjusting the scoring algorithm based on user sentiment

[1000] Adjusting ranking priorities based on user sentiment

[1001] Specific examples

[1002] As a specific example, consider a situation where a user who wants to sell a new cloud service requests the server from their device to "extract corporations suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from its customer database and performs data cleaning. Next, it matches the cloud service attributes with companies that have used similar services in the past. The resulting list of candidate corporations is scored and ranked in order of priority. The server then generates a report based on this and sends it to the device. The user can use this report to efficiently conduct sales activities.

[1003] Furthermore, by utilizing an emotion engine to recognize the user's emotions, the report display format is adjusted according to the user's state. For example, if the user is feeling stressed, the report will be displayed in an easy-to-understand and concise format. Furthermore, the scoring algorithm and ranking priority are also adjusted based on the user's emotions, enabling more appropriate proposals to be made to the user. In this way, the user experience is improved, resulting in more effective corporate identification and more efficient sales activities.

[1004] The processing flow will be explained below.

[1005] Step 1: Receiving a request

[1006] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal then sends this request to the server.

[1007] Step 2: Database Access

[1008] The server accesses the customer database based on the request received from the terminal, and retrieves the required data based on specific filter conditions (e.g., specific industry or region) using an SQL query.

[1009] Step 3: Data Acquisition

[1010] The server receives customer data returned from a database query, including demographic information such as company name, industry, size, location, and purchase history.

[1011] Step 4: Data Cleaning

[1012] The server cleans the customer data it retrieves. For example, it deletes records containing NULL values ​​and converts data with inconsistent formats into a unified format. It also performs complementation processing on incomplete data to optimize it.

[1013] Step 5: Remove duplicates

[1014] The server detects and removes duplicate records from the cleaned data, identifying duplicates based on company name or ID and merging them into a single record.

[1015] Step 6: Processing product attribute information

[1016] The server analyzes the product's attribute information and extracts its characteristics, including the type of business, company size, and location.

[1017] Step 7: Corporate Matching

[1018] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. It also analyzes past purchase history and other data to identify the corporation that is most suitable for the product.

[1019] Step 8: Scoring

[1020] The server assigns a score to each matched company. This score is calculated based on the product compatibility and purchasing history. For example, a company that shows a high compatibility is assigned a high score.

[1021] Step 9: Ranking Generation

[1022] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[1023] Step 10: Generate reports

[1024] The server generates a report based on the ranking results. This report includes the score for each company and an explanation of the reasons. The generated report is available in PDF, HTML, and other formats.

[1025] Step 11: Emotion Recognition

[1026] The server uses an emotion engine to recognize the user's emotions. It evaluates the user's emotional state based on their reactions and input data, and identifies their current emotion.

[1027] Step 12: Adjusting the report display

[1028] Based on the results of emotion recognition, the server adjusts the report display format. For example, if the user is feeling stressed, the report will be displayed in a simple and easy-to-understand manner.

[1029] Step 13: Adjust the scoring algorithm

[1030] Based on the emotion recognition results, the server adjusts the scoring algorithm, for example, presenting a more detailed analysis if the user is excited.

[1031] Step 14: Adjusting Ranking Priority

[1032] Based on the results of emotion recognition, the server adjusts the ranking priority. For example, if the user is calm, the ranking is displayed with normal priority.

[1033] Step 15: Report Submission

[1034] The server generates and adjusts the report and sends it to the terminal, which receives it and displays it to the user.

[1035] These are the processing steps of this system. Based on the reports provided, users can efficiently identify companies that are suitable for their products and conduct sales activities. Adjustments made by the emotion engine also aim to improve the user experience.

[1036] Example 2

[1037] 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."

[1038] Conventional systems that utilize customer data often perform data acquisition, preprocessing, and even corporate matching and scoring individually, without adjusting to the user's experience or emotions. This results in problems such as the information users receive being suboptimal, and insufficient efficiency in sales activities. Furthermore, the lack of a mechanism for adjusting the report content and display format based on the user's current emotions and state makes it difficult to provide information that is easy for users to understand. Given this background, there is a need for the development of a system that utilizes customer data and dynamically provides information based on the user's emotions.

[1039] 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.

[1040] In this invention, the server includes means for acquiring customer data, means for preprocessing the acquired customer data, means for matching the most suitable corporation based on the attribute information of the product and the acquired customer data, means for assigning a score to each corporation and creating a ranking, and means for recognizing the user's emotions and adjusting the report display format and scoring algorithm based on the emotions. This allows the user to receive the information they need in the most suitable format and conduct sales activities more efficiently.

[1041] "Customer data" refers to a dataset that includes all information about customers, and is used to develop sales strategies for products and to respond to customers.

[1042] "Preprocessing" refers to a series of processes such as data cleaning, deleting duplicate data, and standardizing data formats that are carried out to improve the quality of acquired data.

[1043] "Product attribute information" refers to information about the features and characteristics associated with a specific product, such as the industry, company size, and location.

[1044] "Corporate matching" refers to the process of identifying the most suitable business partners and client companies based on product attribute information and pre-processed customer data.

[1045] "Scoring" refers to the process of assigning an evaluation score to matched businesses based on suitability, purchasing history, etc.

[1046] "Ranking" refers to ranking corporations based on the scoring results and creating a list according to importance and suitability.

[1047] A "report" is a document generated based on the ranking results, which includes scores for each corporation and explanations of the reasons, and is provided in PDF or HTML format.

[1048] An "emotion engine" is an engine that has the ability to recognize emotions from user reactions and input data and adjust the system's behavior based on that.

[1049] The present invention relates to a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. The system includes a data acquisition means, a data preprocessing means, a corporation matching means, a scoring means, a ranking means, a report generation means, and an emotion engine.

[1050] System program generation

[1051] The program of this system is realized by the cooperation of the server, terminals, and user operations. The server mainly processes and analyzes data, and the terminals provide an interface with the user. The program includes the following main software libraries:

[1052] MySQL (database management)

[1053] pandas (data preprocessing)

[1054] scikit-learn (machine learning model)

[1055] Fpdf (PDF report generator)

[1056] Transformers (emotion recognition)

[1057] Process Overview

[1058] The user uses a terminal to send a request to extract corporations suitable for introducing a product. This request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal sends this request to the server, which then accesses the MySQL database to retrieve the required customer data.

[1059] The server uses the pandas library to clean the acquired customer data. Specifically, it deletes records containing NULL values, converts data with inconsistent formats into a unified format, and fills in missing data. The server then uses a scikit-learn machine learning model to match the optimal company based on the product attribute information and preprocessed customer data. It analyzes past purchase history and other factors to extract companies that are suitable for the product.

[1060] For each matched company, the server assigns a score using a random forest regression model. This score is calculated based on the product's suitability and past purchase history. Based on the scoring results, the server generates a ranking of companies in descending order of score.

[1061] Based on the generated ranking results, the server uses the Fpdf library to generate a report, which includes scores for each company and explanations of the results, and is provided to the terminal in PDF or HTML format.

[1062] Additionally, the server recognizes the user's emotions through an emotion engine and adjusts the report presentation and scoring algorithms accordingly. Emotion recognition is performed using the Transformers library, and if the user is feeling stressed, the report will be presented in a clearer and more concise format.

[1063] Specific examples

[1064] Consider the case where a user who wants to sell a new cloud service requests the server from a device to "extract corporations suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from a customer database and performs data cleaning. Next, it matches companies that have used similar services in the past based on the attributes of the cloud service. The resulting list of candidate corporations is scored and ranked in order of priority. The server generates a report based on this and sends it to the device. The user can use this report to efficiently conduct sales activities. Furthermore, an emotion engine is used to recognize the user's emotions, and the display format of the report is adjusted according to the user's state.

[1065] Prompt Sentence Examples

[1066] We would like to use customer data to identify companies suitable for the cloud services we currently offer. First, we would like you to acquire and cleanse the data based on the following criteria: industry is IT, company size is small and medium-sized enterprises. Next, we would like you to match the most suitable companies based on the attributes of the cloud services, score and rank them, and generate a report. We would also like you to adjust the report display format and scoring algorithm based on user sentiment.

[1067] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1068] Program processing flow

[1069] Step 1: User submits request

[1070] Input: User inputs product information and customer data filter criteria

[1071] Process: The user uses the terminal to enter the "Request to extract legal entities suitable for cloud services" in the interface and clicks the submit button.

[1072] Output: The device forwards this request data to the server.

[1073] Step 2: Data Acquisition

[1074] Input: Request data sent from the terminal

[1075] Process: The server connects to the customer database and executes a SQL query such as "SELECT FROM customer table WHERE industry='IT' AND company size='Small / Medium Business'" to extract the relevant data.

[1076] Output: Obtain the required customer data and pass it on to the next processing step

[1077] Step 3: Data Preprocessing

[1078] Input: Customer data retrieved by the server

[1079] Processing: The server uses the pandas library to create a data frame, remove records containing NULL values, convert data with different formats to a unified format, and impute missing data.

[1080] Specific behavior: Execute code such as "df.dropna(inplace=True)" or "df.fillna("Unknown", inplace=True)".

[1081] Output: Preprocessed, clean data passed to the next processing step

[1082] Step 4: Corporate Matching

[1083] Input: Preprocessed clean customer data and product attribute information

[1084] Processing: The server uses scikit-learn's KNN (k-nearest neighbor) algorithm to identify corporations with high similarity based on past product usage history.

[1085] Specific operations: Perform operations such as "model.fit(data)" and "model.predict(new data)".

[1086] Output: Pass the list of matched entities to the next processing step

[1087] Step 5: Scoring

[1088] Input: Matched legal entity list

[1089] Processing: The server calculates the fitness of each legal entity using a random forest regression model and assigns a high score to legal entities that show a high fitness.

[1090] Specific operation: Execute code such as "model.fit(X_train, y_train)" or "model.predict(X_test)".

[1091] Output: Pass the scored list of legal entities to the next processing step

[1092] Step 6: Ranking

[1093] Input: List of scored legal entities

[1094] Processing: The server sorts the list of corporations using pandas' "df.sort_values(by='score', ascending=False)" and arranges them in order of highest score.

[1095] Output: Pass the ranked list of companies to the next processing step

[1096] Step 7: Generate reports

[1097] Input: Ranked corporate list

[1098] Processing: The server uses the Fpdf library to generate a report that includes the scores for each company and an explanation of the reasons.

[1099] Specific operation: Execute code such as "pdf.cell(200, 10, txt="Corporate List", ln=True)" and "pdf.output("report.pdf")".

[1100] Output: Generate reports in PDF and HTML format and send them to your device.

[1101] Step 8: Emotional Engine Alignment

[1102] Input: User reactions and input data

[1103] Processing: The server uses the Transformers library to analyze the user's emotions. It executes code like "emotion_analyzer = pipeline('sentiment-analysis')" and "result = emotion_analyzer("text")" to adjust the report display format and scoring algorithm based on the emotions.

[1104] Output: Providing tailored reports and algorithms to users

[1105] (Application example 2)

[1106] 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."

[1107] Conventional corporate matching systems have basic functions such as data cleaning, matching, scoring, and report generation to effectively identify product applications, but they are unable to adjust the report display content or matching algorithms to take user emotions into account. This prevents the system from providing optimal information based on the user's emotional state, limiting the improvement of user experience and efficient sales activities. Furthermore, the system lacks a function to automatically generate report content from input prompts using a generative AI model, resulting in low report creation efficiency.

[1108] 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.

[1109] In this invention, the server includes means for acquiring customer data, means for preprocessing the acquired customer data, means for matching optimal corporations based on product attribute information and the acquired customer data, means for assigning scores to each corporation and creating rankings, means for generating a report including the ranking results and outputting it in a format viewable by the user, means for recognizing user emotions and adjusting the report display, means for adjusting the scoring algorithm and ranking priority based on the user emotions, means for detecting user emotions through video input, and means for automatically generating report content from input prompt sentences using a generative AI model. This enables the provision of more optimal information according to the user's emotional state, improving the user experience and enabling more efficient sales activities.

[1110] "Customer data" refers to information about the corporation to which the product is applied, and includes data such as the customer's name, industry, purchase history, and location.

[1111] "Preprocessing" refers to a series of processes to improve the quality of data, such as cleaning the acquired data, deleting duplicate data, standardizing formats, and filling in missing data.

[1112] "Product attribute information" refers to unique information related to a product, such as its characteristics and functions, target industry, company size, and geographical conditions.

[1113] "Matching" is the process of selecting the most suitable corporation based on the product's attribute information and pre-processed customer data, taking into consideration the customer's industry, purchasing history, company size, etc.

[1114] "Scoring" is the process of quantifying the suitability of products for each matched corporation and assigning them a score.

[1115] "Ranking" refers to arranging corporations in descending order of score based on the scoring results.

[1116] A "report" is a document containing ranking results and an explanation of the reasons for the scores, which is provided to users in a format that can be viewed by them.

[1117] "User emotion" refers to the current emotional state of the user using the system, and includes emotions such as joy, anger, sadness, and stress.

[1118] "Emotion recognition" is a technology that analyzes user input data, primarily video input, to detect the user's emotional state.

[1119] A "scoring algorithm" refers to the calculation method and rules for assigning scores to corporations, and quantifies the suitability of products.

[1120] "Priority" refers to the importance or position of a company in the ranking, and is adjusted based on user sentiment.

[1121] "Video input" refers to input data for recognizing a user's emotions, and includes video footage capturing the user's facial expressions and movements.

[1122] A "generative AI model" is an artificial intelligence model for automated report generation and data analysis that provides appropriate output based on input data.

[1123] A "prompt" is an instruction for operating a generative AI model, and specifically describes the instructions for report generation and data analysis.

[1124] This invention is a system that utilizes customer data to identify the most suitable corporations for product introduction. This system encompasses a series of processes from customer data acquisition to preprocessing, corporation matching, scoring, ranking, report generation, and user emotion recognition.

[1125] Hardware and Software

[1126] The system is built using the following hardware and software:

[1127] Hardware: Smartphones, tablets

[1128] Software: Python, pandas, scikit-learn, FPDF, emotion_recognition (provisional package)

[1129] Data acquisition and preprocessing

[1130] The server receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. Based on this, the server retrieves customer data from the database. The retrieved data is then cleaned, duplicate data is removed, the format is standardized, and missing data is filled in.

[1131] Corporate Matching and Scoring

[1132] The server uses cosine similarity calculations to match the optimal company based on the product's attribute information and pre-processed customer data. It then assigns a score to each company according to a scoring algorithm. This score quantifies the product's suitability.

[1133] Ranking and Report Generation

[1134] Based on the scoring results, the companies are ranked in order of highest score and a report is generated. The generated report is output in PDF format and provided in a format that can be viewed by users.

[1135] Emotion Recognition and Report Adjustment

[1136] The server recognizes the user's emotions through video input. Based on this emotional data, it adjusts the report display format and changes the scoring algorithm and ranking priority. If the user is feeling stressed, the report will be adjusted to be more clear and concise.

[1137] Generative AI model usage example

[1138] The server automatically generates report content using a generative AI model. The generative AI model generates an appropriate report based on the input of a prompt sentence. The following is an example of a prompt sentence:

[1139] user_request = {

[1140] "ad_attributes": [0.8, 0.2, 0.3],

[1141] "user_video": "path / to / user_video.mp4"

[1142] }

[1143] Specific examples

[1144] For example, if a user wants to find target corporations for a new advertising campaign, they provide the system with product attribute information and a user's video input. The server retrieves and preprocesses the customer data to match the corporations that best suit the product. Next, after scoring and ranking, a report based on emotion recognition is generated. This report is automatically generated using a generative AI model and presented in a format that users can view.

[1145] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1146] Step 1:

[1147] The user sends a request from their device. The request includes information about the product to be analyzed (e.g., advertising campaign attribute information) and filter conditions for the required customer data. Based on this input data, the server determines which customer data to retrieve.

[1148] Step 2:

[1149] The server accesses the customer database and retrieves customer data that matches the specified product information and filter criteria. This process involves executing a database query to extract the required records. The retrieved customer data is output in raw data format.

[1150] Step 3:

[1151] The server preprocesses the customer data it acquires. Specifically, it cleans the data (removing NULL values, standardizing formats, and filling in missing data) and removes duplicate data. This process improves the quality of the data and makes it suitable for analysis. The preprocessed data is then output.

[1152] Step 4:

[1153] The server matches the optimal company based on the product's attribute information and pre-processed customer data. It calculates the compatibility between each company and product using cosine similarity calculations. It generates a compatibility score based on this input data, which becomes the output.

[1154] Step 5:

[1155] The server assigns a score to each matched company based on the generated compatibility score. This score assignment process is quantified (e.g., in the range of 0 to 100) based on the compatibility of the product. This score data is output.

[1156] Step 6:

[1157] The server ranks the corporations in descending order based on the scoring results. In this ranking process, the score data is sorted in descending order to create a ranking list. This ranking list is output.

[1158] Step 7:

[1159] The server generates a report based on the ranking list. The report includes scores for each company and an explanation of the reasons. The report is generated and output in PDF format.

[1160] Step 8:

[1161] The server performs emotion recognition based on the video input data provided by the user. It analyzes facial expressions from the video data and detects the user's emotional state (e.g., joy, anger, sadness, stress, etc.). This emotional data is output.

[1162] Step 9:

[1163] The server adjusts the report display format, scoring algorithm, and ranking priority based on the emotion data. For example, if the user is feeling stressed, the report will be adjusted to be more clear and concise. The adjusted report is then output.

[1164] Step 10:

[1165] The server automatically generates report content using a generative AI model. Based on the prompt input (e.g., "user_request = { "ad_attributes": [0.8, 0.2, 0.3], "user_video": "path / to / user_video.mp4"}"), the generative AI model creates an appropriate report. The generated report based on this prompt is output.

[1166] 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.

[1167] 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.

[1168] 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.

[1169] [Fourth embodiment]

[1170] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1171] 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.

[1172] 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).

[1173] 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.

[1174] 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.

[1175] 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).

[1176] 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.

[1177] 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.

[1178] 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.

[1179] 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.

[1180] 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.

[1181] 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.

[1182] 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."

[1183] The present invention relates to a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. This system mainly comprises the following components: data acquisition means, data preprocessing means, corporation matching means, ranking means, and report generation means.

[1184] The program for this system is described below.

[1185] Data Acquisition Method

[1186] The server first receives a request from the terminal. The request includes the conditions for acquiring customer data and attribute information for the product. Based on the applicable conditions, the server accesses the database and acquires the necessary customer data.

[1187] Data preprocessing measures

[1188] The server performs preprocessing on the acquired customer data. Specifically, it cleans the data and removes duplicate data. For example, it deletes records containing NULL values ​​and standardizes data with different formats. It also performs complementation processing on incomplete data to optimize it.

[1189] Corporate matching method

[1190] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. Product attributes include information such as industry, company size, and location. The server extracts suitable corporations from the customer data based on this attribute information. It also analyzes past purchase history and evaluates the applicability of the corporation to the product.

[1191] Ranking methods

[1192] The server assigns scores to matched companies and generates a ranking. Scoring is based on the suitability of the product and purchase history. For example, if the product attributes and customer attributes show a high match, a high score is assigned. The list of companies is sorted in descending order based on the score to create a ranking list.

[1193] Report Generation Method

[1194] Finally, the server creates a report based on the generated ranking results. The report includes a list of the companies that are most suitable for the product, their scores, etc. The server sends this report to the terminal so that the user can easily view it. The report is provided in the format requested by the user, such as PDF or HTML.

[1195] Specific examples

[1196] As a specific example, let's say a user wants to sell a new cloud service. The user makes a request from their device to the server to "extract companies suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from a customer database and performs data cleaning. Next, it matches companies that have used similar services in the past based on the attributes of the cloud service. The resulting list of candidate companies is scored and ranked in order of priority. Finally, the ranking list is generated as a report and sent to the user's device. The user can use this report to efficiently conduct their sales activities.

[1197] As described above, the present invention is a system that realizes effective corporate extraction and sales support through a series of processes from data acquisition to processing, matching, ranking, and report generation.

[1198] The processing flow will be explained below.

[1199] Step 1: Receiving a request

[1200] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal then sends this request to the server.

[1201] Step 2: Database Access

[1202] The server accesses the customer database based on the request received from the terminal, and retrieves the required data using SQL queries under specific filter conditions (e.g., specific industry or region).

[1203] Step 3: Data Acquisition

[1204] The server receives customer data returned from a database query, including demographic information such as company name, industry, size, location, and purchase history.

[1205] Step 4: Data Cleaning

[1206] The server cleans the acquired customer data, for example, removing records containing NULL values ​​and converting data with inconsistent formats into a unified format. Missing data is also imputed during this process.

[1207] Step 5: Remove duplicates

[1208] The server detects and removes duplicate records from the cleaned data, identifying duplicates based on company name or ID and merging them into a single record.

[1209] Step 6: Processing product attribute information

[1210] The server analyzes the product's attribute information and extracts its characteristics, including the product's industry, company size, location, etc.

[1211] Step 7: Corporate Matching

[1212] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. It analyzes past purchase history and corporate attributes to extract the corporation that is most suitable for the product.

[1213] Step 8: Scoring

[1214] The server assigns a score to each matched company. This score is calculated based on the product compatibility and purchasing history. For example, a company that shows a high compatibility is assigned a high score.

[1215] Step 9: Ranking Generation

[1216] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[1217] Step 10: Generate reports

[1218] The server generates a report based on the ranking results. This report includes the score for each company and an explanation of the reasons. The generated report is available in PDF format, HTML format, etc.

[1219] Step 11: Submit report

[1220] The server sends the generated report to the terminal, which receives the report and displays it for the user to view.

[1221] Based on the reports sent from the server, users can use their terminals to identify corporations that are suitable for specific products and efficiently conduct sales activities.

[1222] Example 1

[1223] 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."

[1224] In the past, there was no established method for effectively utilizing customer data to identify the most suitable companies. This resulted in inefficient sales activities and made it difficult to approach the right companies. In addition, data preprocessing and company scoring / ranking were done manually, which was time-consuming and labor-intensive, and lacked accuracy.

[1225] 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.

[1226] In this invention, the server includes means for receiving a prompt sentence entered by a user, means for acquiring customer data, means for preprocessing the acquired customer data, means for matching the optimal corporation based on the attribute information of the product and the preprocessed customer data, means for assigning a score to each corporation and creating a ranking, and means for generating a report including the ranking results and outputting it in a format that can be viewed by the user. This enables the system to efficiently and accurately extract corporations and improve the efficiency of sales activities based on the results.

[1227] A "prompt sentence" refers to a sentence that allows a user to input specific instructions or conditions to a system.

[1228] "Customer data" is a dataset that contains information about companies and individuals, including information about industry, company size, purchasing history, and more.

[1229] "Preprocessing" refers to a series of steps taken to prepare raw data for analysis, including cleaning the data and removing duplicate data.

[1230] "Product attribute information" refers to information that indicates the characteristics and conditions of a specific product or service, including the type of industry, company size, and service content.

[1231] "Matching" refers to the process of combining customer data and product attribute information based on specific conditions to select the most suitable corporation.

[1232] "Scoring" refers to the process of assigning a rating to each entity based on specific criteria.

[1233] A "ranking" is a list of scored corporations arranged in order of their evaluation scores, and is ranked based on specific criteria.

[1234] "Report" means any document or digital data containing the system-generated list of optimal corporations, their scores, rankings, etc.

[1235] A "process" is a series of steps or procedures that are carried out to achieve a particular purpose.

[1236] The present invention is a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. This system receives prompts entered by the user, acquires customer data, and provides the user with a list of optimal corporations through preprocessing, matching, ranking, and report generation.

[1237] Hardware and Software Configuration

[1238] server

[1239] The server processes user requests, performs complex data analysis, and generates rankings. Specifically, it is responsible for the following:

[1240] Receiving a prompt

[1241] Customer data retrieval and database access

[1242] Data preprocessing (cleaning, de-duplicating data)

[1243] Applying a matching algorithm

[1244] Scoring and ranking generation

[1245] Creating and sending reports

[1246] Terminal

[1247] The terminal provides an interface for users to input prompts and also has the functionality to receive and display reports. A typical computer, tablet, or smartphone can be used as the terminal.

[1248] Data acquisition and preprocessing

[1249] The server retrieves customer data from the database based on the prompt entered by the user. This data includes information such as industry, company size, purchasing history, etc. The retrieved data undergoes the following preprocessing steps to prepare it for analysis:

[1250] Cleaning: Filling and removing records containing null values ​​and incomplete data.

[1251] Remove duplicate data: If the same information appears in multiple records, remove it.

[1252] Format unification: Standardize date formats and text formats.

[1253] Matching and Scoring

[1254] The server matches the appropriate company based on the pre-processed data and product attribute information, using machine learning algorithms to take into account past purchase history and company characteristics.

[1255] The server then assigns scores to the matched businesses and generates rankings. Scoring criteria include the degree to which the product attributes match the business's needs and its purchasing history.

[1256] Report generation and delivery

[1257] The server creates a report based on the ranking results. The report includes a list of the most suitable companies and their respective scores, and is generated in a format (PDF, HTML, etc.) according to the user's request. Finally, the report is sent to the terminal so that the user can easily view it.

[1258] Specific examples

[1259] As a concrete example, consider a user who wants to sell a new cloud service. The user sends a request to the server from their device saying, "I want to sell a new cloud service, so please extract suitable companies targeting small and medium-sized businesses in the IT industry and generate a report." In response, the server performs the following steps:

[1260] 1. Obtain customer data on the IT industry and small and medium-sized businesses from the database

[1261] 2. Preprocessing the acquired data (cleaning, deleting duplicate data)

[1262] 3. Matching with companies that have used similar services in the past based on cloud service attribute information

[1263] 4. Scores are assigned to candidate companies and a ranking is generated.

[1264] 5. Finally, the ranking list is generated as a report and sent to the user's device.

[1265] This system allows users to efficiently conduct sales activities.

[1266] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1267] Step 1: Receiving the prompt

[1268] The server receives the prompt text entered by the user from the terminal. This prompt text includes attribute information about the product and the conditions for the target corporations. For example, a user might enter something like, "I want to sell a new cloud service, so please extract suitable corporations targeting small and medium-sized enterprises in the IT industry and generate a report." The input is in text format, and the server analyzes it to extract the information needed for the next step.

[1269] Step 2: Obtain customer data

[1270] The server retrieves relevant customer data from the database based on the information extracted from the prompt. For example, it searches for and retrieves customer data that corresponds to the "IT industry" and "small and medium-sized enterprises." In this case, it uses an SQL query to efficiently extract the required data. The input is the condition set by the prompt, and the output is a list of matching customer data.

[1271] Step 3: Data Preprocessing

[1272] The server performs pre-processing on the acquired customer data, specifically including the following operations:

[1273] Data cleaning: Remove records containing null values ​​and impute incomplete data.

[1274] De-duplicate data: Detect and delete duplicates of identical customer data.

[1275] Standardize formats: Standardize date and text formats.

[1276] The input is the acquired customer data, and the output is a pre-processed, clean dataset.

[1277] Step 4: Matching Companies

[1278] The server matches the most suitable company based on the pre-processed customer data and product attribute information. Specifically, it performs the following operations:

[1279] The preprocessed customer data is analyzed to search for corporations that match the product attributes (e.g., cloud services).

[1280] Evaluate the applicability of products taking into account past purchasing history and company characteristics.

[1281] The input is a preprocessed clean dataset and product attribute information, and the output is a list of matching corporations.

[1282] Step 5: Scoring and Ranking

[1283] The server assigns scores to the matched companies and generates a ranking. Specifically, it performs the following operations:

[1284] A score is assigned based on the degree to which the product's attributes match the company's needs.

[1285] Scores are set taking into consideration past purchasing history and interest in the product.

[1286] The list of corporations is sorted in descending order based on the scores to create a ranking list.

[1287] The input is a list of matched entities and the output is a ranked list of entities.

[1288] Step 6: Generate and send the report

[1289] The server creates a report based on the ranking results and sends it to the user's device. Specifically, it performs the following operations:

[1290] The ranking list is formatted in a format such as PDF or HTML according to the user's request.

[1291] The report will include a list of the best companies and their scores.

[1292] The completed report is sent to the user's terminal so that the user can easily view it.

[1293] The input is a ranked list of companies, and the output is a report in a user-viewable format.

[1294] (Application example 1)

[1295] 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."

[1296] Effective target selection is essential in modern advertising campaigns. However, extracting optimal targets from large amounts of customer data and delivering appropriate advertisements to them remains a difficult challenge. Conventional methods often require manual data preprocessing and target scoring, which is labor-intensive and time-consuming, and has the problem of low accuracy. Furthermore, there is a lack of systems that allow end users to easily use this series of processes.

[1297] 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.

[1298] In this invention, the server includes a means for acquiring customer data, a means for preprocessing the acquired customer data, a means for matching optimal corporations based on product attribute information and the acquired customer data, a means for assigning scores to each corporation and creating rankings, a means for generating a report including the ranking results and outputting it in a format viewable by users, and a means for inputting advertising campaign conditions, extracting targets based on target customer data, scoring them, generating a ranking list, and outputting it in report format. This enables quick and accurate target selection for advertising campaigns and supports sales activities. Furthermore, scoring and ranking are automated, allowing users to efficiently reach optimal targets.

[1299] "Customer data" refers to data containing information about a specific customer, including customer attributes and purchasing history.

[1300] "Preprocessing" is the process of preparing acquired data for analysis, and includes cleaning the data and deleting duplicate data.

[1301] "Product attribute information" is information that indicates characteristics related to a specific product, and includes the industry, company size, location, and the like.

[1302] "Matching" is the process of selecting the most suitable target based on specific criteria.

[1303] "Scoring" is the process of assigning an evaluation criterion to an object based on specific criteria, thereby quantifying the object's suitability.

[1304] "Ranking" is the process of ordering objects based on the scoring results, listing them in order from highest to lowest rating.

[1305] A "report" is a document summarizing the results of analysis and evaluation, and is provided to users in PDF or HTML format.

[1306] "Ad campaign conditions" are setting information related to a particular ad campaign, including target attributes, ad content, and the like.

[1307] "Targeted Customer Data" means data about customers selected based on the terms of an advertising campaign.

[1308] "Filtering" is a process of removing unnecessary parts from data based on specific conditions.

[1309] "Click history" is data on when users have clicked on ads in the past, and is used to evaluate the effectiveness of advertising.

[1310] The present invention is a system that utilizes customer data to extract targets suitable for advertising campaigns and support effective advertising activities. This system includes the following main components: data acquisition means, data preprocessing means, target matching means, scoring means, ranking creation means, report generation means, and advertising campaign condition input means.

[1311] System Program

[1312] The server includes the following means:

[1313] 1. Data acquisition method

[1314] The user inputs the conditions of the advertising campaign (target attributes, ad content, etc.) from the terminal. Based on this, the server accesses the database and retrieves customer data. This database includes customer attributes, purchase history, click history, etc.

[1315] 2. Data preprocessing methods

[1316] The server performs data cleaning on the acquired customer data, specifically deleting records containing NULL values, deleting duplicate data, standardizing data formats, and completing incomplete data.

[1317] 3. Target Matching Methods

[1318] The server extracts suitable targets from customer data based on the conditions of the ad campaign, filtering them based on target attributes and past ad click history.

[1319] 4. Scoring Methods

[1320] The server then scores the filtered targets based on the degree of match with the target attributes and past ad click history.

[1321] 5. Ranking Creation Method

[1322] Based on the scoring results, targets are ranked in descending order of score, making it clear which targets have higher priority.

[1323] 6. Report Generation Methods

[1324] The server generates a report based on the ranking results. The report is exported in PDF or HTML format and sent to the device. Users can view this report and use it for advertising activities.

[1325] Hardware and software used

[1326] Hardware: Smartphones, servers

[1327] Software: Python 3.x, Pandas, scikit-learn, FPDF

[1328] Specific examples

[1329] For example, suppose a user wants to run an advertising campaign for "technology" and "small and medium-sized" businesses. The following prompts can be used to drive the system:

[1330] Please create a Python program to obtain target customer data suitable for the "Technology Industry" and "Small and Medium-sized Business" advertising campaign, clean the data, perform target matching, score, rank, and generate a report.

[1331] Using this prompt, the server accesses the database, retrieves target customer data, preprocesses it, filters it, and scores it, and finally generates a ranking list that can be exported as a report, allowing users to efficiently develop their advertising activities.

[1332] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1333] Step 1:

[1334] The user inputs the conditions of the advertising campaign from the terminal.

[1335] Specifically, target attributes (industry, size) and advertising content are entered. This input data is sent to the server. The input data includes the campaign name, target industry, company size, etc. A prompt sentence is generated to acquire the data.

[1336] Step 2:

[1337] The server accesses the database based on the entered advertising campaign conditions to retrieve customer data.

[1338] The customer data acquired includes basic customer attributes (industry, company size, location), past purchase history, click history, etc. A database query is executed to extract data that matches the conditions. The extracted data is stored in temporary memory.

[1339] Step 3:

[1340] The server performs data preprocessing on the acquired customer data.

[1341] Specifically, the data is cleaned, records containing NULL values ​​and duplicate data are deleted, the format of customer attributes is standardized, and incomplete data is supplemented. After preprocessing, the data is formatted and ready for high-precision analysis.

[1342] Step 4:

[1343] The server performs target matching based on the pre-processed customer data.

[1344] Filter customer data that matches campaign criteria to identify suitable customers for advertising, using a condition-based SQL filtering query.

[1345] Step 5:

[1346] The server scores the matched targets.

[1347] Scores are assigned based on the degree of match with the target's attributes and past ad click history. Scoring is performed using a standardized scaling algorithm (e.g., MinMaxScaler). Evaluation indicators include the degree of match with industry, suitability with company size, and relevance of past click history.

[1348] Step 6:

[1349] The server ranks the targets based on the scoring results.

[1350] The targets are sorted in descending order of score to generate a ranking list, which is used to determine the priority of sales activities. The generated list is stored in temporary memory.

[1351] Step 7:

[1352] The server generates a report based on the ranking results.

[1353] The report includes the target name, score, ranking, etc. The report can be generated in PDF or HTML format and sent to the device, and the report is provided in a format that users can easily view and download.

[1354] Through the above processing steps, target selection in an advertising campaign is automated, and a system that supports effective advertising activities is realized.

[1355] 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.

[1356] This invention relates to a system that utilizes customer data to extract effective corporations for the introduction of products currently handled by the team. This system includes processes for acquiring, preprocessing, matching, scoring, and generating reports on customer data, and further improves the user experience by combining it with an emotion engine that recognizes user emotions.

[1357] System Components

[1358] The system mainly has the following components:

[1359] Data Acquisition Method

[1360] Data preprocessing measures

[1361] Corporate matching method

[1362] Scoring Instrument

[1363] Ranking methods

[1364] Report Generation Method

[1365] Emotion Engine

[1366] Data Acquisition Method

[1367] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal sends this request to the server, which then accesses the customer database to retrieve the required data.

[1368] Data preprocessing measures

[1369] The server then cleans the acquired customer data and removes duplicates, removing records containing NULL values, converting data with inconsistent formats into a unified format, and filling in missing data.

[1370] Corporate matching method

[1371] The server matches the optimal corporation based on the product's attribute information (industry, company size, location, etc.) and pre-processed customer data. Past purchase history is also analyzed to extract the corporation that is most suitable for the product.

[1372] Scoring Instrument

[1373] The server assigns a score to each matched company. This score is calculated based on the suitability of the product and the purchase history. For example, a company that shows a high suitability is assigned a high score.

[1374] Ranking methods

[1375] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[1376] Report Generation Method

[1377] The server generates a report based on the ranking results, which includes the score for each company and an explanation of the reasons, and is provided in PDF, HTML, and other formats.

[1378] Emotion Engine

[1379] The emotion engine has the ability to recognize emotions from user reactions and input data. The emotion engine is used to perform the following processes:

[1380] Adjusting report display based on user sentiment

[1381] Adjusting the scoring algorithm based on user sentiment

[1382] Adjusting ranking priorities based on user sentiment

[1383] Specific examples

[1384] As a specific example, consider a situation where a user who wants to sell a new cloud service requests the server from their device to "extract corporations suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from its customer database and performs data cleaning. Next, it matches the cloud service attributes with companies that have used similar services in the past. The resulting list of candidate corporations is scored and ranked in order of priority. The server then generates a report based on this and sends it to the device. The user can use this report to efficiently conduct sales activities.

[1385] Furthermore, by utilizing an emotion engine to recognize the user's emotions, the report display format is adjusted according to the user's state. For example, if the user is feeling stressed, the report will be displayed in an easy-to-understand and concise format. Furthermore, the scoring algorithm and ranking priority are also adjusted based on the user's emotions, enabling more appropriate proposals to be made to the user. In this way, the user experience is improved, resulting in more effective corporate identification and more efficient sales activities.

[1386] The processing flow will be explained below.

[1387] Step 1: Receiving a request

[1388] The terminal receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal then sends this request to the server.

[1389] Step 2: Database Access

[1390] The server accesses the customer database based on the request received from the terminal, and retrieves the required data based on specific filter conditions (e.g., specific industry or region) using an SQL query.

[1391] Step 3: Data Acquisition

[1392] The server receives customer data returned from a database query, including demographic information such as company name, industry, size, location, and purchase history.

[1393] Step 4: Data Cleaning

[1394] The server cleans the customer data it retrieves. For example, it deletes records containing NULL values ​​and converts data with inconsistent formats into a unified format. It also performs complementation processing on incomplete data to optimize it.

[1395] Step 5: Remove duplicates

[1396] The server detects and removes duplicate records from the cleaned data, identifying duplicates based on company name or ID and merging them into a single record.

[1397] Step 6: Processing product attribute information

[1398] The server analyzes the product's attribute information and extracts its characteristics, including the type of business, company size, and location.

[1399] Step 7: Corporate Matching

[1400] The server matches the optimal corporation based on the product attribute information and pre-processed customer data. It also analyzes past purchase history and other data to identify the corporation that is most suitable for the product.

[1401] Step 8: Scoring

[1402] The server assigns a score to each matched company. This score is calculated based on the product compatibility and purchasing history. For example, a company that shows a high compatibility is assigned a high score.

[1403] Step 9: Ranking Generation

[1404] The server sorts the list of corporations based on the scoring results, placing corporations with higher scores at the top to create a ranking list.

[1405] Step 10: Generate reports

[1406] The server generates a report based on the ranking results. This report includes the score for each company and an explanation of the reasons. The generated report is available in PDF, HTML, and other formats.

[1407] Step 11: Emotion Recognition

[1408] The server uses an emotion engine to recognize the user's emotions. It evaluates the user's emotional state based on their reactions and input data, and identifies their current emotion.

[1409] Step 12: Adjusting the report display

[1410] Based on the results of emotion recognition, the server adjusts the report display format. For example, if the user is feeling stressed, the report will be displayed in a simple and easy-to-understand manner.

[1411] Step 13: Adjust the scoring algorithm

[1412] Based on the emotion recognition results, the server adjusts the scoring algorithm, for example, presenting a more detailed analysis if the user is excited.

[1413] Step 14: Adjusting Ranking Priority

[1414] Based on the results of emotion recognition, the server adjusts the ranking priority. For example, if the user is calm, the ranking is displayed with normal priority.

[1415] Step 15: Report Submission

[1416] The server generates and adjusts the report and sends it to the terminal, which receives it and displays it to the user.

[1417] These are the processing steps of this system. Based on the reports provided, users can efficiently identify companies that are suitable for their products and conduct sales activities. Adjustments made by the emotion engine also aim to improve the user experience.

[1418] Example 2

[1419] 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."

[1420] Conventional systems that utilize customer data often perform data acquisition, preprocessing, and even corporate matching and scoring individually, without adjusting to the user's experience or emotions. This results in problems such as the information users receive being suboptimal, and insufficient efficiency in sales activities. Furthermore, the lack of a mechanism for adjusting the report content and display format based on the user's current emotions and state makes it difficult to provide information that is easy for users to understand. Given this background, there is a need for the development of a system that utilizes customer data and dynamically provides information based on the user's emotions.

[1421] 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.

[1422] In this invention, the server includes means for acquiring customer data, means for preprocessing the acquired customer data, means for matching the most suitable corporation based on the attribute information of the product and the acquired customer data, means for assigning a score to each corporation and creating a ranking, and means for recognizing the user's emotions and adjusting the report display format and scoring algorithm based on the emotions. This allows the user to receive the information they need in the most suitable format and conduct sales activities more efficiently.

[1423] "Customer data" refers to a dataset that includes all information about customers, and is used to develop sales strategies for products and to respond to customers.

[1424] "Preprocessing" refers to a series of processes such as data cleaning, deleting duplicate data, and standardizing data formats that are carried out to improve the quality of acquired data.

[1425] "Product attribute information" refers to information about the features and characteristics associated with a specific product, such as the industry, company size, and location.

[1426] "Corporate matching" refers to the process of identifying the most suitable business partners and client companies based on product attribute information and pre-processed customer data.

[1427] "Scoring" refers to the process of assigning an evaluation score to matched businesses based on suitability, purchasing history, etc.

[1428] "Ranking" refers to ranking corporations based on the scoring results and creating a list according to importance and suitability.

[1429] A "report" is a document generated based on the ranking results, which includes scores for each corporation and explanations of the reasons, and is provided in PDF or HTML format.

[1430] An "emotion engine" is an engine that has the ability to recognize emotions from user reactions and input data and adjust the system's behavior based on that.

[1431] The present invention relates to a system for utilizing customer data to extract effective corporations for the introduction of products currently handled by a team. The system includes a data acquisition means, a data preprocessing means, a corporation matching means, a scoring means, a ranking means, a report generation means, and an emotion engine.

[1432] System program generation

[1433] The program of this system is realized by the cooperation of the server, terminals, and user operations. The server mainly processes and analyzes data, and the terminals provide an interface with the user. The program includes the following main software libraries:

[1434] MySQL (database management)

[1435] pandas (data preprocessing)

[1436] scikit-learn (machine learning model)

[1437] Fpdf (PDF report generator)

[1438] Transformers (emotion recognition)

[1439] Process Overview

[1440] The user uses a terminal to send a request to extract corporations suitable for introducing a product. This request includes information about the product to be analyzed and filter conditions for the required customer data. The terminal sends this request to the server, which then accesses the MySQL database to retrieve the required customer data.

[1441] The server uses the pandas library to clean the acquired customer data. Specifically, it deletes records containing NULL values, converts data with inconsistent formats into a unified format, and fills in missing data. The server then uses a scikit-learn machine learning model to match the optimal company based on the product attribute information and preprocessed customer data. It analyzes past purchase history and other factors to extract companies that are suitable for the product.

[1442] For each matched company, the server assigns a score using a random forest regression model. This score is calculated based on the product's suitability and past purchase history. Based on the scoring results, the server generates a ranking of companies in descending order of score.

[1443] Based on the generated ranking results, the server uses the Fpdf library to generate a report, which includes scores for each company and explanations of the results, and is provided to the terminal in PDF or HTML format.

[1444] Additionally, the server recognizes the user's emotions through an emotion engine and adjusts the report presentation and scoring algorithms accordingly. Emotion recognition is performed using the Transformers library, and if the user is feeling stressed, the report will be presented in a clearer and more concise format.

[1445] Specific examples

[1446] Consider the case where a user who wants to sell a new cloud service requests the server from a device to "extract corporations suitable for cloud services." The server retrieves data on the IT industry and small and medium-sized enterprises from a customer database and performs data cleaning. Next, it matches companies that have used similar services in the past based on the attributes of the cloud service. The resulting list of candidate corporations is scored and ranked in order of priority. The server generates a report based on this and sends it to the device. The user can use this report to efficiently conduct sales activities. Furthermore, an emotion engine is used to recognize the user's emotions, and the display format of the report is adjusted according to the user's state.

[1447] Prompt Sentence Examples

[1448] We would like to use customer data to identify companies suitable for the cloud services we currently offer. First, we would like you to acquire and cleanse the data based on the following criteria: industry is IT, company size is small and medium-sized enterprises. Next, we would like you to match the most suitable companies based on the attributes of the cloud services, score and rank them, and generate a report. We would also like you to adjust the report display format and scoring algorithm based on user sentiment.

[1449] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1450] Program processing flow

[1451] Step 1: User submits request

[1452] Input: User inputs product information and customer data filter criteria

[1453] Process: The user uses the terminal to enter the "Request to extract legal entities suitable for cloud services" in the interface and clicks the submit button.

[1454] Output: The device forwards this request data to the server.

[1455] Step 2: Data Acquisition

[1456] Input: Request data sent from the terminal

[1457] Process: The server connects to the customer database and executes a SQL query such as "SELECT FROM customer table WHERE industry='IT' AND company size='Small / Medium Business'" to extract the relevant data.

[1458] Output: Obtain the required customer data and pass it on to the next processing step

[1459] Step 3: Data Preprocessing

[1460] Input: Customer data retrieved by the server

[1461] Processing: The server uses the pandas library to create a data frame, remove records containing NULL values, convert data with different formats to a unified format, and impute missing data.

[1462] Specific behavior: Execute code such as "df.dropna(inplace=True)" or "df.fillna("Unknown", inplace=True)".

[1463] Output: Preprocessed, clean data passed to the next processing step

[1464] Step 4: Corporate Matching

[1465] Input: Preprocessed clean customer data and product attribute information

[1466] Processing: The server uses scikit-learn's KNN (k-nearest neighbor) algorithm to identify corporations with high similarity based on past product usage history.

[1467] Specific operations: Perform operations such as "model.fit(data)" and "model.predict(new data)".

[1468] Output: Pass the list of matched entities to the next processing step

[1469] Step 5: Scoring

[1470] Input: Matched legal entity list

[1471] Processing: The server calculates the fitness of each legal entity using a random forest regression model and assigns a high score to legal entities that show a high fitness.

[1472] Specific operation: Execute code such as "model.fit(X_train, y_train)" or "model.predict(X_test)".

[1473] Output: Pass the scored list of legal entities to the next processing step

[1474] Step 6: Ranking

[1475] Input: List of scored legal entities

[1476] Processing: The server sorts the list of corporations using pandas' "df.sort_values(by='score', ascending=False)" and arranges them in order of highest score.

[1477] Output: Pass the ranked list of companies to the next processing step

[1478] Step 7: Generate reports

[1479] Input: Ranked corporate list

[1480] Processing: The server uses the Fpdf library to generate a report that includes the scores for each company and an explanation of the reasons.

[1481] Specific operation: Execute code such as "pdf.cell(200, 10, txt="Corporate List", ln=True)" and "pdf.output("report.pdf")".

[1482] Output: Generate reports in PDF and HTML format and send them to your device.

[1483] Step 8: Emotional Engine Alignment

[1484] Input: User reactions and input data

[1485] Processing: The server uses the Transformers library to analyze the user's emotions. It executes code like "emotion_analyzer = pipeline('sentiment-analysis')" and "result = emotion_analyzer("text")" to adjust the report display format and scoring algorithm based on the emotions.

[1486] Output: Providing tailored reports and algorithms to users

[1487] (Application example 2)

[1488] 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."

[1489] Conventional corporate matching systems have basic functions such as data cleaning, matching, scoring, and report generation to effectively identify product applications, but they are unable to adjust the report display content or matching algorithms to take user emotions into account. This prevents the system from providing optimal information based on the user's emotional state, limiting the improvement of user experience and efficient sales activities. Furthermore, the system lacks a function to automatically generate report content from input prompts using a generative AI model, resulting in low report creation efficiency.

[1490] 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.

[1491] In this invention, the server includes means for acquiring customer data, means for preprocessing the acquired customer data, means for matching optimal corporations based on product attribute information and the acquired customer data, means for assigning scores to each corporation and creating rankings, means for generating a report including the ranking results and outputting it in a format viewable by the user, means for recognizing user emotions and adjusting the report display, means for adjusting the scoring algorithm and ranking priority based on the user emotions, means for detecting user emotions through video input, and means for automatically generating report content from input prompt sentences using a generative AI model. This enables the provision of more optimal information according to the user's emotional state, improving the user experience and enabling more efficient sales activities.

[1492] "Customer data" refers to information about the corporation to which the product is applied, and includes data such as the customer's name, industry, purchase history, and location.

[1493] "Preprocessing" refers to a series of processes to improve the quality of data, such as cleaning the acquired data, deleting duplicate data, standardizing formats, and filling in missing data.

[1494] "Product attribute information" refers to unique information related to a product, such as its characteristics and functions, target industry, company size, and geographical conditions.

[1495] "Matching" is the process of selecting the most suitable corporation based on the product's attribute information and pre-processed customer data, taking into consideration the customer's industry, purchasing history, company size, etc.

[1496] "Scoring" is the process of quantifying the suitability of products for each matched corporation and assigning them a score.

[1497] "Ranking" refers to arranging corporations in descending order of score based on the scoring results.

[1498] A "report" is a document containing ranking results and an explanation of the reasons for the scores, which is provided to users in a format that can be viewed by them.

[1499] "User emotion" refers to the current emotional state of the user using the system, and includes emotions such as joy, anger, sadness, and stress.

[1500] "Emotion recognition" is a technology that analyzes user input data, primarily video input, to detect the user's emotional state.

[1501] A "scoring algorithm" refers to the calculation method and rules for assigning scores to corporations, and quantifies the suitability of products.

[1502] "Priority" refers to the importance or position of a company in the ranking, and is adjusted based on user sentiment.

[1503] "Video input" refers to input data for recognizing a user's emotions, and includes video footage capturing the user's facial expressions and movements.

[1504] A "generative AI model" is an artificial intelligence model for automated report generation and data analysis that provides appropriate output based on input data.

[1505] A "prompt" is an instruction for operating a generative AI model, and specifically describes the instructions for report generation and data analysis.

[1506] This invention is a system that utilizes customer data to identify the most suitable corporations for product introduction. This system encompasses a series of processes from customer data acquisition to preprocessing, corporation matching, scoring, ranking, report generation, and user emotion recognition.

[1507] Hardware and Software

[1508] The system is built using the following hardware and software:

[1509] Hardware: Smartphones, tablets

[1510] Software: Python, pandas, scikit-learn, FPDF, emotion_recognition (provisional package)

[1511] Data acquisition and preprocessing

[1512] The server receives a request from the user. The request includes information about the product to be analyzed and filter conditions for the required customer data. Based on this, the server retrieves customer data from the database. The retrieved data is then cleaned, duplicate data is removed, the format is standardized, and missing data is filled in.

[1513] Corporate Matching and Scoring

[1514] The server uses cosine similarity calculations to match the optimal company based on the product's attribute information and pre-processed customer data. It then assigns a score to each company according to a scoring algorithm. This score quantifies the product's suitability.

[1515] Ranking and Report Generation

[1516] Based on the scoring results, the companies are ranked in order of highest score and a report is generated. The generated report is output in PDF format and provided in a format that can be viewed by users.

[1517] Emotion Recognition and Report Adjustment

[1518] The server recognizes the user's emotions through video input. Based on this emotional data, it adjusts the report display format and changes the scoring algorithm and ranking priority. If the user is feeling stressed, the report will be adjusted to be more clear and concise.

[1519] Generative AI model usage example

[1520] The server automatically generates report content using a generative AI model. The generative AI model generates an appropriate report based on the input of a prompt sentence. The following is an example of a prompt sentence:

[1521] user_request = {

[1522] "ad_attributes": [0.8, 0.2, 0.3],

[1523] "user_video": "path / to / user_video.mp4"

[1524] }

[1525] Specific examples

[1526] For example, if a user wants to find target corporations for a new advertising campaign, they provide the system with product attribute information and a user's video input. The server retrieves and preprocesses the customer data to match the corporations that best suit the product. Next, after scoring and ranking, a report based on emotion recognition is generated. This report is automatically generated using a generative AI model and presented in a format that users can view.

[1527] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1528] Step 1:

[1529] The user sends a request from their device. The request includes information about the product to be analyzed (e.g., advertising campaign attribute information) and filter conditions for the required customer data. Based on this input data, the server determines which customer data to retrieve.

[1530] Step 2:

[1531] The server accesses the customer database and retrieves customer data that matches the specified product information and filter criteria. This process involves executing a database query to extract the required records. The retrieved customer data is output in raw data format.

[1532] Step 3:

[1533] The server preprocesses the customer data it acquires. Specifically, it cleans the data (removing NULL values, standardizing formats, and filling in missing data) and removes duplicate data. This process improves the quality of the data and makes it suitable for analysis. The preprocessed data is then output.

[1534] Step 4:

[1535] The server matches the optimal company based on the product's attribute information and pre-processed customer data. It calculates the compatibility between each company and product using cosine similarity calculations. It generates a compatibility score based on this input data, which becomes the output.

[1536] Step 5:

[1537] The server assigns a score to each matched company based on the generated compatibility score. This score assignment process is quantified (e.g., in the range of 0 to 100) based on the compatibility of the product. This score data is output.

[1538] Step 6:

[1539] The server ranks the corporations in descending order based on the scoring results. In this ranking process, the score data is sorted in descending order to create a ranking list. This ranking list is output.

[1540] Step 7:

[1541] The server generates a report based on the ranking list. The report includes scores for each company and an explanation of the reasons. The report is generated and output in PDF format.

[1542] Step 8:

[1543] The server performs emotion recognition based on the video input data provided by the user. It analyzes facial expressions from the video data and detects the user's emotional state (e.g., joy, anger, sadness, stress, etc.). This emotional data is output.

[1544] Step 9:

[1545] The server adjusts the report display format, scoring algorithm, and ranking priority based on the emotion data. For example, if the user is feeling stressed, the report will be adjusted to be more clear and concise. The adjusted report is then output.

[1546] Step 10:

[1547] The server automatically generates report content using a generative AI model. Based on the prompt input (e.g., "user_request = { "ad_attributes": [0.8, 0.2, 0.3], "user_video": "path / to / user_video.mp4"}"), the generative AI model creates an appropriate report. The generated report based on this prompt is output.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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).

[1555] 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.

[1556] 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."

[1557] 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.

[1558] 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).

[1559] 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.

[1560] 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.

[1561] 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.

[1562] 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.

[1563] 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.

[1564] 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.

[1565] 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.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] The following is further disclosed regarding the above embodiment.

[1570] (Claim 1)

[1571] a means of obtaining customer data;

[1572] means for pre-processing the acquired customer data;

[1573] A means of matching the most suitable corporation based on the attribute information of the product and the acquired customer data,

[1574] A means of assigning scores to each corporation and creating rankings;

[1575] means for generating a report including the ranking results and outputting the report in a format viewable by a user;

[1576] A system including:

[1577] (Claim 2)

[1578] 10. The system of claim 1, wherein the customer data preprocessing means includes data cleaning and deduplicate data removal.

[1579] (Claim 3)

[1580] 2. The system of claim 1, wherein the means for matching the most suitable corporation based on the attribute information of the merchandise and customer data includes means for analyzing the customer's purchasing history and extracting patterns related to the merchandise.

[1581] "Example 1"

[1582] Claiming a new invention

[1583] (Claim 1)

[1584] means for receiving a prompt sentence entered by a user;

[1585] a means of obtaining customer data;

[1586] means for pre-processing the acquired customer data;

[1587] A method for matching the most suitable corporation based on product attribute information and pre-processed customer data,

[1588] A means of assigning scores to each corporation and creating rankings;

[1589] means for generating a report including the ranking results and outputting the report in a format viewable by a user;

[1590] A system including:

[1591] (Claim 2)

[1592] 10. The system of claim 1, wherein the customer data preprocessing means includes cleaning the data and removing duplicate data.

[1593] (Claim 3)

[1594] The system of claim 1, wherein the means for matching the most suitable corporation based on the attribute information of the product and the preprocessed customer data includes means for analyzing the customer's purchasing history and extracting patterns related to the product.

[1595] "Application Example 1"

[1596] (Claim 1)

[1597] a means of obtaining customer data;

[1598] means for pre-processing the acquired customer data;

[1599] A means of matching the most suitable corporation based on the attribute information of the product and the acquired customer data,

[1600] A means of assigning scores to each corporation and creating rankings;

[1601] means for generating a report including the ranking results and outputting the report in a format viewable by a user;

[1602] A means to input the conditions of an advertising campaign, extract targets based on target customer data, score them, generate a ranking list, and output it in report format;

[1603] A system including:

[1604] (Claim 2)

[1605] 10. The system of claim 1, wherein the customer data preprocessing means includes data cleaning and deduplicate data removal.

[1606] (Claim 3)

[1607] 2. The system of claim 1, wherein the means for matching the most suitable corporation based on the attribute information of the merchandise and customer data includes means for analyzing the customer's purchasing history and extracting patterns related to the merchandise.

[1608] (Claim 4)

[1609] 2. The system of claim 1, wherein the means for filtering and scoring target customer data based on the conditions of the advertising campaign further comprises means for evaluating attribute matches and past ad click histories of target candidates.

[1610] (Claim 5)

[1611] 10. The system of claim 1, further comprising means for exporting the report in PDF or HTML format.

[1612] "Example 2: Combining Emotion Engines"

[1613] (Claim 1)

[1614] a means of obtaining customer data;

[1615] means for pre-processing the acquired customer data;

[1616] A means of matching the most suitable corporation based on the attribute information of the product and the acquired customer data,

[1617] A means of assigning scores to each corporation and creating rankings;

[1618] means for generating a report including the ranking results and outputting the report in a format viewable by a user;

[1619] A means of recognizing user sentiment and adjusting report presentation and scoring algorithms accordingly; and

[1620] A system including:

[1621] (Claim 2)

[1622] 10. The system of claim 1, wherein the customer data preprocessing means includes data cleaning and deduplicate data removal.

[1623] (Claim 3)

[1624] 2. The system of claim 1, wherein the means for matching the most suitable corporation based on the attribute information of the merchandise and customer data includes means for analyzing the customer's purchasing history and extracting patterns related to the merchandise.

[1625] "Application example 2 when combining emotion engines"

[1626] (Claim 1)

[1627] a means of obtaining customer data;

[1628] means for pre-processing the acquired customer data;

[1629] A means of matching the most suitable corporation based on the attribute information of the product and the acquired customer data,

[1630] A means of assigning scores to each corporation and creating rankings;

[1631] means for generating a report including the ranking results and outputting the report in a format viewable by a user;

[1632] means for recognizing user emotions and adjusting report display;

[1633] means for adjusting the scoring algorithm and ranking priorities based on user sentiment;

[1634] A system including:

[1635] (Claim 2)

[1636] 10. The system of claim 1, wherein the customer data preprocessing means includes data cleaning and deduplicate data removal.

[1637] (Claim 3)

[1638] 2. The system of claim 1, wherein the means for matching the most suitable corporation based on the attribute information of the merchandise and customer data includes means for analyzing the customer's purchasing history and extracting patterns related to the merchandise.

[1639] (Claim 4)

[1640] 10. The system of claim 1, wherein the means for recognizing a user's emotion comprises means for detecting a user's emotion through video input.

[1641] (Claim 5)

[1642] 2. The system of claim 1, wherein the report generation means includes means for automatically generating report content from input prompt statements using a generative AI model. [Explanation of symbols]

[1643] 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 of obtaining customer data; means for pre-processing the acquired customer data; A means of matching the most suitable corporation based on the attribute information of the product and the acquired customer data, A means of assigning scores to each corporation and creating rankings; means for generating a report including the ranking results and outputting the report in a format viewable by a user; A system including:

2. 2. The system of claim 1, wherein the customer data preprocessing means includes data cleaning and deduplicate data removal.

3. 2. The system according to claim 1, wherein the means for matching the most suitable corporation based on the attribute information of the merchandise and the customer data includes means for analyzing the customer's purchase history and extracting patterns related to the merchandise.

Images