system

Abstract

Provide a system. [Solution] A means of receiving feedback and requests from customers; A means of storing received feedback and requests in a database; A means of analyzing stored feedback and requests using natural language processing; A means for generating improvement measures and policies based on the analysis results; A means to visually present the generated improvement measures and initiatives to the customer, Marketing campaign optimization system including.

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] Marketing campaigns require efficient collection of customer feedback and requests, and the ability to quickly and effectively improve campaigns based on that feedback. However, traditional methods require time-consuming collection of feedback, and analyzing that feedback requires significant time and effort. Furthermore, it is difficult to propose specific improvement measures or initiatives based on the analysis results, which creates challenges in improving customer satisfaction and engagement. [Means for solving the problem]

[0005] The present invention is a marketing campaign optimization system that includes a means for receiving feedback and requests from customers, a means for storing the received feedback and requests in a database, a means for analyzing the stored feedback and requests using natural language processing, a means for generating improvement measures and policies based on the analysis results, and a means for visually presenting the generated improvement measures and policies to customers. The present invention makes it possible to maximize the effectiveness of marketing campaigns and increase customer satisfaction and engagement by efficiently collecting and analyzing customer feedback and quickly generating specific improvement measures.

[0006] "Customer" means any person or entity that provides feedback or requests in connection with a marketing campaign.

[0007] "Feedback" refers to the opinions, impressions, and requests that customers provide regarding a campaign.

[0008] "Requests" refer to improvements or specific requests that customers have for your marketing campaign.

[0009] The term "means" refers to technical elements or devices required to perform each step in the present invention.

[0010] "Database" refers to the system for storing and managing collected feedback and requests.

[0011] "Natural language processing" refers to computer technologies and methods for analyzing and understanding the meaning and sentiment of feedback and requests provided by customers.

[0012] "Analysis" refers to the process of using natural language processing to understand customer feedback and requests and extract key information and trends from them.

[0013] "Improvement measures" refer to specific methods or action plans proposed based on the analysis results.

[0014] "Initiative" refers to the specific approach or plan implemented to optimize a marketing campaign.

[0015] "Visually presenting" refers to displaying the generated improvement measures and initiatives in an easy-to-understand manner for customers.

[0016] A "marketing campaign optimization system" refers to a system that combines the above-mentioned measures to maximize the effectiveness of a marketing campaign and increase customer satisfaction and engagement. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention relates to a marketing campaign optimization system that collects feedback and requests from customers, analyzes the feedback and requests, generates improvements to the marketing campaign, and presents them to the customers. Specific embodiments for carrying out the present invention will be described below.

[0039] Program processing and behavior

[0040] 1. Collect customer feedback

[0041] User: Uses a device to enter feedback or requests about the campaign, for example, "The new product introduction article is not very appealing."

[0042] Terminal: Sends the feedback entered by the user to the server.

[0043] 2. Saving your feedback to a database

[0044] Server: Stores the received feedback in a database. The stored data includes the feedback content as well as the user's identification information.

[0045] 3. Analysis using natural language processing

[0046] Server: The stored feedback is fed into a natural language processing engine for content analysis, including sentiment assessment and topic extraction.

[0047] Server: As a result of the analysis, for example, from feedback that "the article introducing a new product is not appealing," the insight that "visual enhancement is needed" is extracted.

[0048] 4. Generate improvements

[0049] Server: Generates recommendations for improving marketing campaigns based on the analysis results, such as "add visual elements to product articles and highlight product benefits with bullet points."

[0050] 5. Providing improvement measures to users

[0051] Server: Sends the generated remediation measures to the device.

[0052] On the device: Display the received improvement recommendations in a user-friendly format, for example, "In your next product launch article, we recommend using more product photos to highlight the benefits."

[0053] 6. Re-feedback

[0054] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[0055] Specific examples

[0056] Example 1: Improving a new product introduction campaign

[0057] 1. User: Enters feedback on the campaign site saying, "The article introducing the new product is not very appealing."

[0058] 2. Device: Sends feedback to the server.

[0059] 3. Server: Stores the received feedback in a database and analyzes the issue of "not visually appealing" using natural language processing.

[0060] 4. Server: Generate an improvement plan: "Add product photos to new product introduction articles to highlight their benefits."

[0061] 5. Server: Sends the improvement plan to the device.

[0062] 6. Device: Suggest to the user, "In your next product launch article, add visuals and explain the benefits in bullet points."

[0063] Example 2: Improving a sales campaign

[0064] 1. User: Enters feedback on the online store saying, "There are not many products on sale and it's not appealing."

[0065] 2. Device: Sends feedback to the server.

[0066] 3. Server: Stores the feedback in a database and analyzes the problem of "not enough products available" using natural language processing.

[0067] 4. Server: Generate an improvement plan: "Increase the number of items on sale and introduce bundle discounts."

[0068] 5. Server: Sends the improvement plan to the device.

[0069] 6. Device: Propose to the user that "In the next sale, we will increase the number of eligible products and introduce set discounts."

[0070] In this way, the present invention can efficiently collect customer feedback, quickly analyze it, generate specific improvement measures, and present them to customers, thereby maximizing the effectiveness of marketing campaigns and increasing customer satisfaction and engagement.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[0074] Step 2:

[0075] Terminal: Receives user feedback and sends feedback data to the server.

[0076] Step 3:

[0077] Server: Receives feedback sent from the device and stores it in a database, including user identification information.

[0078] Step 4:

[0079] Server: Starts parsing the stored feedback data using a natural language processing (NLP) engine, for example using an NLP library such as TextBlob or spaCy.

[0080] Step 5:

[0081] Server: Analyzes the feedback using natural language processing to extract key topics and sentiments, for example, obtaining results such as "visually unappealing."

[0082] Step 6:

[0083] Server: Identify customer requests based on the analysis results. For example, extract a request such as "New product introduction articles need visual enhancements."

[0084] Step 7:

[0085] Server: Review data from other users with similar feedback and perform trend analysis to identify common issues.

[0086] Step 8:

[0087] Server: Generates specific improvements and measures for marketing campaigns based on trend analysis results, such as adding product photos to new product introduction articles and highlighting their benefits in bullet points.

[0088] Step 9:

[0089] Server: Sends the generated remediation measures to the device.

[0090] Step 10:

[0091] On the device: Display the improvement suggestions to the user and present them in an easy-to-understand format, such as "In your next product launch article, we recommend using more product photos to highlight the benefits."

[0092] Step 11:

[0093] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[0094] Example 1

[0095] 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."

[0096] Conventional marketing campaign optimization systems have difficulty efficiently analyzing customer feedback and quickly proposing specific improvement measures. Furthermore, it is difficult to continuously and dynamically incorporate feedback, which results in insufficient improvement of customer satisfaction and engagement. Furthermore, the generated improvement measures are often not specific and not feasible.

[0097] 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.

[0098] In this invention, the server includes a means for receiving feedback and requests from customers, a means for storing the received feedback and requests in an information repository, a means for analyzing the stored feedback and requests using natural language processing, a means for generating improvement measures and policies based on the analysis results using a generative AI model, and a means for visually presenting the generated improvement measures and policies to customers. This makes it possible to efficiently collect and analyze customer feedback and quickly provide specific, actionable improvement measures. Furthermore, by forming a continuous feedback loop, the effectiveness of marketing campaigns can be maximized and customer satisfaction and engagement can be improved.

[0099] "Feedback" refers to information such as opinions, requests, and evaluations provided by customers.

[0100] "Requests" are requests for improvements or new features that customers expect from services or products.

[0101] An "information repository" is a system for storing and managing data, such as a database or storage system.

[0102] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0103] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to automatically generate new data or suggestions.

[0104] "Improvements" are specific proposals and measures to improve existing systems and campaigns.

[0105] "Measures" are specific actions or strategies planned to achieve business goals.

[0106] "Visual presentation" means displaying information on a screen or display in a format that is easy for the user to understand.

[0107] The present invention relates to a marketing campaign optimization system that collects and analyzes feedback and requests from customers, generates improvements to the marketing campaign based on the collected feedback, and presents the improvements to the customers. Specific embodiments for carrying out the present invention will be described below.

[0108] This system mainly consists of a server, terminals, and users. The specific roles and processes of each component are shown below.

[0109] Gathering feedback

[0110] Users can use their devices to input their feedback and requests about the campaign. The device interface can be a web form, a mobile application, etc. For example, a user might input, "The article introducing the new product is not very appealing."

[0111] The terminal receives the feedback information input by the user, generates an HTTP POST request, and sends it to the server.

[0112] Feedback storage and analysis

[0113] The server stores the feedback received from the terminal in a database (information collection), and the stored data includes the feedback content, user identification information, and a timestamp.

[0114] The stored feedback data is analyzed using a natural language processing (NLP) engine (e.g., Microsoft® Azure® Cognitive Services text analysis API or Google® Cloud Natural Language API). The server sends the feedback data to these external APIs and receives the analysis results.

[0115] As a result of the analysis, the main topics and emotional evaluations of the feedback are extracted. For example, from feedback that "the new product introduction article is not appealing," the insight that "visual appeal needs to be improved" can be obtained.

[0116] Generate improvements

[0117] The server generates specific marketing campaign improvement measures using a generative AI model (e.g., a general natural language generation model) based on the analysis results of natural language processing. For example, improvement measures such as "add visual elements to product introduction articles and emphasize the product's benefits in bullet points" are generated.

[0118] The generated improvements are formatted in a way that is easy for the user to understand.

[0119] Providing improvement measures and providing feedback

[0120] The server sends the generated remediation measures to the terminal as an HTTP response.

[0121] The device converts the received improvements into a display data structure and displays it in the UI of a web page or application, for example, "In our next new product introduction article, we'll add visual elements and explain the benefits in bullet points."

[0122] Users can then provide additional feedback or new suggestions for improvements, creating a feedback loop that allows for continuous improvement of the campaign.

[0123] Examples of prompt statements

[0124] Prompt 1: "How would you generate improvements based on customer feedback about a new product introduction article that they found less appealing?"

[0125] Prompt 2: "Explain how to generate optimal improvements based on customer feedback that feels there are not enough products in a sales campaign."

[0126] The above is a specific embodiment of the present invention. This system efficiently collects and analyzes customer feedback and can quickly provide specific and actionable improvement measures, thereby maximizing the effectiveness of marketing campaigns and improving customer satisfaction.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Step 1: Gather feedback

[0129] The user uses the terminal to input feedback and requests about the campaign, for example, "The article introducing the new product is not very appealing."

[0130] Input: Feedback text (e.g., "The new product introduction article is not very appealing.")

[0131] Action: Enter your feedback through a device interface (e.g., a web form or a mobile application) and click the "Submit" button.

[0132] Output: User feedback is sent to the device.

[0133] Step 2: Submit your feedback

[0134] The terminal receives the feedback information input by the user, generates an HTTP POST request, and sends it to the server.

[0135] Input: The feedback text entered by the user

[0136] What it does: Creates an HTTP POST request and sends it to the server with the feedback information.

[0137] Output: The feedback information is sent to the server.

[0138] Step 3: Save your feedback

[0139] The server stores the feedback received from the terminal in a database, and the stored data includes the feedback content, user identification information, and a timestamp.

[0140] Input: Feedback information sent from the device

[0141] What it does: Parses the feedback information and executes an insert query to the database to save the data.

[0142] Output: The feedback information is stored in a database.

[0143] Step 4: Analyze the feedback

[0144] The server then inputs the stored feedback data into a natural language processing (NLP) engine to analyze the content, for example, using the Microsoft Azure Cognitive Services text analysis API or the Google Cloud Natural Language API.

[0145] Input: Feedback information stored in the database

[0146] How it works: Sends feedback data to a natural language processing API and receives analysis results.

[0147] Output: Analysis results such as main topics of feedback and sentiment ratings

[0148] Step 5: Extracting insights

[0149] The server extracts key topics and insights from the feedback based on the results of natural language processing analysis. For example, from feedback such as "The article introducing a new product is not appealing," it can obtain the insight that "The visual appeal needs to be improved."

[0150] Input: Analysis results of natural language processing

[0151] What it does: Extract topics and insights from the analysis results and store them in a database.

[0152] Output: Insights and topic information

[0153] Step 6: Generate remediation measures

[0154] Based on the analysis results, the server generates specific marketing campaign improvement measures using a generative AI model (e.g., GPT-3 (registered trademark)).

[0155] Input: Insights and topic information

[0156] How it works: Input insight data into a generative AI model and get output improvement measures.

[0157] Output: Specific improvement suggestions (e.g., "Add visual elements to product articles and highlight product benefits with bullet points")

[0158] Step 7: Propose improvement measures

[0159] The server transmits the generated remedial measures to the terminal.

[0160] Input: Improvements generated by a generative AI model

[0161] Behavior: Remediation data is sent to the device as an HTTP response.

[0162] Output: Remediation data is sent to the terminal.

[0163] The device converts the received remedial measures into a display data structure and displays them on a web page or application UI.

[0164] Input: Remediation data sent from the server

[0165] How it works: Received data is bound to HTML and application UI components and displayed on the screen.

[0166] Output: The remediation measures are displayed in a format that the user can understand visually.

[0167] Step 8: Re-feedback

[0168] Users can then provide additional feedback or new requests for the proposed improvements, creating a feedback loop that allows for continuous improvement of the campaign.

[0169] Input: Feedback on the improvement plan (e.g., "I agree with the improvement plan" or "I would like to add another request")

[0170] Action: Fill out the feedback form again and click the "Submit" button.

[0171] Output: New feedback is sent to the terminal and processing begins again.

[0172] (Application example 1)

[0173] 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."

[0174] Modern marketing campaigns require the rapid and effective incorporation of customer feedback to optimize the campaign. However, with conventional systems, the collection, analysis, generation, and presentation of feedback improvements were separated, making it impossible to integrate these processes. Furthermore, it was difficult to propose products and improvements tailored to individual customer needs, resulting in insufficient improvement of customer satisfaction.

[0175] 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.

[0176] In this invention, the server includes means for receiving feedback and requests from customers, means for storing the received feedback and requests in a database, means for analyzing the stored feedback and requests using natural language processing, means for generating improvement measures and policies based on the analysis results, means for visually presenting the generated improvement measures and policies to customers, and means for improving a recommendation algorithm based on feedback and making optimal product proposals for individual customers. This makes it possible to efficiently incorporate customer feedback and make personalized product proposals, thereby optimizing marketing campaigns and improving customer satisfaction.

[0177] "Customer Feedback" is input from customers providing their experiences, opinions, and requests.

[0178] A "database" is a computer system that systematically stores and manages information such as feedback and requests received from customers.

[0179] "Natural language processing" is a technology that allows computers to analyze human language and understand its meaning.

[0180] "Improvements" are specific measures developed based on customer feedback to improve marketing campaigns or services.

[0181] "Visual presentation" is a means of displaying the generated improvement measures and initiatives to the customer in an easy-to-read format.

[0182] A "recommendation algorithm" is an algorithm that analyzes a customer's past behavior and feedback to suggest the best products and services for each individual customer.

[0183] "Product suggestion" is an action that recommends products that are considered to be best suited to individual customers based on customer feedback and behavioral data.

[0184] This invention is realized using a smartphone application called a “Personalized Shopping Assistant.” A detailed embodiment of this system will be described below.

[0185] A customer (user) starts the app on their smartphone and enters their opinions and requests into the feedback form. For example, they might enter feedback such as "There are too few items on sale recently." The device then sends this input to the server.

[0186] The server stores the received feedback in a database, which serves to store and manage customer feedback in an organized manner.

[0187] The server then inputs the saved feedback into a natural language processing (NLP) engine and analyzes its content. For analysis, existing NLP engines such as Google Cloud Natural Language API and Amazon Comprehend are used. As a result of the analysis, sentiment ratings and topics of the feedback are extracted. For example, a sentiment rating of "visually unappealing" is obtained.

[0188] Based on the analysis results, the server generates improvement measures for the marketing campaign. Specific improvement measures are proposed using a generative AI model. For example, the generated improvement measures might be to "increase the number of products on sale and introduce new discount sets."

[0189] The server then sends the generated improvement plan to the terminal, which visually displays the received improvement plan to the customer. For example, it may display, "In the next sale, we will expand the range of eligible products and introduce a new discount set."

[0190] Furthermore, the server uses the feedback to improve its recommendation algorithm and make optimal product suggestions for each individual customer, such as "The following products are recommended for you."

[0191] This will enable efficient incorporation of customer feedback and personalized product recommendations, optimizing marketing campaigns and improving customer satisfaction.

[0192] Examples of concrete examples and prompts

[0193] As a concrete example, imagine a user who opens the smartphone app "Personalized Shopping Assistant" enters "There are too few recent sale items" into the feedback form. This feedback is sent to the server and analyzed by Amazon Comprehend. Based on the analysis results, the user is given a specific improvement suggestion, such as "In the next sale, expand the range of eligible products and introduce a new discount set."

[0194] Example prompt sentence:

[0195] Please analyze the following feedback statement and suggest improvements:

[0196] Feedback: "There are too few sale items these days."

[0197] These prompts enable the generative AI model to provide further actionable insights and recommendations for improvement, leading to improved customer satisfaction and effective optimization of marketing campaigns.

[0198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0199] Step 1:

[0200] A user launches the app on their smartphone. The user enters their opinions and requests into the feedback form. For example, the user might enter feedback such as "There are too few items on sale recently." The input data is in the form of a string, and the device sends this data to the server.

[0201] Step 2:

[0202] The device sends the feedback entered by the user to the server. This data transfer uses the HTTPS protocol, and the sent data is in JSON format. The server stores the received feedback in a database. When saving, the user's identification information is also saved.

[0203] Step 3:

[0204] The server inputs the saved feedback into a natural language processing engine (e.g., Google Cloud Natural Language API or Amazon Comprehend) and analyzes its content. The main task of the analysis is to evaluate the sentiment of the text data and extract topics. For example, the topic "visually unattractive" and its sentiment evaluation are obtained.

[0205] Step 4:

[0206] The server generates improvement measures for the marketing campaign based on the analysis results from the natural language processing engine. For example, the generated improvement measures might be to "increase the number of products on sale and introduce new discount sets." The natural language generation model used here is a generative AI model. It inputs a prompt sentence and outputs specific improvement measures.

[0207] Step 5:

[0208] The server sends the generated improvement measures to the terminal. The terminal visually displays the received improvement measures to the user. For example, it may display "In the next sale, we will expand the range of eligible products and introduce a new discount set." The display format is a visually easy-to-understand UI design, and a user interface framework (e.g., React Native) is used.

[0209] Step 6:

[0210] The server improves the recommendation algorithm based on the feedback and makes optimal product suggestions for each individual customer. In this process, past feedback data and behavioral data are integrated and the improved recommendation algorithm is applied. For example, the server may make suggestions to the user such as, "The following products are recommended for you." This allows the optimal product list to be updated in real time, enabling personalized product suggestions.

[0211] Through these steps, it becomes possible to effectively incorporate user feedback and provide personalized product recommendations, optimizing marketing campaigns and improving customer satisfaction.

[0212] 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.

[0213] The present invention relates to a marketing campaign optimization system that collects feedback and requests from customers, analyzes the collected feedback and requests, generates improvements to the marketing campaign, and presents them to the customers. The present invention further incorporates an emotion engine that recognizes the emotions in the customer feedback and requests. Specific embodiments for implementing the present invention will be described below.

[0214] Program processing and behavior

[0215] 1. Collect customer feedback

[0216] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[0217] Terminal: Receives user feedback and sends feedback data to the server.

[0218] 2. Saving your feedback to a database

[0219] Server: Stores the received feedback in a database. The stored data includes the feedback content as well as the user's identification information.

[0220] 3. Analysis using natural language processing and sentiment engines

[0221] Server: Starts parsing the stored feedback data using a natural language processing (NLP) engine, for example using an NLP library such as TextBlob or spaCy.

[0222] Server: Analyzes the feedback content using NLP and extracts key topics and sentiments, for example, "visually unappealing."

[0223] Server: The emotion engine recognizes emotional elements in the feedback. For example, it detects the emotion "dissatisfied."

[0224] 4. Generate improvement measures and reflect sentiment data

[0225] Server: Based on the analysis results of NLP and the emotion engine, it generates specific improvement measures that take into account customer requests and emotions. For example, it suggests improvement measures such as "add product photos to new product introduction articles and emphasize their benefits with bullet points" and "use designs that evoke positive emotions."

[0226] 5. Providing improvement measures to users

[0227] Server: Sends the generated remediation measures to the device.

[0228] On-device: Display the received improvement recommendations in a user-friendly format, such as "In your next new product introduction article, we recommend using more product photos and emphasizing the benefits. Also, consider creating a design that evokes positive emotions."

[0229] 6. Re-feedback

[0230] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[0231] Specific examples

[0232] Example 1: Improving a new product introduction campaign

[0233] 1. User: Enters feedback on the campaign site saying, "The article introducing the new product is not very appealing."

[0234] 2. Device: Sends feedback to the server.

[0235] 3. Server: The received feedback is stored in a database, and the natural language processing engine analyzes whether the feedback is visually unattractive, and the emotion engine recognizes the emotion of "dissatisfaction."

[0236] 4. Server: Generate the following improvements: "Add product photos to new product introduction articles to highlight their benefits" and "Use designs that elicit positive emotions."

[0237] 5. Server: Sends the improvement plan to the device.

[0238] 6. Device: Suggest to users, "In your next product launch article, we recommend using more product photos and highlighting the benefits. Also, consider creating a design that evokes positive emotions."

[0239] Example 2: Improving a sales campaign

[0240] 1. User: Enters feedback on the online store saying, "There are not many products on sale and it's not appealing."

[0241] 2. Device: Sends feedback to the server.

[0242] 3. Server: The feedback is stored in a database, the natural language processing engine analyzes that there are few eligible products, and the emotion engine recognizes the emotion of "disappointment."

[0243] 4. Server: Generates the following improvement measures: "Increase the number of items on sale and introduce bundle discounts" and "Add rewards that elicit positive emotions."

[0244] 5. Server: Sends the improvement plan to the device.

[0245] 6. Device: Suggest to the user, "For your next sale, we recommend expanding the selection and introducing bundled discounts. Also, add rewards that evoke positive emotions."

[0246] In this way, the present invention can efficiently collect and analyze customer feedback to generate specific improvement measures, and by taking customer sentiment into account, can realize more effective improvements to marketing campaigns, thereby increasing customer satisfaction and engagement and maximizing the results of marketing campaigns.

[0247] The processing flow will be explained below.

[0248] Step 1:

[0249] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[0250] Step 2:

[0251] Terminal: Receives user feedback and sends feedback data to the server.

[0252] Step 3:

[0253] Server: Receives feedback sent from the device and stores the feedback and user identification information in a database.

[0254] Step 4:

[0255] Server: Starts analyzing the stored feedback data using a natural language processing (NLP) engine. For example, it uses an NLP library such as TextBlob or spaCy to analyze the feedback content.

[0256] Step 5:

[0257] Server: Analyzes the feedback content using natural language processing and extracts key topics and sentiments. For example, the analysis results "visually unappealing."

[0258] Step 6:

[0259] Server: Uses an emotion engine to recognize emotional elements in the feedback. For example, it detects the emotion "dissatisfied."

[0260] Step 7:

[0261] Server: Based on the results of natural language processing and emotion engine analysis, the server generates specific improvement measures that take into account customer requests and emotions. For example, it suggests an improvement such as "adding product photos to new product introduction articles and emphasizing their benefits in bullet points."

[0262] Step 8:

[0263] Server: Conducts trend analysis and integrates multiple feedback data to identify common issues, allowing for adjustments to be made to overall improvements.

[0264] Step 9:

[0265] Server: Adjusts the improvement plan and develops the optimal improvement plan that takes into account the sentiment data. For example, add a suggestion such as "Use designs that elicit positive emotions."

[0266] Step 10:

[0267] Server: Sends the generated final remediation to the device.

[0268] Step 11:

[0269] On device: Display the received improvement recommendations in a user-friendly format, such as "In your next product launch article, please consider using more product photos, explaining benefits in bullet points, and using a design that evokes positive emotions."

[0270] Step 12:

[0271] User: Re-enter the suggested improvement with additional feedback or new requests, such as "I'll try that strategy in my next post."

[0272] Step 13:

[0273] Device: Receive feedback again and send it to the server.

[0274] Step 14:

[0275] Server: Again, the received feedback is stored in a database and the process from step 3 to step 13 above is repeated to continuously improve the campaign.

[0276] Example 2

[0277] 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."

[0278] Modern marketing campaigns require the rapid and effective collection of customer feedback, accurate analysis of that feedback, and the development of improvement measures. Furthermore, by taking into account customer emotional factors, it is necessary to propose more accurate improvement measures and increase customer satisfaction. However, with conventional systems, the process from collecting feedback to analyzing it and proposing improvement measures relies on manual work, which takes a great deal of time and effort and is hardly efficient.

[0279] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving feedback and requests from customers, a means for storing the received feedback and requests in a database, a means for analyzing the stored feedback and requests using natural language processing, a means for recognizing emotions in the feedback and requests, a means for generating improvement measures based on the analysis results of the natural language processing and emotion recognition, and a means for visually presenting the generated improvement measures. This makes it possible to automate the process from collecting feedback to analyzing it and presenting improvement measures, thereby realizing efficient and effective optimization of marketing campaigns that also take customer emotions into consideration.

[0280] "Feedback" refers to opinions, requests, and evaluations provided by customers.

[0281] A "request" is a proposal for an improvement, new feature, or service that a customer wants for a particular product or service.

[0282] "Means" refers to a method, device, or process for achieving a specific purpose.

[0283] A "database" is a system for efficiently storing, managing, and retrieving data.

[0284] "Natural language processing" is a technology that allows computers to understand human language and analyze text.

[0285] "Emotion recognition" is a technology that detects and classifies emotional states from data such as text and voice.

[0286] "Analysis results" refers to the insights and information obtained after analyzing data.

[0287] "Improvements" are specific actions or methods proposed to resolve existing problems.

[0288] "Visually presenting" means displaying information in a format that is easy for the user to view.

[0289] A "marketing campaign" is a series of activities designed to promote a particular product or service.

[0290] The present invention relates to a marketing campaign optimization system that collects customer feedback and requests, analyzes them, and generates improvements to the marketing campaign. The system incorporates an emotion engine that recognizes the emotions in the feedback and requests. Specific embodiments for implementing the present invention will be described below.

[0291] System Configuration

[0292] Hardware and Software Configuration

[0293] Users: Enter feedback using a computer, mobile device, or other device.

[0294] Device: Receives user feedback and sends it to the server. Software used includes a web browser and dedicated applications.

[0295] Server: Receives feedback data and stores it in a database. Python scripts are used for data analysis, and libraries such as TextBlob and spaCy are used for natural language processing (NLP). A dedicated emotion recognition engine is used for sentiment analysis.

[0296] Data processing and calculation

[0297] Collecting and storing feedback

[0298] User: Enter feedback or requests about the campaign into the terminal. For example, enter feedback such as "The article introducing the new product is not very appealing."

[0299] Terminal: Receives feedback from the user, stores it temporarily, and then sends the feedback data to the server using an HTTP POST request.

[0300] Feedback Analysis

[0301] Server: Stores the received feedback data in a database and runs an analysis engine. Specifically, it uses a natural language processing engine to analyze the text and extract key topics and sentiment. It uses NLP libraries such as TextBlob and spaCy.

[0302] Server: Uses an emotion recognition engine to identify emotional elements in the feedback, for example, detecting emotions such as "dissatisfaction" or "disappointment."

[0303] Generate improvements

[0304] Server: Based on the analysis results, a generative AI model is used to generate specific improvement measures, such as GPT-3.

[0305] Server: Enters the prompt "The user is dissatisfied with the new product introduction article. Please suggest improvements," and obtains improvements from the generative AI model.

[0306] Proposal of improvement measures

[0307] Server: Sends the generated remediation measures to the device.

[0308] On the device: Visually present the received improvement recommendations through the user interface, for example, by displaying a message such as, "In your next new product introduction article, we recommend that you use more product photos and emphasize the benefits. Also, consider a design that evokes positive emotions."

[0309] Handling re-feedback

[0310] Users: Enter additional feedback or new requests based on the proposed improvements, creating a feedback loop that allows for continuous campaign improvement.

[0311] Specific examples

[0312] Example 1: Improving a new product introduction campaign

[0313] 1. User: Enters feedback saying, "The new product introduction article isn't very appealing."

[0314] 2. Device: Sends feedback to the server.

[0315] 3. Server: Stores the received feedback in a database and analyzes it using a natural language processing engine and emotion recognition engine.

[0316] 4. Server: Generate the following improvements: "Add product photos to new product introduction articles to highlight their benefits" and "Use designs that elicit positive emotions."

[0317] 5. Server: Sends the remediation plan to the device.

[0318] 6. Device: Suggest to users, "In your next product launch article, we recommend using more product photos and highlighting the benefits. Also, consider creating a design that evokes positive emotions."

[0319] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0320] Step 1: Gather feedback

[0321] User: Enter feedback or requests about the campaign into the terminal. For example, enter feedback such as "The article introducing the new product is not very appealing."

[0322] Input: The feedback text entered by the user.

[0323] Output: Feedback data.

[0324] On the device: Receive feedback from the user, temporarily store it, and then send the feedback data to the server using an HTTP POST request.

[0325] Step 2: Store feedback in a database

[0326] Server: Receives received feedback data and generates a log entry acknowledging receipt.

[0327] Input: Feedback data sent from the device.

[0328] Output: Feedback data stored in a database.

[0329] Server: The feedback data is saved in the database using the INSERT statement. The data saved in the database also includes the user's identification information.

[0330] Step 3: Analyze the feedback data

[0331] Server: Retrieves new feedback entries in the database and triggers the Natural Language Processing (NLP) engine using a Python script and TextBlob and spaCy as NLP libraries.

[0332] Input: Feedback data retrieved from the database.

[0333] Output: Analysis results (major topics and sentiment).

[0334] What it does: The NLP engine analyzes the feedback text and extracts key topics. The emotion recognition engine is used to recognize the emotional components of the feedback (e.g., "dissatisfied").

[0335] Step 4: Generate remediation measures

[0336] Server: Based on the analysis results of the NLP and emotion recognition engine, a generative AI model (e.g., GPT-3) is used to generate specific improvement measures.

[0337] Input: Analysis results (major topics and sentiment).

[0338] Output: Remedies.

[0339] Specific behavior: The prompt sentence "The user is dissatisfied with the new product introduction article. Please suggest improvements" is input into the generative AI model to generate improvements. For example, a specific improvement suggestion is obtained: "Add product photos to the new product introduction article and highlight its benefits."

[0340] Step 5: Submit and present your remediation plan

[0341] Server: Sends the generated remediation to the device using an HTTP POST request.

[0342] Input: The generated remediation measures.

[0343] Output: Submitted remediation.

[0344] Device: Visually present the received improvement recommendations through the user interface. For example, display a message such as, "In your next new product introduction article, we recommend using more product photos and emphasizing the benefits. Also, consider designing it to evoke positive emotions."

[0345] Step 6: Processing re-feedback

[0346] Users: Re-enter any additional feedback or new requests for the proposed improvements.

[0347] Input: Any additional feedback entered by the user.

[0348] Output: The collected feedback data again.

[0349] What it does: The re-entered feedback data is then sent back to the server by the device, and the feedback collection and storage process is repeated, creating a feedback loop that allows for continuous campaign improvement.

[0350] (Application example 2)

[0351] 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."

[0352] In conventional marketing campaign optimization systems, analysis and improvement plan generation based on collected customer feedback was often done manually, resulting in a waste of time and effort. Furthermore, the system for properly reflecting customer sentiment was inadequate, making it difficult to improve customer satisfaction. Furthermore, there was no established method for efficiently collecting and presenting feedback using smart devices.

[0353] 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.

[0354] In this invention, the server includes means for receiving feedback and requests from customers, means for storing the received feedback and requests in a database, means for analyzing the stored feedback and requests using natural language processing, means for generating improvement measures and policies based on the analysis results, means for visually presenting the generated improvement measures and policies to customers, and means for efficiently collecting and presenting feedback from customers using a smart device. This automates the collection and analysis of feedback, making it possible to quickly generate and present specific improvement measures that take customer sentiment into consideration.

[0355] "Customer" refers to a person who uses a service or purchases a product.

[0356] "Feedback" refers to opinions and ratings provided by customers regarding services and products.

[0357] "Requests" refer to improvements or additional features that customers expect from a particular service or product.

[0358] "Database" refers to a system for systematically storing and managing collected feedback and requests.

[0359] "Natural language processing" refers to the technology of understanding and analyzing feedback and requests as human language.

[0360] "Improvement measures" refer to specific measures to improve services or products based on feedback and requests.

[0361] "Visually presenting" refers to displaying the generated improvement measures and initiatives in a way that is easy for customers to see.

[0362] "Smart devices" refers to devices with internet connectivity, such as smartphones, smart glasses, and head-mounted displays.

[0363] "Collection" refers to the act of gathering feedback and requests from customers.

[0364] "Presenting" refers to the act of displaying the collected information and generated improvement measures to the user.

[0365] To implement the present invention, the following steps are followed to implement a program using the specified hardware and software.

[0366] 1. System Configuration

[0367] Customers use their smartphones to enter feedback and requests about products and services.

[0368] This feedback is sent by the terminal to the server.

[0369] The server stores the received feedback in a database and then analyzes the stored data using a natural language processing (NLP) engine, spaCy, and TextBlob for sentiment analysis.

[0370] The server generates improvement measures and policies based on the analysis results of the NLP and emotion engine. This involves extracting key topics and emotions and generating specific improvement proposals based on them.

[0371] The server transmits the generated remedial measures back to the terminal, which visually displays the remedial measures to the customer.

[0372] 2. Program Implementation

[0373] Use smart devices to efficiently gather feedback from users and suggest improvements.

[0374] After receiving the feedback, it sends it to the server, where the data is stored in a database.

[0375] The feedback stored in the database is analyzed using an NLP engine (spaCy) and an emotion engine (TextBlob) to extract key topics and emotions.

[0376] Based on the extracted analysis results, logic is implemented on the server to generate improvement measures corresponding to specific keywords and emotions.

[0377] An interface is constructed on the terminal side to visually present the final generated improvement measures to the user.

[0378] Hardware and software used

[0379] Smartphone device: Used to enter feedback and view improvements.

[0380] Server: Stores and analyzes feedback and generates improvement measures.

[0381] Database: Used to store feedback and analysis results.

[0382] Natural language processing engine: spaCy is used to analyze feedback topics.

[0383] Sentiment Analysis Engine: Uses TextBlob to analyze the sentiment of feedback.

[0384] Specific examples

[0385] When the user inputs feedback such as "the product description is insufficient," the terminal transmits the feedback to the server.

[0386] The server stores the received feedback in a database and then parses the feedback using spaCy and TextBlob.

[0387] As a result of the analysis, the topic of "insufficient description" and negative sentiment are extracted, and an improvement measure of "adding a detailed description of the product" is generated.

[0388] The generated improvement measures are sent to the terminal and visually displayed to the user in the form of "Please add product description."

[0389] Prompt Sentence Examples

[0390] You received feedback from users that the product page was difficult to navigate and lacked information. Based on this feedback, please analyze it using an NLP engine and a sentiment engine, and suggest specific improvements based on the resulting keywords and sentiment.

[0391] As described above, the present invention is capable of efficiently collecting and analyzing feedback from customers to generate specific improvement measures and visually presenting them in a form that takes into account the customer's feelings.

[0392] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0393] Step 1:

[0394] Users use their smartphones to input feedback and requests about products and services. The input feedback data (e.g., "The product description is insufficient") is saved on the device.

[0395] Step 2:

[0396] The terminal sends the input feedback data to the server. At this time, the feedback content and the user's identification information are included in the transmitted data. The feedback data is transferred to the server via an HTTP request.

[0397] Step 3:

[0398] The server stores the received feedback data in a database. The stored data includes the feedback content and user identification information. The database stores the feedback text, user ID, timestamp, etc.

[0399] Step 4:

[0400] The server starts natural language processing (NLP) on the stored feedback data. It uses spaCy as its NLP engine to extract the main topics of the feedback. The input is the feedback text, and the output is a list of extracted keywords. Specifically, it tokenizes the text and extracts noun phrases.

[0401] Step 5:

[0402] The server uses a sentiment analysis engine (TextBlob) to analyze the sentiment of the feedback. The input is the feedback text and the output is a sentiment score (positive, negative, neutral). The TextBlob is used to process the sentiment polarity of the text.

[0403] Step 6:

[0404] The server generates improvement measures based on the results of NLP and sentiment analysis. The input is the extracted keywords and sentiment scores, and the output is a list of specific improvement measures. Specifically, it selects and generates appropriate improvement measures from a pre-defined list of improvement candidate measures.

[0405] Step 7:

[0406] The server sends the generated remediation plan to the terminal, along with details of the remediation plan as an HTTP response. The output includes specific suggestions for the customer.

[0407] Step 8:

[0408] The device visually displays the received improvement measures to the user, using pop-up messages, notification banners, etc. Specifically, the device displays the improvement measures on the user interface based on the received data.

[0409] Step 9:

[0410] Users can then provide additional feedback and suggestions for the proposed improvements, creating a feedback loop that continually refines the actual campaign.

[0411] Through the above steps, the present invention can effectively collect and analyze customer feedback, and generate and present specific improvement measures.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] [Second embodiment]

[0416] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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).

[0422] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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."

[0428] The present invention relates to a marketing campaign optimization system that collects feedback and requests from customers, analyzes the feedback and requests, generates improvements to the marketing campaign, and presents them to the customers. Specific embodiments for carrying out the present invention will be described below.

[0429] Program processing and behavior

[0430] 1. Collect customer feedback

[0431] User: Uses a device to enter feedback or requests about the campaign, for example, "The new product introduction article is not very appealing."

[0432] Terminal: Sends the feedback entered by the user to the server.

[0433] 2. Saving your feedback to a database

[0434] Server: Stores the received feedback in a database. The stored data includes the feedback content as well as the user's identification information.

[0435] 3. Analysis using natural language processing

[0436] Server: The stored feedback is fed into a natural language processing engine for content analysis, including sentiment assessment and topic extraction.

[0437] Server: As a result of the analysis, for example, from feedback that "the article introducing a new product is not appealing," the insight that "visual enhancement is needed" is extracted.

[0438] 4. Generate improvements

[0439] Server: Generates recommendations for improving marketing campaigns based on the analysis results, such as "add visual elements to product articles and highlight product benefits with bullet points."

[0440] 5. Providing improvement measures to users

[0441] Server: Sends the generated remediation measures to the device.

[0442] On the device: Display the received improvement recommendations in a user-friendly format, for example, "In your next product launch article, we recommend using more product photos to highlight the benefits."

[0443] 6. Re-feedback

[0444] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[0445] Specific examples

[0446] Example 1: Improving a new product introduction campaign

[0447] 1. User: Enters feedback on the campaign site saying, "The article introducing the new product is not very appealing."

[0448] 2. Device: Sends feedback to the server.

[0449] 3. Server: Stores the received feedback in a database and analyzes the issue of "not visually appealing" using natural language processing.

[0450] 4. Server: Generate an improvement plan: "Add product photos to new product introduction articles to highlight their benefits."

[0451] 5. Server: Sends the improvement plan to the device.

[0452] 6. Device: Suggest to the user, "In your next product launch article, add visuals and explain the benefits in bullet points."

[0453] Example 2: Improving a sales campaign

[0454] 1. User: Enters feedback on the online store saying, "There are not many products on sale and it's not appealing."

[0455] 2. Device: Sends feedback to the server.

[0456] 3. Server: Stores the feedback in a database and analyzes the problem of "not enough products available" using natural language processing.

[0457] 4. Server: Generate an improvement plan: "Increase the number of items on sale and introduce bundle discounts."

[0458] 5. Server: Sends the improvement plan to the device.

[0459] 6. Device: Propose to the user that "In the next sale, we will increase the number of eligible products and introduce set discounts."

[0460] In this way, the present invention can efficiently collect customer feedback, quickly analyze it, generate specific improvement measures, and present them to customers, thereby maximizing the effectiveness of marketing campaigns and increasing customer satisfaction and engagement.

[0461] The processing flow will be explained below.

[0462] Step 1:

[0463] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[0464] Step 2:

[0465] Terminal: Receives user feedback and sends feedback data to the server.

[0466] Step 3:

[0467] Server: Receives feedback sent from the device and stores it in a database, including user identification information.

[0468] Step 4:

[0469] Server: Starts parsing the stored feedback data using a natural language processing (NLP) engine, for example using an NLP library such as TextBlob or spaCy.

[0470] Step 5:

[0471] Server: Analyzes the feedback using natural language processing to extract key topics and sentiments, for example, obtaining results such as "visually unappealing."

[0472] Step 6:

[0473] Server: Identify customer requests based on the analysis results. For example, extract a request such as "New product introduction articles need visual enhancements."

[0474] Step 7:

[0475] Server: Review data from other users with similar feedback and perform trend analysis to identify common issues.

[0476] Step 8:

[0477] Server: Generates specific improvements and measures for marketing campaigns based on trend analysis results, such as adding product photos to new product introduction articles and highlighting their benefits in bullet points.

[0478] Step 9:

[0479] Server: Sends the generated remediation measures to the device.

[0480] Step 10:

[0481] On the device: Display the improvement suggestions to the user and present them in an easy-to-understand format, such as "In your next product launch article, we recommend using more product photos to highlight the benefits."

[0482] Step 11:

[0483] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[0484] Example 1

[0485] 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."

[0486] Conventional marketing campaign optimization systems have difficulty efficiently analyzing customer feedback and quickly proposing specific improvement measures. Furthermore, it is difficult to continuously and dynamically incorporate feedback, which results in insufficient improvement of customer satisfaction and engagement. Furthermore, the generated improvement measures are often not specific and not feasible.

[0487] 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.

[0488] In this invention, the server includes a means for receiving feedback and requests from customers, a means for storing the received feedback and requests in an information repository, a means for analyzing the stored feedback and requests using natural language processing, a means for generating improvement measures and policies based on the analysis results using a generative AI model, and a means for visually presenting the generated improvement measures and policies to customers. This makes it possible to efficiently collect and analyze customer feedback and quickly provide specific, actionable improvement measures. Furthermore, by forming a continuous feedback loop, the effectiveness of marketing campaigns can be maximized and customer satisfaction and engagement can be improved.

[0489] "Feedback" refers to information such as opinions, requests, and evaluations provided by customers.

[0490] "Requests" are requests for improvements or new features that customers expect from services or products.

[0491] An "information repository" is a system for storing and managing data, such as a database or storage system.

[0492] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0493] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to automatically generate new data or suggestions.

[0494] "Improvements" are specific proposals and measures to improve existing systems and campaigns.

[0495] "Measures" are specific actions or strategies planned to achieve business goals.

[0496] "Visual presentation" means displaying information on a screen or display in a format that is easy for the user to understand.

[0497] The present invention relates to a marketing campaign optimization system that collects and analyzes feedback and requests from customers, generates improvements to the marketing campaign based on the collected feedback, and presents the improvements to the customers. Specific embodiments for carrying out the present invention will be described below.

[0498] This system mainly consists of a server, terminals, and users. The specific roles and processes of each component are shown below.

[0499] Gathering feedback

[0500] Users can use their devices to input their feedback and requests about the campaign. The device interface can be a web form, a mobile application, etc. For example, a user might input, "The article introducing the new product is not very appealing."

[0501] The terminal receives the feedback information input by the user, generates an HTTP POST request, and sends it to the server.

[0502] Feedback storage and analysis

[0503] The server stores the feedback received from the terminal in a database (information collection), and the stored data includes the feedback content, user identification information, and a timestamp.

[0504] The stored feedback data is analyzed using a natural language processing (NLP) engine (e.g., Microsoft Azure Cognitive Services text analysis API or Google Cloud Natural Language API). The server sends the feedback data to these external APIs and receives the analysis results.

[0505] As a result of the analysis, the main topics and emotional evaluations of the feedback are extracted. For example, from feedback that "the new product introduction article is not appealing," the insight that "visual appeal needs to be improved" can be obtained.

[0506] Generate improvements

[0507] The server generates specific marketing campaign improvement measures using a generative AI model (e.g., a general natural language generation model) based on the analysis results of natural language processing. For example, improvement measures such as "add visual elements to product introduction articles and emphasize the product's benefits in bullet points" are generated.

[0508] The generated improvements are formatted in a way that is easy for the user to understand.

[0509] Providing improvement measures and providing feedback

[0510] The server sends the generated remediation measures to the terminal as an HTTP response.

[0511] The device converts the received improvements into a display data structure and displays it in the UI of a web page or application, for example, "In our next new product introduction article, we'll add visual elements and explain the benefits in bullet points."

[0512] Users can then provide additional feedback or new suggestions for improvements, creating a feedback loop that allows for continuous improvement of the campaign.

[0513] Examples of prompt statements

[0514] Prompt 1: "How would you generate improvements based on customer feedback about a new product introduction article that they found less appealing?"

[0515] Prompt 2: "Explain how to generate optimal improvements based on customer feedback that feels there are not enough products in a sales campaign."

[0516] The above is a specific embodiment of the present invention. This system efficiently collects and analyzes customer feedback and can quickly provide specific and actionable improvement measures, thereby maximizing the effectiveness of marketing campaigns and improving customer satisfaction.

[0517] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0518] Step 1: Gather feedback

[0519] The user uses the terminal to input feedback and requests about the campaign, for example, "The article introducing the new product is not very appealing."

[0520] Input: Feedback text (e.g., "The new product introduction article is not very appealing.")

[0521] Action: Enter your feedback through a device interface (e.g., a web form or a mobile application) and click the "Submit" button.

[0522] Output: User feedback is sent to the device.

[0523] Step 2: Submit your feedback

[0524] The terminal receives the feedback information input by the user, generates an HTTP POST request, and sends it to the server.

[0525] Input: The feedback text entered by the user

[0526] What it does: Creates an HTTP POST request and sends it to the server with the feedback information.

[0527] Output: The feedback information is sent to the server.

[0528] Step 3: Save your feedback

[0529] The server stores the feedback received from the terminal in a database, and the stored data includes the feedback content, user identification information, and a timestamp.

[0530] Input: Feedback information sent from the device

[0531] What it does: Parses the feedback information and executes an insert query to the database to save the data.

[0532] Output: The feedback information is stored in a database.

[0533] Step 4: Analyze the feedback

[0534] The server then inputs the stored feedback data into a natural language processing (NLP) engine to analyze the content, for example, using the Microsoft Azure Cognitive Services text analysis API or the Google Cloud Natural Language API.

[0535] Input: Feedback information stored in the database

[0536] How it works: Sends feedback data to a natural language processing API and receives analysis results.

[0537] Output: Analysis results such as main topics of feedback and sentiment ratings

[0538] Step 5: Extracting insights

[0539] The server extracts key topics and insights from the feedback based on the results of natural language processing analysis. For example, from feedback such as "The article introducing a new product is not appealing," it can obtain the insight that "The visual appeal needs to be improved."

[0540] Input: Analysis results of natural language processing

[0541] What it does: Extract topics and insights from the analysis results and store them in a database.

[0542] Output: Insights and topic information

[0543] Step 6: Generate remediation measures

[0544] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate specific marketing campaign improvement measures.

[0545] Input: Insights and topic information

[0546] How it works: Input insight data into a generative AI model and get output improvement measures.

[0547] Output: Specific improvement suggestions (e.g., "Add visual elements to product articles and highlight product benefits with bullet points")

[0548] Step 7: Propose improvement measures

[0549] The server transmits the generated remedial measures to the terminal.

[0550] Input: Improvements generated by a generative AI model

[0551] Behavior: Remediation data is sent to the device as an HTTP response.

[0552] Output: Remediation data is sent to the terminal.

[0553] The device converts the received remedial measures into a display data structure and displays them on a web page or application UI.

[0554] Input: Remediation data sent from the server

[0555] How it works: Received data is bound to HTML and application UI components and displayed on the screen.

[0556] Output: The remediation measures are displayed in a format that the user can understand visually.

[0557] Step 8: Re-feedback

[0558] Users can then provide additional feedback or new requests for the proposed improvements, creating a feedback loop that allows for continuous improvement of the campaign.

[0559] Input: Feedback on the improvement plan (e.g., "I agree with the improvement plan" or "I would like to add another request")

[0560] Action: Fill out the feedback form again and click the "Submit" button.

[0561] Output: New feedback is sent to the terminal and processing begins again.

[0562] (Application example 1)

[0563] 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."

[0564] Modern marketing campaigns require the rapid and effective incorporation of customer feedback to optimize the campaign. However, with conventional systems, the collection, analysis, generation, and presentation of feedback improvements were separated, making it impossible to integrate these processes. Furthermore, it was difficult to propose products and improvements tailored to individual customer needs, resulting in insufficient improvement of customer satisfaction.

[0565] 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.

[0566] In this invention, the server includes means for receiving feedback and requests from customers, means for storing the received feedback and requests in a database, means for analyzing the stored feedback and requests using natural language processing, means for generating improvement measures and policies based on the analysis results, means for visually presenting the generated improvement measures and policies to customers, and means for improving a recommendation algorithm based on feedback and making optimal product proposals for individual customers. This makes it possible to efficiently incorporate customer feedback and make personalized product proposals, thereby optimizing marketing campaigns and improving customer satisfaction.

[0567] "Customer Feedback" is input from customers providing their experiences, opinions, and requests.

[0568] A "database" is a computer system that systematically stores and manages information such as feedback and requests received from customers.

[0569] "Natural language processing" is a technology that allows computers to analyze human language and understand its meaning.

[0570] "Improvements" are specific measures developed based on customer feedback to improve marketing campaigns or services.

[0571] "Visual presentation" is a means of displaying the generated improvement measures and initiatives to the customer in an easy-to-read format.

[0572] A "recommendation algorithm" is an algorithm that analyzes a customer's past behavior and feedback to suggest the best products and services for each individual customer.

[0573] "Product suggestion" is an action that recommends products that are considered to be best suited to individual customers based on customer feedback and behavioral data.

[0574] This invention is realized using a smartphone application called a “Personalized Shopping Assistant.” A detailed embodiment of this system will be described below.

[0575] A customer (user) starts the app on their smartphone and enters their opinions and requests into the feedback form. For example, they might enter feedback such as "There are too few items on sale recently." The device then sends this input to the server.

[0576] The server stores the received feedback in a database, which serves to store and manage customer feedback in an organized manner.

[0577] The server then inputs the saved feedback into a natural language processing (NLP) engine and analyzes its content. For analysis, existing NLP engines such as Google Cloud Natural Language API and Amazon Comprehend are used. As a result of the analysis, sentiment ratings and topics of the feedback are extracted. For example, a sentiment rating of "visually unappealing" is obtained.

[0578] Based on the analysis results, the server generates improvement measures for the marketing campaign. Specific improvement measures are proposed using a generative AI model. For example, the generated improvement measures might be to "increase the number of products on sale and introduce new discount sets."

[0579] The server then sends the generated improvement plan to the terminal, which visually displays the received improvement plan to the customer. For example, it may display, "In the next sale, we will expand the range of eligible products and introduce a new discount set."

[0580] Furthermore, the server uses the feedback to improve its recommendation algorithm and make optimal product suggestions for each individual customer, such as "The following products are recommended for you."

[0581] This will enable efficient incorporation of customer feedback and personalized product recommendations, optimizing marketing campaigns and improving customer satisfaction.

[0582] Examples of concrete examples and prompts

[0583] As a concrete example, imagine a user who opens the smartphone app "Personalized Shopping Assistant" enters "There are too few recent sale items" into the feedback form. This feedback is sent to the server and analyzed by Amazon Comprehend. Based on the analysis results, the user is given a specific improvement suggestion, such as "In the next sale, expand the range of eligible products and introduce a new discount set."

[0584] Example prompt sentence:

[0585] Please analyze the following feedback statement and suggest improvements:

[0586] Feedback: "There are too few sale items these days."

[0587] These prompts enable the generative AI model to provide further actionable insights and recommendations for improvement, leading to improved customer satisfaction and effective optimization of marketing campaigns.

[0588] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0589] Step 1:

[0590] A user launches the app on their smartphone. The user enters their opinions and requests into the feedback form. For example, the user might enter feedback such as "There are too few items on sale recently." The input data is in the form of a string, and the device sends this data to the server.

[0591] Step 2:

[0592] The device sends the feedback entered by the user to the server. This data transfer uses the HTTPS protocol, and the sent data is in JSON format. The server stores the received feedback in a database. When saving, the user's identification information is also saved.

[0593] Step 3:

[0594] The server inputs the saved feedback into a natural language processing engine (e.g., Google Cloud Natural Language API or Amazon Comprehend) and analyzes its content. The main task of the analysis is to evaluate the sentiment of the text data and extract topics. For example, the topic "visually unattractive" and its sentiment evaluation are obtained.

[0595] Step 4:

[0596] The server generates improvement measures for the marketing campaign based on the analysis results from the natural language processing engine. For example, the generated improvement measures might be to "increase the number of products on sale and introduce new discount sets." The natural language generation model used here is a generative AI model. It inputs a prompt sentence and outputs specific improvement measures.

[0597] Step 5:

[0598] The server sends the generated improvement measures to the terminal. The terminal visually displays the received improvement measures to the user. For example, it may display "In the next sale, we will expand the range of eligible products and introduce a new discount set." The display format is a visually easy-to-understand UI design, and a user interface framework (e.g., React Native) is used.

[0599] Step 6:

[0600] The server improves the recommendation algorithm based on the feedback and makes optimal product suggestions for each individual customer. In this process, past feedback data and behavioral data are integrated and the improved recommendation algorithm is applied. For example, the server may make suggestions to the user such as, "The following products are recommended for you." This allows the optimal product list to be updated in real time, enabling personalized product suggestions.

[0601] Through these steps, it becomes possible to effectively incorporate user feedback and provide personalized product recommendations, optimizing marketing campaigns and improving customer satisfaction.

[0602] 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.

[0603] The present invention relates to a marketing campaign optimization system that collects feedback and requests from customers, analyzes the collected feedback and requests, generates improvements to the marketing campaign, and presents them to the customers. The present invention further incorporates an emotion engine that recognizes the emotions in the customer feedback and requests. Specific embodiments for implementing the present invention will be described below.

[0604] Program processing and behavior

[0605] 1. Collect customer feedback

[0606] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[0607] Terminal: Receives user feedback and sends feedback data to the server.

[0608] 2. Saving your feedback to a database

[0609] Server: Stores the received feedback in a database. The stored data includes the feedback content as well as the user's identification information.

[0610] 3. Analysis using natural language processing and sentiment engines

[0611] Server: Starts parsing the stored feedback data using a natural language processing (NLP) engine, for example using an NLP library such as TextBlob or spaCy.

[0612] Server: Analyzes the feedback content using NLP and extracts key topics and sentiments, for example, "visually unappealing."

[0613] Server: The emotion engine recognizes emotional elements in the feedback. For example, it detects the emotion "dissatisfied."

[0614] 4. Generate improvement measures and reflect sentiment data

[0615] Server: Based on the analysis results of NLP and the emotion engine, it generates specific improvement measures that take into account customer requests and emotions. For example, it suggests improvement measures such as "add product photos to new product introduction articles and emphasize their benefits with bullet points" and "use designs that evoke positive emotions."

[0616] 5. Providing improvement measures to users

[0617] Server: Sends the generated remediation measures to the device.

[0618] On-device: Display the received improvement recommendations in a user-friendly format, such as "In your next new product introduction article, we recommend using more product photos and emphasizing the benefits. Also, consider creating a design that evokes positive emotions."

[0619] 6. Re-feedback

[0620] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[0621] Specific examples

[0622] Example 1: Improving a new product introduction campaign

[0623] 1. User: Enters feedback on the campaign site saying, "The article introducing the new product is not very appealing."

[0624] 2. Device: Sends feedback to the server.

[0625] 3. Server: The received feedback is stored in a database, and the natural language processing engine analyzes whether the feedback is visually unattractive, and the emotion engine recognizes the emotion of "dissatisfaction."

[0626] 4. Server: Generate the following improvements: "Add product photos to new product introduction articles to highlight their benefits" and "Use designs that elicit positive emotions."

[0627] 5. Server: Sends the improvement plan to the device.

[0628] 6. Device: Suggest to users, "In your next product launch article, we recommend using more product photos and highlighting the benefits. Also, consider creating a design that evokes positive emotions."

[0629] Example 2: Improving a sales campaign

[0630] 1. User: Enters feedback on the online store saying, "There are not many products on sale and it's not appealing."

[0631] 2. Device: Sends feedback to the server.

[0632] 3. Server: The feedback is stored in a database, the natural language processing engine analyzes that there are few eligible products, and the emotion engine recognizes the emotion of "disappointment."

[0633] 4. Server: Generates the following improvement measures: "Increase the number of items on sale and introduce bundle discounts" and "Add rewards that elicit positive emotions."

[0634] 5. Server: Sends the improvement plan to the device.

[0635] 6. Device: Suggest to the user, "For your next sale, we recommend expanding the selection and introducing bundled discounts. Also, add rewards that evoke positive emotions."

[0636] In this way, the present invention can efficiently collect and analyze customer feedback to generate specific improvement measures, and by taking customer sentiment into account, can realize more effective improvements to marketing campaigns, thereby increasing customer satisfaction and engagement and maximizing the results of marketing campaigns.

[0637] The processing flow will be explained below.

[0638] Step 1:

[0639] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[0640] Step 2:

[0641] Terminal: Receives user feedback and sends feedback data to the server.

[0642] Step 3:

[0643] Server: Receives feedback sent from the device and stores the feedback and user identification information in a database.

[0644] Step 4:

[0645] Server: Starts analyzing the stored feedback data using a natural language processing (NLP) engine. For example, it uses an NLP library such as TextBlob or spaCy to analyze the feedback content.

[0646] Step 5:

[0647] Server: Analyzes the feedback content using natural language processing and extracts key topics and sentiments. For example, the analysis results "visually unappealing."

[0648] Step 6:

[0649] Server: Uses an emotion engine to recognize emotional elements in the feedback. For example, it detects the emotion "dissatisfied."

[0650] Step 7:

[0651] Server: Based on the results of natural language processing and emotion engine analysis, the server generates specific improvement measures that take into account customer requests and emotions. For example, it suggests an improvement such as "adding product photos to new product introduction articles and emphasizing their benefits in bullet points."

[0652] Step 8:

[0653] Server: Conducts trend analysis and integrates multiple feedback data to identify common issues, allowing for adjustments to be made to overall improvements.

[0654] Step 9:

[0655] Server: Adjusts the improvement plan and develops the optimal improvement plan that takes into account the sentiment data. For example, add a suggestion such as "Use designs that elicit positive emotions."

[0656] Step 10:

[0657] Server: Sends the generated final remediation to the device.

[0658] Step 11:

[0659] On device: Display the received improvement recommendations in a user-friendly format, such as "In your next product launch article, please consider using more product photos, explaining benefits in bullet points, and using a design that evokes positive emotions."

[0660] Step 12:

[0661] User: Re-enter the suggested improvement with additional feedback or new requests, such as "I'll try that strategy in my next post."

[0662] Step 13:

[0663] Device: Receive feedback again and send it to the server.

[0664] Step 14:

[0665] Server: Again, the received feedback is stored in a database and the process from step 3 to step 13 above is repeated to continuously improve the campaign.

[0666] Example 2

[0667] 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."

[0668] Modern marketing campaigns require the rapid and effective collection of customer feedback, accurate analysis of that feedback, and the development of improvement measures. Furthermore, by taking into account customer emotional factors, it is necessary to propose more accurate improvement measures and increase customer satisfaction. However, with conventional systems, the process from collecting feedback to analyzing it and proposing improvement measures relies on manual work, which takes a great deal of time and effort and is hardly efficient.

[0669] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving feedback and requests from customers, a means for storing the received feedback and requests in a database, a means for analyzing the stored feedback and requests using natural language processing, a means for recognizing emotions in the feedback and requests, a means for generating improvement measures based on the analysis results of the natural language processing and emotion recognition, and a means for visually presenting the generated improvement measures. This makes it possible to automate the process from collecting feedback to analyzing it and presenting improvement measures, thereby realizing efficient and effective optimization of marketing campaigns that also take customer emotions into consideration.

[0670] "Feedback" refers to opinions, requests, and evaluations provided by customers.

[0671] A "request" is a proposal for an improvement, new feature, or service that a customer wants for a particular product or service.

[0672] "Means" refers to a method, device, or process for achieving a specific purpose.

[0673] A "database" is a system for efficiently storing, managing, and retrieving data.

[0674] "Natural language processing" is a technology that allows computers to understand human language and analyze text.

[0675] "Emotion recognition" is a technology that detects and classifies emotional states from data such as text and voice.

[0676] "Analysis results" refers to the insights and information obtained after analyzing data.

[0677] "Improvements" are specific actions or methods proposed to resolve existing problems.

[0678] "Visually presenting" means displaying information in a format that is easy for the user to view.

[0679] A "marketing campaign" is a series of activities designed to promote a particular product or service.

[0680] The present invention relates to a marketing campaign optimization system that collects customer feedback and requests, analyzes them, and generates improvements to the marketing campaign. The system incorporates an emotion engine that recognizes the emotions in the feedback and requests. Specific embodiments for implementing the present invention will be described below.

[0681] System Configuration

[0682] Hardware and Software Configuration

[0683] Users: Enter feedback using a computer, mobile device, or other device.

[0684] Device: Receives user feedback and sends it to the server. Software used includes a web browser and dedicated applications.

[0685] Server: Receives feedback data and stores it in a database. Python scripts are used for data analysis, and libraries such as TextBlob and spaCy are used for natural language processing (NLP). A dedicated emotion recognition engine is used for sentiment analysis.

[0686] Data processing and calculation

[0687] Collecting and storing feedback

[0688] User: Enter feedback or requests about the campaign into the terminal. For example, enter feedback such as "The article introducing the new product is not very appealing."

[0689] Terminal: Receives feedback from the user, stores it temporarily, and then sends the feedback data to the server using an HTTP POST request.

[0690] Feedback Analysis

[0691] Server: Stores the received feedback data in a database and runs an analysis engine. Specifically, it uses a natural language processing engine to analyze the text and extract key topics and sentiment. It uses NLP libraries such as TextBlob and spaCy.

[0692] Server: Uses an emotion recognition engine to identify emotional elements in the feedback, for example, detecting emotions such as "dissatisfaction" or "disappointment."

[0693] Generate improvements

[0694] Server: Based on the analysis results, a generative AI model is used to generate specific improvement measures, such as GPT-3.

[0695] Server: Enters the prompt "The user is dissatisfied with the new product introduction article. Please suggest improvements," and obtains improvements from the generative AI model.

[0696] Proposal of improvement measures

[0697] Server: Sends the generated remediation measures to the device.

[0698] On the device: Visually present the received improvement recommendations through the user interface, for example, by displaying a message such as, "In your next new product introduction article, we recommend that you use more product photos and emphasize the benefits. Also, consider a design that evokes positive emotions."

[0699] Handling re-feedback

[0700] Users: Enter additional feedback or new requests based on the proposed improvements, creating a feedback loop that allows for continuous campaign improvement.

[0701] Specific examples

[0702] Example 1: Improving a new product introduction campaign

[0703] 1. User: Enters feedback saying, "The new product introduction article isn't very appealing."

[0704] 2. Device: Sends feedback to the server.

[0705] 3. Server: Stores the received feedback in a database and analyzes it using a natural language processing engine and emotion recognition engine.

[0706] 4. Server: Generate the following improvements: "Add product photos to new product introduction articles to highlight their benefits" and "Use designs that elicit positive emotions."

[0707] 5. Server: Sends the remediation plan to the device.

[0708] 6. Device: Suggest to users, "In your next product launch article, we recommend using more product photos and highlighting the benefits. Also, consider creating a design that evokes positive emotions."

[0709] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0710] Step 1: Gather feedback

[0711] User: Enter feedback or requests about the campaign into the terminal. For example, enter feedback such as "The article introducing the new product is not very appealing."

[0712] Input: The feedback text entered by the user.

[0713] Output: Feedback data.

[0714] On the device: Receive feedback from the user, temporarily store it, and then send the feedback data to the server using an HTTP POST request.

[0715] Step 2: Store feedback in a database

[0716] Server: Receives received feedback data and generates a log entry acknowledging receipt.

[0717] Input: Feedback data sent from the device.

[0718] Output: Feedback data stored in a database.

[0719] Server: The feedback data is saved in the database using the INSERT statement. The data saved in the database also includes the user's identification information.

[0720] Step 3: Analyze the feedback data

[0721] Server: Retrieves new feedback entries in the database and triggers the Natural Language Processing (NLP) engine using a Python script and TextBlob and spaCy as NLP libraries.

[0722] Input: Feedback data retrieved from the database.

[0723] Output: Analysis results (major topics and sentiment).

[0724] What it does: The NLP engine analyzes the feedback text and extracts key topics. The emotion recognition engine is used to recognize the emotional components of the feedback (e.g., "dissatisfied").

[0725] Step 4: Generate remediation measures

[0726] Server: Based on the analysis results of the NLP and emotion recognition engine, a generative AI model (e.g., GPT-3) is used to generate specific improvement measures.

[0727] Input: Analysis results (major topics and sentiment).

[0728] Output: Remedies.

[0729] Specific behavior: The prompt sentence "The user is dissatisfied with the new product introduction article. Please suggest improvements" is input into the generative AI model to generate improvements. For example, a specific improvement suggestion is obtained: "Add product photos to the new product introduction article and highlight its benefits."

[0730] Step 5: Submit and present your remediation plan

[0731] Server: Sends the generated remediation to the device using an HTTP POST request.

[0732] Input: The generated remediation measures.

[0733] Output: Submitted remediation.

[0734] Device: Visually present the received improvement recommendations through the user interface. For example, display a message such as, "In your next new product introduction article, we recommend using more product photos and emphasizing the benefits. Also, consider designing it to evoke positive emotions."

[0735] Step 6: Processing re-feedback

[0736] Users: Re-enter any additional feedback or new requests for the proposed improvements.

[0737] Input: Any additional feedback entered by the user.

[0738] Output: The collected feedback data again.

[0739] What it does: The re-entered feedback data is then sent back to the server by the device, and the feedback collection and storage process is repeated, creating a feedback loop that allows for continuous campaign improvement.

[0740] (Application example 2)

[0741] 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."

[0742] In conventional marketing campaign optimization systems, analysis and improvement plan generation based on collected customer feedback was often done manually, resulting in a waste of time and effort. Furthermore, the system for properly reflecting customer sentiment was inadequate, making it difficult to improve customer satisfaction. Furthermore, there was no established method for efficiently collecting and presenting feedback using smart devices.

[0743] 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.

[0744] In this invention, the server includes means for receiving feedback and requests from customers, means for storing the received feedback and requests in a database, means for analyzing the stored feedback and requests using natural language processing, means for generating improvement measures and policies based on the analysis results, means for visually presenting the generated improvement measures and policies to customers, and means for efficiently collecting and presenting feedback from customers using a smart device. This automates the collection and analysis of feedback, making it possible to quickly generate and present specific improvement measures that take customer sentiment into consideration.

[0745] "Customer" refers to a person who uses a service or purchases a product.

[0746] "Feedback" refers to opinions and ratings provided by customers regarding services and products.

[0747] "Requests" refer to improvements or additional features that customers expect from a particular service or product.

[0748] "Database" refers to a system for systematically storing and managing collected feedback and requests.

[0749] "Natural language processing" refers to the technology of understanding and analyzing feedback and requests as human language.

[0750] "Improvement measures" refer to specific measures to improve services or products based on feedback and requests.

[0751] "Visually presenting" refers to displaying the generated improvement measures and initiatives in a way that is easy for customers to see.

[0752] "Smart devices" refers to devices with internet connectivity, such as smartphones, smart glasses, and head-mounted displays.

[0753] "Collection" refers to the act of gathering feedback and requests from customers.

[0754] "Presenting" refers to the act of displaying the collected information and generated improvement measures to the user.

[0755] To implement the present invention, the following steps are followed to implement a program using the specified hardware and software.

[0756] 1. System Configuration

[0757] Customers use their smartphones to enter feedback and requests about products and services.

[0758] This feedback is sent by the terminal to the server.

[0759] The server stores the received feedback in a database and then analyzes the stored data using a natural language processing (NLP) engine, spaCy, and TextBlob for sentiment analysis.

[0760] The server generates improvement measures and policies based on the analysis results of the NLP and emotion engine. This involves extracting key topics and emotions and generating specific improvement proposals based on them.

[0761] The server transmits the generated remedial measures back to the terminal, which visually displays the remedial measures to the customer.

[0762] 2. Program Implementation

[0763] Use smart devices to efficiently gather feedback from users and suggest improvements.

[0764] After receiving the feedback, it sends it to the server, where the data is stored in a database.

[0765] The feedback stored in the database is analyzed using an NLP engine (spaCy) and an emotion engine (TextBlob) to extract key topics and emotions.

[0766] Based on the extracted analysis results, logic is implemented on the server to generate improvement measures corresponding to specific keywords and emotions.

[0767] An interface is constructed on the terminal side to visually present the final generated improvement measures to the user.

[0768] Hardware and software used

[0769] Smartphone device: Used to enter feedback and view improvements.

[0770] Server: Stores and analyzes feedback and generates improvement measures.

[0771] Database: Used to store feedback and analysis results.

[0772] Natural language processing engine: spaCy is used to analyze feedback topics.

[0773] Sentiment Analysis Engine: Uses TextBlob to analyze the sentiment of feedback.

[0774] Specific examples

[0775] When the user inputs feedback such as "the product description is insufficient," the terminal transmits the feedback to the server.

[0776] The server stores the received feedback in a database and then parses the feedback using spaCy and TextBlob.

[0777] As a result of the analysis, the topic of "insufficient description" and negative sentiment are extracted, and an improvement measure of "adding a detailed description of the product" is generated.

[0778] The generated improvement measures are sent to the terminal and visually displayed to the user in the form of "Please add product description."

[0779] Prompt Sentence Examples

[0780] You received feedback from users that the product page was difficult to navigate and lacked information. Based on this feedback, please analyze it using an NLP engine and a sentiment engine, and suggest specific improvements based on the resulting keywords and sentiment.

[0781] As described above, the present invention is capable of efficiently collecting and analyzing feedback from customers to generate specific improvement measures and visually presenting them in a form that takes into account the customer's feelings.

[0782] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0783] Step 1:

[0784] Users use their smartphones to input feedback and requests about products and services. The input feedback data (e.g., "The product description is insufficient") is saved on the device.

[0785] Step 2:

[0786] The terminal sends the input feedback data to the server. At this time, the feedback content and the user's identification information are included in the transmitted data. The feedback data is transferred to the server via an HTTP request.

[0787] Step 3:

[0788] The server stores the received feedback data in a database. The stored data includes the feedback content and user identification information. The database stores the feedback text, user ID, timestamp, etc.

[0789] Step 4:

[0790] The server starts natural language processing (NLP) on the stored feedback data. It uses spaCy as its NLP engine to extract the main topics of the feedback. The input is the feedback text, and the output is a list of extracted keywords. Specifically, it tokenizes the text and extracts noun phrases.

[0791] Step 5:

[0792] The server uses a sentiment analysis engine (TextBlob) to analyze the sentiment of the feedback. The input is the feedback text and the output is a sentiment score (positive, negative, neutral). The TextBlob is used to process the sentiment polarity of the text.

[0793] Step 6:

[0794] The server generates improvement measures based on the results of NLP and sentiment analysis. The input is the extracted keywords and sentiment scores, and the output is a list of specific improvement measures. Specifically, it selects and generates appropriate improvement measures from a pre-defined list of improvement candidate measures.

[0795] Step 7:

[0796] The server sends the generated remediation plan to the terminal, along with details of the remediation plan as an HTTP response. The output includes specific suggestions for the customer.

[0797] Step 8:

[0798] The device visually displays the received improvement measures to the user, using pop-up messages, notification banners, etc. Specifically, the device displays the improvement measures on the user interface based on the received data.

[0799] Step 9:

[0800] Users can then provide additional feedback and suggestions for the proposed improvements, creating a feedback loop that continually refines the actual campaign.

[0801] Through the above steps, the present invention can effectively collect and analyze customer feedback, and generate and present specific improvement measures.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] [Third embodiment]

[0806] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0807] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0808] 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).

[0809] 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.

[0810] 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.

[0811] 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).

[0812] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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."

[0818] The present invention relates to a marketing campaign optimization system that collects feedback and requests from customers, analyzes the feedback and requests, generates improvements to the marketing campaign, and presents them to the customers. Specific embodiments for carrying out the present invention will be described below.

[0819] Program processing and behavior

[0820] 1. Collect customer feedback

[0821] User: Uses a device to enter feedback or requests about the campaign, for example, "The new product introduction article is not very appealing."

[0822] Terminal: Sends the feedback entered by the user to the server.

[0823] 2. Saving your feedback to a database

[0824] Server: Stores the received feedback in a database. The stored data includes the feedback content as well as the user's identification information.

[0825] 3. Analysis using natural language processing

[0826] Server: The stored feedback is fed into a natural language processing engine for content analysis, including sentiment assessment and topic extraction.

[0827] Server: As a result of the analysis, for example, from feedback that "the article introducing a new product is not appealing," the insight that "visual enhancement is needed" is extracted.

[0828] 4. Generate improvements

[0829] Server: Generates recommendations for improving marketing campaigns based on the analysis results, such as "add visual elements to product articles and highlight product benefits with bullet points."

[0830] 5. Providing improvement measures to users

[0831] Server: Sends the generated remediation measures to the device.

[0832] On the device: Display the received improvement recommendations in a user-friendly format, for example, "In your next product launch article, we recommend using more product photos to highlight the benefits."

[0833] 6. Re-feedback

[0834] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[0835] Specific examples

[0836] Example 1: Improving a new product introduction campaign

[0837] 1. User: Enters feedback on the campaign site saying, "The article introducing the new product is not very appealing."

[0838] 2. Device: Sends feedback to the server.

[0839] 3. Server: Stores the received feedback in a database and analyzes the issue of "not visually appealing" using natural language processing.

[0840] 4. Server: Generate an improvement plan: "Add product photos to new product introduction articles to highlight their benefits."

[0841] 5. Server: Sends the improvement plan to the device.

[0842] 6. Device: Suggest to the user, "In your next product launch article, add visuals and explain the benefits in bullet points."

[0843] Example 2: Improving a sales campaign

[0844] 1. User: Enters feedback on the online store saying, "There are not many products on sale and it's not appealing."

[0845] 2. Device: Sends feedback to the server.

[0846] 3. Server: Stores the feedback in a database and analyzes the problem of "not enough products available" using natural language processing.

[0847] 4. Server: Generate an improvement plan: "Increase the number of items on sale and introduce bundle discounts."

[0848] 5. Server: Sends the improvement plan to the device.

[0849] 6. Device: Propose to the user that "In the next sale, we will increase the number of eligible products and introduce set discounts."

[0850] In this way, the present invention can efficiently collect customer feedback, quickly analyze it, generate specific improvement measures, and present them to customers, thereby maximizing the effectiveness of marketing campaigns and increasing customer satisfaction and engagement.

[0851] The processing flow will be explained below.

[0852] Step 1:

[0853] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[0854] Step 2:

[0855] Terminal: Receives user feedback and sends feedback data to the server.

[0856] Step 3:

[0857] Server: Receives feedback sent from the device and stores it in a database, including user identification information.

[0858] Step 4:

[0859] Server: Starts parsing the stored feedback data using a natural language processing (NLP) engine, for example using an NLP library such as TextBlob or spaCy.

[0860] Step 5:

[0861] Server: Analyzes the feedback using natural language processing to extract key topics and sentiments, for example, obtaining results such as "visually unappealing."

[0862] Step 6:

[0863] Server: Identify customer requests based on the analysis results. For example, extract a request such as "New product introduction articles need visual enhancements."

[0864] Step 7:

[0865] Server: Review data from other users with similar feedback and perform trend analysis to identify common issues.

[0866] Step 8:

[0867] Server: Generates specific improvements and measures for marketing campaigns based on trend analysis results, such as adding product photos to new product introduction articles and highlighting their benefits in bullet points.

[0868] Step 9:

[0869] Server: Sends the generated remediation measures to the device.

[0870] Step 10:

[0871] On the device: Display the improvement suggestions to the user and present them in an easy-to-understand format, such as "In your next product launch article, we recommend using more product photos to highlight the benefits."

[0872] Step 11:

[0873] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[0874] Example 1

[0875] 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."

[0876] Conventional marketing campaign optimization systems have difficulty efficiently analyzing customer feedback and quickly proposing specific improvement measures. Furthermore, it is difficult to continuously and dynamically incorporate feedback, which results in insufficient improvement of customer satisfaction and engagement. Furthermore, the generated improvement measures are often not specific and not feasible.

[0877] 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.

[0878] In this invention, the server includes a means for receiving feedback and requests from customers, a means for storing the received feedback and requests in an information repository, a means for analyzing the stored feedback and requests using natural language processing, a means for generating improvement measures and policies based on the analysis results using a generative AI model, and a means for visually presenting the generated improvement measures and policies to customers. This makes it possible to efficiently collect and analyze customer feedback and quickly provide specific, actionable improvement measures. Furthermore, by forming a continuous feedback loop, the effectiveness of marketing campaigns can be maximized and customer satisfaction and engagement can be improved.

[0879] "Feedback" refers to information such as opinions, requests, and evaluations provided by customers.

[0880] "Requests" are requests for improvements or new features that customers expect from services or products.

[0881] An "information repository" is a system for storing and managing data, such as a database or storage system.

[0882] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0883] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to automatically generate new data or suggestions.

[0884] "Improvements" are specific proposals and measures to improve existing systems and campaigns.

[0885] "Measures" are specific actions or strategies planned to achieve business goals.

[0886] "Visual presentation" means displaying information on a screen or display in a format that is easy for the user to understand.

[0887] The present invention relates to a marketing campaign optimization system that collects and analyzes feedback and requests from customers, generates improvements to the marketing campaign based on the collected feedback, and presents the improvements to the customers. Specific embodiments for carrying out the present invention will be described below.

[0888] This system mainly consists of a server, terminals, and users. The specific roles and processes of each component are shown below.

[0889] Gathering feedback

[0890] Users can use their devices to input their feedback and requests about the campaign. The device interface can be a web form, a mobile application, etc. For example, a user might input, "The article introducing the new product is not very appealing."

[0891] The terminal receives the feedback information input by the user, generates an HTTP POST request, and sends it to the server.

[0892] Feedback storage and analysis

[0893] The server stores the feedback received from the terminal in a database (information collection), and the stored data includes the feedback content, user identification information, and a timestamp.

[0894] The stored feedback data is analyzed using a natural language processing (NLP) engine (e.g., Microsoft Azure Cognitive Services text analysis API or Google Cloud Natural Language API). The server sends the feedback data to these external APIs and receives the analysis results.

[0895] As a result of the analysis, the main topics and emotional evaluations of the feedback are extracted. For example, from feedback that "the new product introduction article is not appealing," the insight that "visual appeal needs to be improved" can be obtained.

[0896] Generate improvements

[0897] The server generates specific marketing campaign improvement measures using a generative AI model (e.g., a general natural language generation model) based on the analysis results of natural language processing. For example, improvement measures such as "add visual elements to product introduction articles and emphasize the product's benefits in bullet points" are generated.

[0898] The generated improvements are formatted in a way that is easy for the user to understand.

[0899] Providing improvement measures and providing feedback

[0900] The server sends the generated remediation measures to the terminal as an HTTP response.

[0901] The device converts the received improvements into a display data structure and displays it in the UI of a web page or application, for example, "In our next new product introduction article, we'll add visual elements and explain the benefits in bullet points."

[0902] Users can then provide additional feedback or new suggestions for improvements, creating a feedback loop that allows for continuous improvement of the campaign.

[0903] Examples of prompt statements

[0904] Prompt 1: "How would you generate improvements based on customer feedback about a new product introduction article that they found less appealing?"

[0905] Prompt 2: "Explain how to generate optimal improvements based on customer feedback that feels there are not enough products in a sales campaign."

[0906] The above is a specific embodiment of the present invention. This system efficiently collects and analyzes customer feedback and can quickly provide specific and actionable improvement measures, thereby maximizing the effectiveness of marketing campaigns and improving customer satisfaction.

[0907] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0908] Step 1: Gather feedback

[0909] The user uses the terminal to input feedback and requests about the campaign, for example, "The article introducing the new product is not very appealing."

[0910] Input: Feedback text (e.g., "The new product introduction article is not very appealing.")

[0911] Action: Enter your feedback through a device interface (e.g., a web form or a mobile application) and click the "Submit" button.

[0912] Output: User feedback is sent to the device.

[0913] Step 2: Submit your feedback

[0914] The terminal receives the feedback information input by the user, generates an HTTP POST request, and sends it to the server.

[0915] Input: The feedback text entered by the user

[0916] What it does: Creates an HTTP POST request and sends it to the server with the feedback information.

[0917] Output: The feedback information is sent to the server.

[0918] Step 3: Save your feedback

[0919] The server stores the feedback received from the terminal in a database, and the stored data includes the feedback content, user identification information, and a timestamp.

[0920] Input: Feedback information sent from the device

[0921] What it does: Parses the feedback information and executes an insert query to the database to save the data.

[0922] Output: The feedback information is stored in a database.

[0923] Step 4: Analyze the feedback

[0924] The server then inputs the stored feedback data into a natural language processing (NLP) engine to analyze the content, for example, using the Microsoft Azure Cognitive Services text analysis API or the Google Cloud Natural Language API.

[0925] Input: Feedback information stored in the database

[0926] How it works: Sends feedback data to a natural language processing API and receives analysis results.

[0927] Output: Analysis results such as main topics of feedback and sentiment ratings

[0928] Step 5: Extracting insights

[0929] The server extracts key topics and insights from the feedback based on the results of natural language processing analysis. For example, from feedback such as "The article introducing a new product is not appealing," it can obtain the insight that "The visual appeal needs to be improved."

[0930] Input: Analysis results of natural language processing

[0931] What it does: Extract topics and insights from the analysis results and store them in a database.

[0932] Output: Insights and topic information

[0933] Step 6: Generate remediation measures

[0934] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate specific marketing campaign improvement measures.

[0935] Input: Insights and topic information

[0936] How it works: Input insight data into a generative AI model and get output improvement measures.

[0937] Output: Specific improvement suggestions (e.g., "Add visual elements to product articles and highlight product benefits with bullet points")

[0938] Step 7: Propose improvement measures

[0939] The server transmits the generated remedial measures to the terminal.

[0940] Input: Improvements generated by a generative AI model

[0941] Behavior: Remediation data is sent to the device as an HTTP response.

[0942] Output: Remediation data is sent to the terminal.

[0943] The device converts the received remedial measures into a display data structure and displays them on a web page or application UI.

[0944] Input: Remediation data sent from the server

[0945] How it works: Received data is bound to HTML and application UI components and displayed on the screen.

[0946] Output: The remediation measures are displayed in a format that the user can understand visually.

[0947] Step 8: Re-feedback

[0948] Users can then provide additional feedback or new requests for the proposed improvements, creating a feedback loop that allows for continuous improvement of the campaign.

[0949] Input: Feedback on the improvement plan (e.g., "I agree with the improvement plan" or "I would like to add another request")

[0950] Action: Fill out the feedback form again and click the "Submit" button.

[0951] Output: New feedback is sent to the terminal and processing begins again.

[0952] (Application example 1)

[0953] 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."

[0954] Modern marketing campaigns require the rapid and effective incorporation of customer feedback to optimize the campaign. However, with conventional systems, the collection, analysis, generation, and presentation of feedback improvements were separated, making it impossible to integrate these processes. Furthermore, it was difficult to propose products and improvements tailored to individual customer needs, resulting in insufficient improvement of customer satisfaction.

[0955] 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.

[0956] In this invention, the server includes means for receiving feedback and requests from customers, means for storing the received feedback and requests in a database, means for analyzing the stored feedback and requests using natural language processing, means for generating improvement measures and policies based on the analysis results, means for visually presenting the generated improvement measures and policies to customers, and means for improving a recommendation algorithm based on feedback and making optimal product proposals for individual customers. This makes it possible to efficiently incorporate customer feedback and make personalized product proposals, thereby optimizing marketing campaigns and improving customer satisfaction.

[0957] "Customer Feedback" is input from customers providing their experiences, opinions, and requests.

[0958] A "database" is a computer system that systematically stores and manages information such as feedback and requests received from customers.

[0959] "Natural language processing" is a technology that allows computers to analyze human language and understand its meaning.

[0960] "Improvements" are specific measures developed based on customer feedback to improve marketing campaigns or services.

[0961] "Visual presentation" is a means of displaying the generated improvement measures and initiatives to the customer in an easy-to-read format.

[0962] A "recommendation algorithm" is an algorithm that analyzes a customer's past behavior and feedback to suggest the best products and services for each individual customer.

[0963] "Product suggestion" is an action that recommends products that are considered to be best suited to individual customers based on customer feedback and behavioral data.

[0964] This invention is realized using a smartphone application called a “Personalized Shopping Assistant.” A detailed embodiment of this system will be described below.

[0965] A customer (user) starts the app on their smartphone and enters their opinions and requests into the feedback form. For example, they might enter feedback such as "There are too few items on sale recently." The device then sends this input to the server.

[0966] The server stores the received feedback in a database, which serves to store and manage customer feedback in an organized manner.

[0967] The server then inputs the saved feedback into a natural language processing (NLP) engine and analyzes its content. For analysis, existing NLP engines such as Google Cloud Natural Language API and Amazon Comprehend are used. As a result of the analysis, sentiment ratings and topics of the feedback are extracted. For example, a sentiment rating of "visually unappealing" is obtained.

[0968] Based on the analysis results, the server generates improvement measures for the marketing campaign. Specific improvement measures are proposed using a generative AI model. For example, the generated improvement measures might be to "increase the number of products on sale and introduce new discount sets."

[0969] The server then sends the generated improvement plan to the terminal, which visually displays the received improvement plan to the customer. For example, it may display, "In the next sale, we will expand the range of eligible products and introduce a new discount set."

[0970] Furthermore, the server uses the feedback to improve its recommendation algorithm and make optimal product suggestions for each individual customer, such as "The following products are recommended for you."

[0971] This will enable efficient incorporation of customer feedback and personalized product recommendations, optimizing marketing campaigns and improving customer satisfaction.

[0972] Examples of concrete examples and prompts

[0973] As a concrete example, imagine a user who opens the smartphone app "Personalized Shopping Assistant" enters "There are too few recent sale items" into the feedback form. This feedback is sent to the server and analyzed by Amazon Comprehend. Based on the analysis results, the user is given a specific improvement suggestion, such as "In the next sale, expand the range of eligible products and introduce a new discount set."

[0974] Example prompt sentence:

[0975] Please analyze the following feedback statement and suggest improvements:

[0976] Feedback: "There are too few sale items these days."

[0977] These prompts enable the generative AI model to provide further actionable insights and recommendations for improvement, leading to improved customer satisfaction and effective optimization of marketing campaigns.

[0978] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0979] Step 1:

[0980] A user launches the app on their smartphone. The user enters their opinions and requests into the feedback form. For example, the user might enter feedback such as "There are too few items on sale recently." The input data is in the form of a string, and the device sends this data to the server.

[0981] Step 2:

[0982] The device sends the feedback entered by the user to the server. This data transfer uses the HTTPS protocol, and the sent data is in JSON format. The server stores the received feedback in a database. When saving, the user's identification information is also saved.

[0983] Step 3:

[0984] The server inputs the saved feedback into a natural language processing engine (e.g., Google Cloud Natural Language API or Amazon Comprehend) and analyzes its content. The main task of the analysis is to evaluate the sentiment of the text data and extract topics. For example, the topic "visually unattractive" and its sentiment evaluation are obtained.

[0985] Step 4:

[0986] The server generates improvement measures for the marketing campaign based on the analysis results from the natural language processing engine. For example, the generated improvement measures might be to "increase the number of products on sale and introduce new discount sets." The natural language generation model used here is a generative AI model. It inputs a prompt sentence and outputs specific improvement measures.

[0987] Step 5:

[0988] The server sends the generated improvement measures to the terminal. The terminal visually displays the received improvement measures to the user. For example, it may display "In the next sale, we will expand the range of eligible products and introduce a new discount set." The display format is a visually easy-to-understand UI design, and a user interface framework (e.g., React Native) is used.

[0989] Step 6:

[0990] The server improves the recommendation algorithm based on the feedback and makes optimal product suggestions for each individual customer. In this process, past feedback data and behavioral data are integrated and the improved recommendation algorithm is applied. For example, the server may make suggestions to the user such as, "The following products are recommended for you." This allows the optimal product list to be updated in real time, enabling personalized product suggestions.

[0991] Through these steps, it becomes possible to effectively incorporate user feedback and provide personalized product recommendations, optimizing marketing campaigns and improving customer satisfaction.

[0992] 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.

[0993] The present invention relates to a marketing campaign optimization system that collects feedback and requests from customers, analyzes the collected feedback and requests, generates improvements to the marketing campaign, and presents them to the customers. The present invention further incorporates an emotion engine that recognizes the emotions in the customer feedback and requests. Specific embodiments for implementing the present invention will be described below.

[0994] Program processing and behavior

[0995] 1. Collect customer feedback

[0996] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[0997] Terminal: Receives user feedback and sends feedback data to the server.

[0998] 2. Saving your feedback to a database

[0999] Server: Stores the received feedback in a database. The stored data includes the feedback content as well as the user's identification information.

[1000] 3. Analysis using natural language processing and sentiment engines

[1001] Server: Starts parsing the stored feedback data using a natural language processing (NLP) engine, for example using an NLP library such as TextBlob or spaCy.

[1002] Server: Analyzes the feedback content using NLP and extracts key topics and sentiments, for example, "visually unappealing."

[1003] Server: The emotion engine recognizes emotional elements in the feedback. For example, it detects the emotion "dissatisfied."

[1004] 4. Generate improvement measures and reflect sentiment data

[1005] Server: Based on the analysis results of NLP and the emotion engine, it generates specific improvement measures that take into account customer requests and emotions. For example, it suggests improvement measures such as "add product photos to new product introduction articles and emphasize their benefits with bullet points" and "use designs that evoke positive emotions."

[1006] 5. Providing improvement measures to users

[1007] Server: Sends the generated remediation measures to the device.

[1008] On-device: Display the received improvement recommendations in a user-friendly format, such as "In your next new product introduction article, we recommend using more product photos and emphasizing the benefits. Also, consider creating a design that evokes positive emotions."

[1009] 6. Re-feedback

[1010] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[1011] Specific examples

[1012] Example 1: Improving a new product introduction campaign

[1013] 1. User: Enters feedback on the campaign site saying, "The article introducing the new product is not very appealing."

[1014] 2. Device: Sends feedback to the server.

[1015] 3. Server: The received feedback is stored in a database, and the natural language processing engine analyzes whether the feedback is visually unattractive, and the emotion engine recognizes the emotion of "dissatisfaction."

[1016] 4. Server: Generate the following improvements: "Add product photos to new product introduction articles to highlight their benefits" and "Use designs that elicit positive emotions."

[1017] 5. Server: Sends the improvement plan to the device.

[1018] 6. Device: Suggest to users, "In your next product launch article, we recommend using more product photos and highlighting the benefits. Also, consider creating a design that evokes positive emotions."

[1019] Example 2: Improving a sales campaign

[1020] 1. User: Enters feedback on the online store saying, "There are not many products on sale and it's not appealing."

[1021] 2. Device: Sends feedback to the server.

[1022] 3. Server: The feedback is stored in a database, the natural language processing engine analyzes that there are few eligible products, and the emotion engine recognizes the emotion of "disappointment."

[1023] 4. Server: Generates the following improvement measures: "Increase the number of items on sale and introduce bundle discounts" and "Add rewards that elicit positive emotions."

[1024] 5. Server: Sends the improvement plan to the device.

[1025] 6. Device: Suggest to the user, "For your next sale, we recommend expanding the selection and introducing bundled discounts. Also, add rewards that evoke positive emotions."

[1026] In this way, the present invention can efficiently collect and analyze customer feedback to generate specific improvement measures, and by taking customer sentiment into account, can realize more effective improvements to marketing campaigns, thereby increasing customer satisfaction and engagement and maximizing the results of marketing campaigns.

[1027] The processing flow will be explained below.

[1028] Step 1:

[1029] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[1030] Step 2:

[1031] Terminal: Receives user feedback and sends feedback data to the server.

[1032] Step 3:

[1033] Server: Receives feedback sent from the device and stores the feedback and user identification information in a database.

[1034] Step 4:

[1035] Server: Starts analyzing the stored feedback data using a natural language processing (NLP) engine. For example, it uses an NLP library such as TextBlob or spaCy to analyze the feedback content.

[1036] Step 5:

[1037] Server: Analyzes the feedback content using natural language processing and extracts key topics and sentiments. For example, the analysis results "visually unappealing."

[1038] Step 6:

[1039] Server: Uses an emotion engine to recognize emotional elements in the feedback. For example, it detects the emotion "dissatisfied."

[1040] Step 7:

[1041] Server: Based on the results of natural language processing and emotion engine analysis, the server generates specific improvement measures that take into account customer requests and emotions. For example, it suggests an improvement such as "adding product photos to new product introduction articles and emphasizing their benefits in bullet points."

[1042] Step 8:

[1043] Server: Conducts trend analysis and integrates multiple feedback data to identify common issues, allowing for adjustments to be made to overall improvements.

[1044] Step 9:

[1045] Server: Adjusts the improvement plan and develops the optimal improvement plan that takes into account the sentiment data. For example, add a suggestion such as "Use designs that elicit positive emotions."

[1046] Step 10:

[1047] Server: Sends the generated final remediation to the device.

[1048] Step 11:

[1049] On device: Display the received improvement recommendations in a user-friendly format, such as "In your next product launch article, please consider using more product photos, explaining benefits in bullet points, and using a design that evokes positive emotions."

[1050] Step 12:

[1051] User: Re-enter the suggested improvement with additional feedback or new requests, such as "I'll try that strategy in my next post."

[1052] Step 13:

[1053] Device: Receive feedback again and send it to the server.

[1054] Step 14:

[1055] Server: Again, the received feedback is stored in a database and the process from step 3 to step 13 above is repeated to continuously improve the campaign.

[1056] Example 2

[1057] 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."

[1058] Modern marketing campaigns require the rapid and effective collection of customer feedback, accurate analysis of that feedback, and the development of improvement measures. Furthermore, by taking into account customer emotional factors, it is necessary to propose more accurate improvement measures and increase customer satisfaction. However, with conventional systems, the process from collecting feedback to analyzing it and proposing improvement measures relies on manual work, which takes a great deal of time and effort and is hardly efficient.

[1059] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving feedback and requests from customers, a means for storing the received feedback and requests in a database, a means for analyzing the stored feedback and requests using natural language processing, a means for recognizing emotions in the feedback and requests, a means for generating improvement measures based on the analysis results of the natural language processing and emotion recognition, and a means for visually presenting the generated improvement measures. This makes it possible to automate the process from collecting feedback to analyzing it and presenting improvement measures, thereby realizing efficient and effective optimization of marketing campaigns that also take customer emotions into consideration.

[1060] "Feedback" refers to opinions, requests, and evaluations provided by customers.

[1061] A "request" is a proposal for an improvement, new feature, or service that a customer wants for a particular product or service.

[1062] "Means" refers to a method, device, or process for achieving a specific purpose.

[1063] A "database" is a system for efficiently storing, managing, and retrieving data.

[1064] "Natural language processing" is a technology that allows computers to understand human language and analyze text.

[1065] "Emotion recognition" is a technology that detects and classifies emotional states from data such as text and voice.

[1066] "Analysis results" refers to the insights and information obtained after analyzing data.

[1067] "Improvements" are specific actions or methods proposed to resolve existing problems.

[1068] "Visually presenting" means displaying information in a format that is easy for the user to view.

[1069] A "marketing campaign" is a series of activities designed to promote a particular product or service.

[1070] The present invention relates to a marketing campaign optimization system that collects customer feedback and requests, analyzes them, and generates improvements to the marketing campaign. The system incorporates an emotion engine that recognizes the emotions in the feedback and requests. Specific embodiments for implementing the present invention will be described below.

[1071] System Configuration

[1072] Hardware and Software Configuration

[1073] Users: Enter feedback using a computer, mobile device, or other device.

[1074] Device: Receives user feedback and sends it to the server. Software used includes a web browser and dedicated applications.

[1075] Server: Receives feedback data and stores it in a database. Python scripts are used for data analysis, and libraries such as TextBlob and spaCy are used for natural language processing (NLP). A dedicated emotion recognition engine is used for sentiment analysis.

[1076] Data processing and calculation

[1077] Collecting and storing feedback

[1078] User: Enter feedback or requests about the campaign into the terminal. For example, enter feedback such as "The article introducing the new product is not very appealing."

[1079] Terminal: Receives feedback from the user, stores it temporarily, and then sends the feedback data to the server using an HTTP POST request.

[1080] Feedback Analysis

[1081] Server: Stores the received feedback data in a database and runs an analysis engine. Specifically, it uses a natural language processing engine to analyze the text and extract key topics and sentiment. It uses NLP libraries such as TextBlob and spaCy.

[1082] Server: Uses an emotion recognition engine to identify emotional elements in the feedback, for example, detecting emotions such as "dissatisfaction" or "disappointment."

[1083] Generate improvements

[1084] Server: Based on the analysis results, a generative AI model is used to generate specific improvement measures, such as GPT-3.

[1085] Server: Enters the prompt "The user is dissatisfied with the new product introduction article. Please suggest improvements," and obtains improvements from the generative AI model.

[1086] Proposal of improvement measures

[1087] Server: Sends the generated remediation measures to the device.

[1088] On the device: Visually present the received improvement recommendations through the user interface, for example, by displaying a message such as, "In your next new product introduction article, we recommend that you use more product photos and emphasize the benefits. Also, consider a design that evokes positive emotions."

[1089] Handling re-feedback

[1090] Users: Enter additional feedback or new requests based on the proposed improvements, creating a feedback loop that allows for continuous campaign improvement.

[1091] Specific examples

[1092] Example 1: Improving a new product introduction campaign

[1093] 1. User: Enters feedback saying, "The new product introduction article isn't very appealing."

[1094] 2. Device: Sends feedback to the server.

[1095] 3. Server: Stores the received feedback in a database and analyzes it using a natural language processing engine and emotion recognition engine.

[1096] 4. Server: Generate the following improvements: "Add product photos to new product introduction articles to highlight their benefits" and "Use designs that elicit positive emotions."

[1097] 5. Server: Sends the remediation plan to the device.

[1098] 6. Device: Suggest to users, "In your next product launch article, we recommend using more product photos and highlighting the benefits. Also, consider creating a design that evokes positive emotions."

[1099] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1100] Step 1: Gather feedback

[1101] User: Enter feedback or requests about the campaign into the terminal. For example, enter feedback such as "The article introducing the new product is not very appealing."

[1102] Input: The feedback text entered by the user.

[1103] Output: Feedback data.

[1104] On the device: Receive feedback from the user, temporarily store it, and then send the feedback data to the server using an HTTP POST request.

[1105] Step 2: Store feedback in a database

[1106] Server: Receives received feedback data and generates a log entry acknowledging receipt.

[1107] Input: Feedback data sent from the device.

[1108] Output: Feedback data stored in a database.

[1109] Server: The feedback data is saved in the database using the INSERT statement. The data saved in the database also includes the user's identification information.

[1110] Step 3: Analyze the feedback data

[1111] Server: Retrieves new feedback entries in the database and triggers the Natural Language Processing (NLP) engine using a Python script and TextBlob and spaCy as NLP libraries.

[1112] Input: Feedback data retrieved from the database.

[1113] Output: Analysis results (major topics and sentiment).

[1114] What it does: The NLP engine analyzes the feedback text and extracts key topics. The emotion recognition engine is used to recognize the emotional components of the feedback (e.g., "dissatisfied").

[1115] Step 4: Generate remediation measures

[1116] Server: Based on the analysis results of the NLP and emotion recognition engine, a generative AI model (e.g., GPT-3) is used to generate specific improvement measures.

[1117] Input: Analysis results (major topics and sentiment).

[1118] Output: Remedies.

[1119] Specific behavior: The prompt sentence "The user is dissatisfied with the new product introduction article. Please suggest improvements" is input into the generative AI model to generate improvements. For example, a specific improvement suggestion is obtained: "Add product photos to the new product introduction article and highlight its benefits."

[1120] Step 5: Submit and present your remediation plan

[1121] Server: Sends the generated remediation to the device using an HTTP POST request.

[1122] Input: The generated remediation measures.

[1123] Output: Submitted remediation.

[1124] Device: Visually present the received improvement recommendations through the user interface. For example, display a message such as, "In your next new product introduction article, we recommend using more product photos and emphasizing the benefits. Also, consider designing it to evoke positive emotions."

[1125] Step 6: Processing re-feedback

[1126] Users: Re-enter any additional feedback or new requests for the proposed improvements.

[1127] Input: Any additional feedback entered by the user.

[1128] Output: The collected feedback data again.

[1129] What it does: The re-entered feedback data is then sent back to the server by the device, and the feedback collection and storage process is repeated, creating a feedback loop that allows for continuous campaign improvement.

[1130] (Application example 2)

[1131] 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."

[1132] In conventional marketing campaign optimization systems, analysis and improvement plan generation based on collected customer feedback was often done manually, resulting in a waste of time and effort. Furthermore, the system for properly reflecting customer sentiment was inadequate, making it difficult to improve customer satisfaction. Furthermore, there was no established method for efficiently collecting and presenting feedback using smart devices.

[1133] 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.

[1134] In this invention, the server includes means for receiving feedback and requests from customers, means for storing the received feedback and requests in a database, means for analyzing the stored feedback and requests using natural language processing, means for generating improvement measures and policies based on the analysis results, means for visually presenting the generated improvement measures and policies to customers, and means for efficiently collecting and presenting feedback from customers using a smart device. This automates the collection and analysis of feedback, making it possible to quickly generate and present specific improvement measures that take customer sentiment into consideration.

[1135] "Customer" refers to a person who uses a service or purchases a product.

[1136] "Feedback" refers to opinions and ratings provided by customers regarding services and products.

[1137] "Requests" refer to improvements or additional features that customers expect from a particular service or product.

[1138] "Database" refers to a system for systematically storing and managing collected feedback and requests.

[1139] "Natural language processing" refers to the technology of understanding and analyzing feedback and requests as human language.

[1140] "Improvement measures" refer to specific measures to improve services or products based on feedback and requests.

[1141] "Visually presenting" refers to displaying the generated improvement measures and initiatives in a way that is easy for customers to see.

[1142] "Smart devices" refers to devices with internet connectivity, such as smartphones, smart glasses, and head-mounted displays.

[1143] "Collection" refers to the act of gathering feedback and requests from customers.

[1144] "Presenting" refers to the act of displaying the collected information and generated improvement measures to the user.

[1145] To implement the present invention, the following steps are followed to implement a program using the specified hardware and software.

[1146] 1. System Configuration

[1147] Customers use their smartphones to enter feedback and requests about products and services.

[1148] This feedback is sent by the terminal to the server.

[1149] The server stores the received feedback in a database and then analyzes the stored data using a natural language processing (NLP) engine, spaCy, and TextBlob for sentiment analysis.

[1150] The server generates improvement measures and policies based on the analysis results of the NLP and emotion engine. This involves extracting key topics and emotions and generating specific improvement proposals based on them.

[1151] The server transmits the generated remedial measures back to the terminal, which visually displays the remedial measures to the customer.

[1152] 2. Program Implementation

[1153] Use smart devices to efficiently gather feedback from users and suggest improvements.

[1154] After receiving the feedback, it sends it to the server, where the data is stored in a database.

[1155] The feedback stored in the database is analyzed using an NLP engine (spaCy) and an emotion engine (TextBlob) to extract key topics and emotions.

[1156] Based on the extracted analysis results, logic is implemented on the server to generate improvement measures corresponding to specific keywords and emotions.

[1157] An interface is constructed on the terminal side to visually present the final generated improvement measures to the user.

[1158] Hardware and software used

[1159] Smartphone device: Used to enter feedback and view improvements.

[1160] Server: Stores and analyzes feedback and generates improvement measures.

[1161] Database: Used to store feedback and analysis results.

[1162] Natural language processing engine: spaCy is used to analyze feedback topics.

[1163] Sentiment Analysis Engine: Uses TextBlob to analyze the sentiment of feedback.

[1164] Specific examples

[1165] When the user inputs feedback such as "the product description is insufficient," the terminal transmits the feedback to the server.

[1166] The server stores the received feedback in a database and then parses the feedback using spaCy and TextBlob.

[1167] As a result of the analysis, the topic of "insufficient description" and negative sentiment are extracted, and an improvement measure of "adding a detailed description of the product" is generated.

[1168] The generated improvement measures are sent to the terminal and visually displayed to the user in the form of "Please add product description."

[1169] Prompt Sentence Examples

[1170] You received feedback from users that the product page was difficult to navigate and lacked information. Based on this feedback, please analyze it using an NLP engine and a sentiment engine, and suggest specific improvements based on the resulting keywords and sentiment.

[1171] As described above, the present invention is capable of efficiently collecting and analyzing feedback from customers to generate specific improvement measures and visually presenting them in a form that takes into account the customer's feelings.

[1172] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1173] Step 1:

[1174] Users use their smartphones to input feedback and requests about products and services. The input feedback data (e.g., "The product description is insufficient") is saved on the device.

[1175] Step 2:

[1176] The terminal sends the input feedback data to the server. At this time, the feedback content and the user's identification information are included in the transmitted data. The feedback data is transferred to the server via an HTTP request.

[1177] Step 3:

[1178] The server stores the received feedback data in a database. The stored data includes the feedback content and user identification information. The database stores the feedback text, user ID, timestamp, etc.

[1179] Step 4:

[1180] The server starts natural language processing (NLP) on the stored feedback data. It uses spaCy as its NLP engine to extract the main topics of the feedback. The input is the feedback text, and the output is a list of extracted keywords. Specifically, it tokenizes the text and extracts noun phrases.

[1181] Step 5:

[1182] The server uses a sentiment analysis engine (TextBlob) to analyze the sentiment of the feedback. The input is the feedback text and the output is a sentiment score (positive, negative, neutral). The TextBlob is used to process the sentiment polarity of the text.

[1183] Step 6:

[1184] The server generates improvement measures based on the results of NLP and sentiment analysis. The input is the extracted keywords and sentiment scores, and the output is a list of specific improvement measures. Specifically, it selects and generates appropriate improvement measures from a pre-defined list of improvement candidate measures.

[1185] Step 7:

[1186] The server sends the generated remediation plan to the terminal, along with details of the remediation plan as an HTTP response. The output includes specific suggestions for the customer.

[1187] Step 8:

[1188] The device visually displays the received improvement measures to the user, using pop-up messages, notification banners, etc. Specifically, the device displays the improvement measures on the user interface based on the received data.

[1189] Step 9:

[1190] Users can then provide additional feedback and suggestions for the proposed improvements, creating a feedback loop that continually refines the actual campaign.

[1191] Through the above steps, the present invention can effectively collect and analyze customer feedback, and generate and present specific improvement measures.

[1192] 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.

[1193] 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.

[1194] 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.

[1195] [Fourth embodiment]

[1196] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1197] 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.

[1198] 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).

[1199] 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.

[1200] 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.

[1201] 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).

[1202] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1203] 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.

[1204] 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.

[1205] 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.

[1206] 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.

[1207] 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.

[1208] 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."

[1209] The present invention relates to a marketing campaign optimization system that collects feedback and requests from customers, analyzes the feedback and requests, generates improvements to the marketing campaign, and presents them to the customers. Specific embodiments for carrying out the present invention will be described below.

[1210] Program processing and behavior

[1211] 1. Collect customer feedback

[1212] User: Uses a device to enter feedback or requests about the campaign, for example, "The new product introduction article is not very appealing."

[1213] Terminal: Sends the feedback entered by the user to the server.

[1214] 2. Saving your feedback to a database

[1215] Server: Stores the received feedback in a database. The stored data includes the feedback content as well as the user's identification information.

[1216] 3. Analysis using natural language processing

[1217] Server: The stored feedback is fed into a natural language processing engine for content analysis, including sentiment assessment and topic extraction.

[1218] Server: As a result of the analysis, for example, from feedback that "the article introducing a new product is not appealing," the insight that "visual enhancement is needed" is extracted.

[1219] 4. Generate improvements

[1220] Server: Generates recommendations for improving marketing campaigns based on the analysis results, such as "add visual elements to product articles and highlight product benefits with bullet points."

[1221] 5. Providing improvement measures to users

[1222] Server: Sends the generated remediation measures to the device.

[1223] On the device: Display the received improvement recommendations in a user-friendly format, for example, "In your next product launch article, we recommend using more product photos to highlight the benefits."

[1224] 6. Re-feedback

[1225] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[1226] Specific examples

[1227] Example 1: Improving a new product introduction campaign

[1228] 1. User: Enters feedback on the campaign site saying, "The article introducing the new product is not very appealing."

[1229] 2. Device: Sends feedback to the server.

[1230] 3. Server: Stores the received feedback in a database and analyzes the issue of "not visually appealing" using natural language processing.

[1231] 4. Server: Generate an improvement plan: "Add product photos to new product introduction articles to highlight their benefits."

[1232] 5. Server: Sends the improvement plan to the device.

[1233] 6. Device: Suggest to the user, "In your next product launch article, add visuals and explain the benefits in bullet points."

[1234] Example 2: Improving a sales campaign

[1235] 1. User: Enters feedback on the online store saying, "There are not many products on sale and it's not appealing."

[1236] 2. Device: Sends feedback to the server.

[1237] 3. Server: Stores the feedback in a database and analyzes the problem of "not enough products available" using natural language processing.

[1238] 4. Server: Generate an improvement plan: "Increase the number of items on sale and introduce bundle discounts."

[1239] 5. Server: Sends the improvement plan to the device.

[1240] 6. Device: Propose to the user that "In the next sale, we will increase the number of eligible products and introduce set discounts."

[1241] In this way, the present invention can efficiently collect customer feedback, quickly analyze it, generate specific improvement measures, and present them to customers, thereby maximizing the effectiveness of marketing campaigns and increasing customer satisfaction and engagement.

[1242] The processing flow will be explained below.

[1243] Step 1:

[1244] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[1245] Step 2:

[1246] Terminal: Receives user feedback and sends feedback data to the server.

[1247] Step 3:

[1248] Server: Receives feedback sent from the device and stores it in a database, including user identification information.

[1249] Step 4:

[1250] Server: Starts parsing the stored feedback data using a natural language processing (NLP) engine, for example using an NLP library such as TextBlob or spaCy.

[1251] Step 5:

[1252] Server: Analyzes the feedback using natural language processing to extract key topics and sentiments, for example, obtaining results such as "visually unappealing."

[1253] Step 6:

[1254] Server: Identify customer requests based on the analysis results. For example, extract a request such as "New product introduction articles need visual enhancements."

[1255] Step 7:

[1256] Server: Review data from other users with similar feedback and perform trend analysis to identify common issues.

[1257] Step 8:

[1258] Server: Generates specific improvements and measures for marketing campaigns based on trend analysis results, such as adding product photos to new product introduction articles and highlighting their benefits in bullet points.

[1259] Step 9:

[1260] Server: Sends the generated remediation measures to the device.

[1261] Step 10:

[1262] On the device: Display the improvement suggestions to the user and present them in an easy-to-understand format, such as "In your next product launch article, we recommend using more product photos to highlight the benefits."

[1263] Step 11:

[1264] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[1265] Example 1

[1266] 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."

[1267] Conventional marketing campaign optimization systems have difficulty efficiently analyzing customer feedback and quickly proposing specific improvement measures. Furthermore, it is difficult to continuously and dynamically incorporate feedback, which results in insufficient improvement of customer satisfaction and engagement. Furthermore, the generated improvement measures are often not specific and not feasible.

[1268] 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.

[1269] In this invention, the server includes a means for receiving feedback and requests from customers, a means for storing the received feedback and requests in an information repository, a means for analyzing the stored feedback and requests using natural language processing, a means for generating improvement measures and policies based on the analysis results using a generative AI model, and a means for visually presenting the generated improvement measures and policies to customers. This makes it possible to efficiently collect and analyze customer feedback and quickly provide specific, actionable improvement measures. Furthermore, by forming a continuous feedback loop, the effectiveness of marketing campaigns can be maximized and customer satisfaction and engagement can be improved.

[1270] "Feedback" refers to information such as opinions, requests, and evaluations provided by customers.

[1271] "Requests" are requests for improvements or new features that customers expect from services or products.

[1272] An "information repository" is a system for storing and managing data, such as a database or storage system.

[1273] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[1274] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to automatically generate new data or suggestions.

[1275] "Improvements" are specific proposals and measures to improve existing systems and campaigns.

[1276] "Measures" are specific actions or strategies planned to achieve business goals.

[1277] "Visual presentation" means displaying information on a screen or display in a format that is easy for the user to understand.

[1278] The present invention relates to a marketing campaign optimization system that collects and analyzes feedback and requests from customers, generates improvements to the marketing campaign based on the collected feedback, and presents the improvements to the customers. Specific embodiments for carrying out the present invention will be described below.

[1279] This system mainly consists of a server, terminals, and users. The specific roles and processes of each component are shown below.

[1280] Gathering feedback

[1281] Users can use their devices to input their feedback and requests about the campaign. The device interface can be a web form, a mobile application, etc. For example, a user might input, "The article introducing the new product is not very appealing."

[1282] The terminal receives the feedback information input by the user, generates an HTTP POST request, and sends it to the server.

[1283] Feedback storage and analysis

[1284] The server stores the feedback received from the terminal in a database (information collection), and the stored data includes the feedback content, user identification information, and a timestamp.

[1285] The stored feedback data is analyzed using a natural language processing (NLP) engine (e.g., Microsoft Azure Cognitive Services text analysis API or Google Cloud Natural Language API). The server sends the feedback data to these external APIs and receives the analysis results.

[1286] As a result of the analysis, the main topics and emotional evaluations of the feedback are extracted. For example, from feedback that "the new product introduction article is not appealing," the insight that "visual appeal needs to be improved" can be obtained.

[1287] Generate improvements

[1288] The server generates specific marketing campaign improvement measures using a generative AI model (e.g., a general natural language generation model) based on the analysis results of natural language processing. For example, improvement measures such as "add visual elements to product introduction articles and emphasize the product's benefits in bullet points" are generated.

[1289] The generated improvements are formatted in a way that is easy for the user to understand.

[1290] Providing improvement measures and providing feedback

[1291] The server sends the generated remediation measures to the terminal as an HTTP response.

[1292] The device converts the received improvements into a display data structure and displays it in the UI of a web page or application, for example, "In our next new product introduction article, we'll add visual elements and explain the benefits in bullet points."

[1293] Users can then provide additional feedback or new suggestions for improvements, creating a feedback loop that allows for continuous improvement of the campaign.

[1294] Examples of prompt statements

[1295] Prompt 1: "How would you generate improvements based on customer feedback about a new product introduction article that they found less appealing?"

[1296] Prompt 2: "Explain how to generate optimal improvements based on customer feedback that feels there are not enough products in a sales campaign."

[1297] The above is a specific embodiment of the present invention. This system efficiently collects and analyzes customer feedback and can quickly provide specific and actionable improvement measures, thereby maximizing the effectiveness of marketing campaigns and improving customer satisfaction.

[1298] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1299] Step 1: Gather feedback

[1300] The user uses the terminal to input feedback and requests about the campaign, for example, "The article introducing the new product is not very appealing."

[1301] Input: Feedback text (e.g., "The new product introduction article is not very appealing.")

[1302] Action: Enter your feedback through a device interface (e.g., a web form or a mobile application) and click the "Submit" button.

[1303] Output: User feedback is sent to the device.

[1304] Step 2: Submit your feedback

[1305] The terminal receives the feedback information input by the user, generates an HTTP POST request, and sends it to the server.

[1306] Input: The feedback text entered by the user

[1307] What it does: Creates an HTTP POST request and sends it to the server with the feedback information.

[1308] Output: The feedback information is sent to the server.

[1309] Step 3: Save your feedback

[1310] The server stores the feedback received from the terminal in a database, and the stored data includes the feedback content, user identification information, and a timestamp.

[1311] Input: Feedback information sent from the device

[1312] What it does: Parses the feedback information and executes an insert query to the database to save the data.

[1313] Output: The feedback information is stored in a database.

[1314] Step 4: Analyze the feedback

[1315] The server then inputs the stored feedback data into a natural language processing (NLP) engine to analyze the content, for example, using the Microsoft Azure Cognitive Services text analysis API or the Google Cloud Natural Language API.

[1316] Input: Feedback information stored in the database

[1317] How it works: Sends feedback data to a natural language processing API and receives analysis results.

[1318] Output: Analysis results such as main topics of feedback and sentiment ratings

[1319] Step 5: Extracting insights

[1320] The server extracts key topics and insights from the feedback based on the results of natural language processing analysis. For example, from feedback such as "The article introducing a new product is not appealing," it can obtain the insight that "The visual appeal needs to be improved."

[1321] Input: Analysis results of natural language processing

[1322] What it does: Extract topics and insights from the analysis results and store them in a database.

[1323] Output: Insights and topic information

[1324] Step 6: Generate remediation measures

[1325] Based on the analysis results, the server uses a generative AI model (e.g., GPT-3) to generate specific marketing campaign improvement measures.

[1326] Input: Insights and topic information

[1327] How it works: Input insight data into a generative AI model and get output improvement measures.

[1328] Output: Specific improvement suggestions (e.g., "Add visual elements to product articles and highlight product benefits with bullet points")

[1329] Step 7: Propose improvement measures

[1330] The server transmits the generated remedial measures to the terminal.

[1331] Input: Improvements generated by a generative AI model

[1332] Behavior: Remediation data is sent to the device as an HTTP response.

[1333] Output: Remediation data is sent to the terminal.

[1334] The device converts the received remedial measures into a display data structure and displays them on a web page or application UI.

[1335] Input: Remediation data sent from the server

[1336] How it works: Received data is bound to HTML and application UI components and displayed on the screen.

[1337] Output: The remediation measures are displayed in a format that the user can understand visually.

[1338] Step 8: Re-feedback

[1339] Users can then provide additional feedback or new requests for the proposed improvements, creating a feedback loop that allows for continuous improvement of the campaign.

[1340] Input: Feedback on the improvement plan (e.g., "I agree with the improvement plan" or "I would like to add another request")

[1341] Action: Fill out the feedback form again and click the "Submit" button.

[1342] Output: New feedback is sent to the terminal and processing begins again.

[1343] (Application example 1)

[1344] 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."

[1345] Modern marketing campaigns require the rapid and effective incorporation of customer feedback to optimize the campaign. However, with conventional systems, the collection, analysis, generation, and presentation of feedback improvements were separated, making it impossible to integrate these processes. Furthermore, it was difficult to propose products and improvements tailored to individual customer needs, resulting in insufficient improvement of customer satisfaction.

[1346] 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.

[1347] In this invention, the server includes means for receiving feedback and requests from customers, means for storing the received feedback and requests in a database, means for analyzing the stored feedback and requests using natural language processing, means for generating improvement measures and policies based on the analysis results, means for visually presenting the generated improvement measures and policies to customers, and means for improving a recommendation algorithm based on feedback and making optimal product proposals for individual customers. This makes it possible to efficiently incorporate customer feedback and make personalized product proposals, thereby optimizing marketing campaigns and improving customer satisfaction.

[1348] "Customer Feedback" is input from customers providing their experiences, opinions, and requests.

[1349] A "database" is a computer system that systematically stores and manages information such as feedback and requests received from customers.

[1350] "Natural language processing" is a technology that allows computers to analyze human language and understand its meaning.

[1351] "Improvements" are specific measures developed based on customer feedback to improve marketing campaigns or services.

[1352] "Visual presentation" is a means of displaying the generated improvement measures and initiatives to the customer in an easy-to-read format.

[1353] A "recommendation algorithm" is an algorithm that analyzes a customer's past behavior and feedback to suggest the best products and services for each individual customer.

[1354] "Product suggestion" is an action that recommends products that are considered to be best suited to individual customers based on customer feedback and behavioral data.

[1355] This invention is realized using a smartphone application called a “Personalized Shopping Assistant.” A detailed embodiment of this system will be described below.

[1356] A customer (user) starts the app on their smartphone and enters their opinions and requests into the feedback form. For example, they might enter feedback such as "There are too few items on sale recently." The device then sends this input to the server.

[1357] The server stores the received feedback in a database, which serves to store and manage customer feedback in an organized manner.

[1358] The server then inputs the saved feedback into a natural language processing (NLP) engine and analyzes its content. For analysis, existing NLP engines such as Google Cloud Natural Language API and Amazon Comprehend are used. As a result of the analysis, sentiment ratings and topics of the feedback are extracted. For example, a sentiment rating of "visually unappealing" is obtained.

[1359] Based on the analysis results, the server generates improvement measures for the marketing campaign. Specific improvement measures are proposed using a generative AI model. For example, the generated improvement measures might be to "increase the number of products on sale and introduce new discount sets."

[1360] The server then sends the generated improvement plan to the terminal, which visually displays the received improvement plan to the customer. For example, it may display, "In the next sale, we will expand the range of eligible products and introduce a new discount set."

[1361] Furthermore, the server uses the feedback to improve its recommendation algorithm and make optimal product suggestions for each individual customer, such as "The following products are recommended for you."

[1362] This will enable efficient incorporation of customer feedback and personalized product recommendations, optimizing marketing campaigns and improving customer satisfaction.

[1363] Examples of concrete examples and prompts

[1364] As a concrete example, imagine a user who opens the smartphone app "Personalized Shopping Assistant" enters "There are too few recent sale items" into the feedback form. This feedback is sent to the server and analyzed by Amazon Comprehend. Based on the analysis results, the user is given a specific improvement suggestion, such as "In the next sale, expand the range of eligible products and introduce a new discount set."

[1365] Example prompt sentence:

[1366] Please analyze the following feedback statement and suggest improvements:

[1367] Feedback: "There are too few sale items these days."

[1368] These prompts enable the generative AI model to provide further actionable insights and recommendations for improvement, leading to improved customer satisfaction and effective optimization of marketing campaigns.

[1369] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1370] Step 1:

[1371] A user launches the app on their smartphone. The user enters their opinions and requests into the feedback form. For example, the user might enter feedback such as "There are too few items on sale recently." The input data is in the form of a string, and the device sends this data to the server.

[1372] Step 2:

[1373] The device sends the feedback entered by the user to the server. This data transfer uses the HTTPS protocol, and the sent data is in JSON format. The server stores the received feedback in a database. When saving, the user's identification information is also saved.

[1374] Step 3:

[1375] The server inputs the saved feedback into a natural language processing engine (e.g., Google Cloud Natural Language API or Amazon Comprehend) and analyzes its content. The main task of the analysis is to evaluate the sentiment of the text data and extract topics. For example, the topic "visually unattractive" and its sentiment evaluation are obtained.

[1376] Step 4:

[1377] The server generates improvement measures for the marketing campaign based on the analysis results from the natural language processing engine. For example, the generated improvement measures might be to "increase the number of products on sale and introduce new discount sets." The natural language generation model used here is a generative AI model. It inputs a prompt sentence and outputs specific improvement measures.

[1378] Step 5:

[1379] The server sends the generated improvement measures to the terminal. The terminal visually displays the received improvement measures to the user. For example, it may display "In the next sale, we will expand the range of eligible products and introduce a new discount set." The display format is a visually easy-to-understand UI design, and a user interface framework (e.g., React Native) is used.

[1380] Step 6:

[1381] The server improves the recommendation algorithm based on the feedback and makes optimal product suggestions for each individual customer. In this process, past feedback data and behavioral data are integrated and the improved recommendation algorithm is applied. For example, the server may make suggestions to the user such as, "The following products are recommended for you." This allows the optimal product list to be updated in real time, enabling personalized product suggestions.

[1382] Through these steps, it becomes possible to effectively incorporate user feedback and provide personalized product recommendations, optimizing marketing campaigns and improving customer satisfaction.

[1383] 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.

[1384] The present invention relates to a marketing campaign optimization system that collects feedback and requests from customers, analyzes the collected feedback and requests, generates improvements to the marketing campaign, and presents them to the customers. The present invention further incorporates an emotion engine that recognizes the emotions in the customer feedback and requests. Specific embodiments for implementing the present invention will be described below.

[1385] Program processing and behavior

[1386] 1. Collect customer feedback

[1387] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[1388] Terminal: Receives user feedback and sends feedback data to the server.

[1389] 2. Saving your feedback to a database

[1390] Server: Stores the received feedback in a database. The stored data includes the feedback content as well as the user's identification information.

[1391] 3. Analysis using natural language processing and sentiment engines

[1392] Server: Starts parsing the stored feedback data using a natural language processing (NLP) engine, for example using an NLP library such as TextBlob or spaCy.

[1393] Server: Analyzes the feedback content using NLP and extracts key topics and sentiments, for example, "visually unappealing."

[1394] Server: The emotion engine recognizes emotional elements in the feedback. For example, it detects the emotion "dissatisfied."

[1395] 4. Generate improvement measures and reflect sentiment data

[1396] Server: Based on the analysis results of NLP and the emotion engine, it generates specific improvement measures that take into account customer requests and emotions. For example, it suggests improvement measures such as "add product photos to new product introduction articles and emphasize their benefits with bullet points" and "use designs that evoke positive emotions."

[1397] 5. Providing improvement measures to users

[1398] Server: Sends the generated remediation measures to the device.

[1399] On-device: Display the received improvement recommendations in a user-friendly format, such as "In your next new product introduction article, we recommend using more product photos and emphasizing the benefits. Also, consider creating a design that evokes positive emotions."

[1400] 6. Re-feedback

[1401] Users: Return to provide additional feedback or new requests for suggested improvements, creating a feedback loop that continually improves the campaign.

[1402] Specific examples

[1403] Example 1: Improving a new product introduction campaign

[1404] 1. User: Enters feedback on the campaign site saying, "The article introducing the new product is not very appealing."

[1405] 2. Device: Sends feedback to the server.

[1406] 3. Server: The received feedback is stored in a database, and the natural language processing engine analyzes whether the feedback is visually unattractive, and the emotion engine recognizes the emotion of "dissatisfaction."

[1407] 4. Server: Generate the following improvements: "Add product photos to new product introduction articles to highlight their benefits" and "Use designs that elicit positive emotions."

[1408] 5. Server: Sends the improvement plan to the device.

[1409] 6. Device: Suggest to users, "In your next product launch article, we recommend using more product photos and highlighting the benefits. Also, consider creating a design that evokes positive emotions."

[1410] Example 2: Improving a sales campaign

[1411] 1. User: Enters feedback on the online store saying, "There are not many products on sale and it's not appealing."

[1412] 2. Device: Sends feedback to the server.

[1413] 3. Server: The feedback is stored in a database, the natural language processing engine analyzes that there are few eligible products, and the emotion engine recognizes the emotion of "disappointment."

[1414] 4. Server: Generates the following improvement measures: "Increase the number of items on sale and introduce bundle discounts" and "Add rewards that elicit positive emotions."

[1415] 5. Server: Sends the improvement plan to the device.

[1416] 6. Device: Suggest to the user, "For your next sale, we recommend expanding the selection and introducing bundled discounts. Also, add rewards that evoke positive emotions."

[1417] In this way, the present invention can efficiently collect and analyze customer feedback to generate specific improvement measures, and by taking customer sentiment into account, can realize more effective improvements to marketing campaigns, thereby increasing customer satisfaction and engagement and maximizing the results of marketing campaigns.

[1418] The processing flow will be explained below.

[1419] Step 1:

[1420] User: Enter their feedback or requests about the campaign into the device. For example, they might enter, "The new product introduction article isn't very appealing."

[1421] Step 2:

[1422] Terminal: Receives user feedback and sends feedback data to the server.

[1423] Step 3:

[1424] Server: Receives feedback sent from the device and stores the feedback and user identification information in a database.

[1425] Step 4:

[1426] Server: Starts analyzing the stored feedback data using a natural language processing (NLP) engine. For example, it uses an NLP library such as TextBlob or spaCy to analyze the feedback content.

[1427] Step 5:

[1428] Server: Analyzes the feedback content using natural language processing and extracts key topics and sentiments. For example, the analysis results "visually unappealing."

[1429] Step 6:

[1430] Server: Uses an emotion engine to recognize emotional elements in the feedback. For example, it detects the emotion "dissatisfied."

[1431] Step 7:

[1432] Server: Based on the results of natural language processing and emotion engine analysis, the server generates specific improvement measures that take into account customer requests and emotions. For example, it suggests an improvement such as "adding product photos to new product introduction articles and emphasizing their benefits in bullet points."

[1433] Step 8:

[1434] Server: Conducts trend analysis and integrates multiple feedback data to identify common issues, allowing for adjustments to be made to overall improvements.

[1435] Step 9:

[1436] Server: Adjusts the improvement plan and develops the optimal improvement plan that takes into account the sentiment data. For example, add a suggestion such as "Use designs that elicit positive emotions."

[1437] Step 10:

[1438] Server: Sends the generated final remediation to the device.

[1439] Step 11:

[1440] On device: Display the received improvement recommendations in a user-friendly format, such as "In your next product launch article, please consider using more product photos, explaining benefits in bullet points, and using a design that evokes positive emotions."

[1441] Step 12:

[1442] User: Re-enter the suggested improvement with additional feedback or new requests, such as "I'll try that strategy in my next post."

[1443] Step 13:

[1444] Device: Receive feedback again and send it to the server.

[1445] Step 14:

[1446] Server: Again, the received feedback is stored in a database and the process from step 3 to step 13 above is repeated to continuously improve the campaign.

[1447] Example 2

[1448] 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."

[1449] Modern marketing campaigns require the rapid and effective collection of customer feedback, accurate analysis of that feedback, and the development of improvement measures. Furthermore, by taking into account customer emotional factors, it is necessary to propose more accurate improvement measures and increase customer satisfaction. However, with conventional systems, the process from collecting feedback to analyzing it and proposing improvement measures relies on manual work, which takes a great deal of time and effort and is hardly efficient.

[1450] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving feedback and requests from customers, a means for storing the received feedback and requests in a database, a means for analyzing the stored feedback and requests using natural language processing, a means for recognizing emotions in the feedback and requests, a means for generating improvement measures based on the analysis results of the natural language processing and emotion recognition, and a means for visually presenting the generated improvement measures. This makes it possible to automate the process from collecting feedback to analyzing it and presenting improvement measures, thereby realizing efficient and effective optimization of marketing campaigns that also take customer emotions into consideration.

[1451] "Feedback" refers to opinions, requests, and evaluations provided by customers.

[1452] A "request" is a proposal for an improvement, new feature, or service that a customer wants for a particular product or service.

[1453] "Means" refers to a method, device, or process for achieving a specific purpose.

[1454] A "database" is a system for efficiently storing, managing, and retrieving data.

[1455] "Natural language processing" is a technology that allows computers to understand human language and analyze text.

[1456] "Emotion recognition" is a technology that detects and classifies emotional states from data such as text and voice.

[1457] "Analysis results" refers to the insights and information obtained after analyzing data.

[1458] "Improvements" are specific actions or methods proposed to resolve existing problems.

[1459] "Visually presenting" means displaying information in a format that is easy for the user to view.

[1460] A "marketing campaign" is a series of activities designed to promote a particular product or service.

[1461] The present invention relates to a marketing campaign optimization system that collects customer feedback and requests, analyzes them, and generates improvements to the marketing campaign. The system incorporates an emotion engine that recognizes the emotions in the feedback and requests. Specific embodiments for implementing the present invention will be described below.

[1462] System Configuration

[1463] Hardware and Software Configuration

[1464] Users: Enter feedback using a computer, mobile device, or other device.

[1465] Device: Receives user feedback and sends it to the server. Software used includes a web browser and dedicated applications.

[1466] Server: Receives feedback data and stores it in a database. Python scripts are used for data analysis, and libraries such as TextBlob and spaCy are used for natural language processing (NLP). A dedicated emotion recognition engine is used for sentiment analysis.

[1467] Data processing and calculation

[1468] Collecting and storing feedback

[1469] User: Enter feedback or requests about the campaign into the terminal. For example, enter feedback such as "The article introducing the new product is not very appealing."

[1470] Terminal: Receives feedback from the user, stores it temporarily, and then sends the feedback data to the server using an HTTP POST request.

[1471] Feedback Analysis

[1472] Server: Stores the received feedback data in a database and runs an analysis engine. Specifically, it uses a natural language processing engine to analyze the text and extract key topics and sentiment. It uses NLP libraries such as TextBlob and spaCy.

[1473] Server: Uses an emotion recognition engine to identify emotional elements in the feedback, for example, detecting emotions such as "dissatisfaction" or "disappointment."

[1474] Generate improvements

[1475] Server: Based on the analysis results, a generative AI model is used to generate specific improvement measures, such as GPT-3.

[1476] Server: Enters the prompt "The user is dissatisfied with the new product introduction article. Please suggest improvements," and obtains improvements from the generative AI model.

[1477] Proposal of improvement measures

[1478] Server: Sends the generated remediation measures to the device.

[1479] On the device: Visually present the received improvement recommendations through the user interface, for example, by displaying a message such as, "In your next new product introduction article, we recommend that you use more product photos and emphasize the benefits. Also, consider a design that evokes positive emotions."

[1480] Handling re-feedback

[1481] Users: Enter additional feedback or new requests based on the proposed improvements, creating a feedback loop that allows for continuous campaign improvement.

[1482] Specific examples

[1483] Example 1: Improving a new product introduction campaign

[1484] 1. User: Enters feedback saying, "The new product introduction article isn't very appealing."

[1485] 2. Device: Sends feedback to the server.

[1486] 3. Server: Stores the received feedback in a database and analyzes it using a natural language processing engine and emotion recognition engine.

[1487] 4. Server: Generate the following improvements: "Add product photos to new product introduction articles to highlight their benefits" and "Use designs that elicit positive emotions."

[1488] 5. Server: Sends the remediation plan to the device.

[1489] 6. Device: Suggest to users, "In your next product launch article, we recommend using more product photos and highlighting the benefits. Also, consider creating a design that evokes positive emotions."

[1490] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1491] Step 1: Gather feedback

[1492] User: Enter feedback or requests about the campaign into the terminal. For example, enter feedback such as "The article introducing the new product is not very appealing."

[1493] Input: The feedback text entered by the user.

[1494] Output: Feedback data.

[1495] On the device: Receive feedback from the user, temporarily store it, and then send the feedback data to the server using an HTTP POST request.

[1496] Step 2: Store feedback in a database

[1497] Server: Receives received feedback data and generates a log entry acknowledging receipt.

[1498] Input: Feedback data sent from the device.

[1499] Output: Feedback data stored in a database.

[1500] Server: The feedback data is saved in the database using the INSERT statement. The data saved in the database also includes the user's identification information.

[1501] Step 3: Analyze the feedback data

[1502] Server: Retrieves new feedback entries in the database and triggers the Natural Language Processing (NLP) engine using a Python script and TextBlob and spaCy as NLP libraries.

[1503] Input: Feedback data retrieved from the database.

[1504] Output: Analysis results (major topics and sentiment).

[1505] What it does: The NLP engine analyzes the feedback text and extracts key topics. The emotion recognition engine is used to recognize the emotional components of the feedback (e.g., "dissatisfied").

[1506] Step 4: Generate remediation measures

[1507] Server: Based on the analysis results of the NLP and emotion recognition engine, a generative AI model (e.g., GPT-3) is used to generate specific improvement measures.

[1508] Input: Analysis results (major topics and sentiment).

[1509] Output: Remedies.

[1510] Specific behavior: The prompt sentence "The user is dissatisfied with the new product introduction article. Please suggest improvements" is input into the generative AI model to generate improvements. For example, a specific improvement suggestion is obtained: "Add product photos to the new product introduction article and highlight its benefits."

[1511] Step 5: Submit and present your remediation plan

[1512] Server: Sends the generated remediation to the device using an HTTP POST request.

[1513] Input: The generated remediation measures.

[1514] Output: Submitted remediation.

[1515] Device: Visually present the received improvement recommendations through the user interface. For example, display a message such as, "In your next new product introduction article, we recommend using more product photos and emphasizing the benefits. Also, consider designing it to evoke positive emotions."

[1516] Step 6: Processing re-feedback

[1517] Users: Re-enter any additional feedback or new requests for the proposed improvements.

[1518] Input: Any additional feedback entered by the user.

[1519] Output: The collected feedback data again.

[1520] What it does: The re-entered feedback data is then sent back to the server by the device, and the feedback collection and storage process is repeated, creating a feedback loop that allows for continuous campaign improvement.

[1521] (Application example 2)

[1522] 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."

[1523] In conventional marketing campaign optimization systems, analysis and improvement plan generation based on collected customer feedback was often done manually, resulting in a waste of time and effort. Furthermore, the system for properly reflecting customer sentiment was inadequate, making it difficult to improve customer satisfaction. Furthermore, there was no established method for efficiently collecting and presenting feedback using smart devices.

[1524] 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.

[1525] In this invention, the server includes means for receiving feedback and requests from customers, means for storing the received feedback and requests in a database, means for analyzing the stored feedback and requests using natural language processing, means for generating improvement measures and policies based on the analysis results, means for visually presenting the generated improvement measures and policies to customers, and means for efficiently collecting and presenting feedback from customers using a smart device. This automates the collection and analysis of feedback, making it possible to quickly generate and present specific improvement measures that take customer sentiment into consideration.

[1526] "Customer" refers to a person who uses a service or purchases a product.

[1527] "Feedback" refers to opinions and ratings provided by customers regarding services and products.

[1528] "Requests" refer to improvements or additional features that customers expect from a particular service or product.

[1529] "Database" refers to a system for systematically storing and managing collected feedback and requests.

[1530] "Natural language processing" refers to the technology of understanding and analyzing feedback and requests as human language.

[1531] "Improvement measures" refer to specific measures to improve services or products based on feedback and requests.

[1532] "Visually presenting" refers to displaying the generated improvement measures and initiatives in a way that is easy for customers to see.

[1533] "Smart devices" refers to devices with internet connectivity, such as smartphones, smart glasses, and head-mounted displays.

[1534] "Collection" refers to the act of gathering feedback and requests from customers.

[1535] "Presenting" refers to the act of displaying the collected information and generated improvement measures to the user.

[1536] To implement the present invention, the following steps are followed to implement a program using the specified hardware and software.

[1537] 1. System Configuration

[1538] Customers use their smartphones to enter feedback and requests about products and services.

[1539] This feedback is sent by the terminal to the server.

[1540] The server stores the received feedback in a database and then analyzes the stored data using a natural language processing (NLP) engine, spaCy, and TextBlob for sentiment analysis.

[1541] The server generates improvement measures and policies based on the analysis results of the NLP and emotion engine. This involves extracting key topics and emotions and generating specific improvement proposals based on them.

[1542] The server transmits the generated remedial measures back to the terminal, which visually displays the remedial measures to the customer.

[1543] 2. Program Implementation

[1544] Use smart devices to efficiently gather feedback from users and suggest improvements.

[1545] After receiving the feedback, it sends it to the server, where the data is stored in a database.

[1546] The feedback stored in the database is analyzed using an NLP engine (spaCy) and an emotion engine (TextBlob) to extract key topics and emotions.

[1547] Based on the extracted analysis results, logic is implemented on the server to generate improvement measures corresponding to specific keywords and emotions.

[1548] An interface is constructed on the terminal side to visually present the final generated improvement measures to the user.

[1549] Hardware and software used

[1550] Smartphone device: Used to enter feedback and view improvements.

[1551] Server: Stores and analyzes feedback and generates improvement measures.

[1552] Database: Used to store feedback and analysis results.

[1553] Natural language processing engine: spaCy is used to analyze feedback topics.

[1554] Sentiment Analysis Engine: Uses TextBlob to analyze the sentiment of feedback.

[1555] Specific examples

[1556] When the user inputs feedback such as "the product description is insufficient," the terminal transmits the feedback to the server.

[1557] The server stores the received feedback in a database and then parses the feedback using spaCy and TextBlob.

[1558] As a result of the analysis, the topic of "insufficient description" and negative sentiment are extracted, and an improvement measure of "adding a detailed description of the product" is generated.

[1559] The generated improvement measures are sent to the terminal and visually displayed to the user in the form of "Please add product description."

[1560] Prompt Sentence Examples

[1561] You received feedback from users that the product page was difficult to navigate and lacked information. Based on this feedback, please analyze it using an NLP engine and a sentiment engine, and suggest specific improvements based on the resulting keywords and sentiment.

[1562] As described above, the present invention is capable of efficiently collecting and analyzing feedback from customers to generate specific improvement measures and visually presenting them in a form that takes into account the customer's feelings.

[1563] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1564] Step 1:

[1565] Users use their smartphones to input feedback and requests about products and services. The input feedback data (e.g., "The product description is insufficient") is saved on the device.

[1566] Step 2:

[1567] The terminal sends the input feedback data to the server. At this time, the feedback content and the user's identification information are included in the transmitted data. The feedback data is transferred to the server via an HTTP request.

[1568] Step 3:

[1569] The server stores the received feedback data in a database. The stored data includes the feedback content and user identification information. The database stores the feedback text, user ID, timestamp, etc.

[1570] Step 4:

[1571] The server starts natural language processing (NLP) on the stored feedback data. It uses spaCy as its NLP engine to extract the main topics of the feedback. The input is the feedback text, and the output is a list of extracted keywords. Specifically, it tokenizes the text and extracts noun phrases.

[1572] Step 5:

[1573] The server uses a sentiment analysis engine (TextBlob) to analyze the sentiment of the feedback. The input is the feedback text and the output is a sentiment score (positive, negative, neutral). The TextBlob is used to process the sentiment polarity of the text.

[1574] Step 6:

[1575] The server generates improvement measures based on the results of NLP and sentiment analysis. The input is the extracted keywords and sentiment scores, and the output is a list of specific improvement measures. Specifically, it selects and generates appropriate improvement measures from a pre-defined list of improvement candidate measures.

[1576] Step 7:

[1577] The server sends the generated remediation plan to the terminal, along with details of the remediation plan as an HTTP response. The output includes specific suggestions for the customer.

[1578] Step 8:

[1579] The device visually displays the received improvement measures to the user, using pop-up messages, notification banners, etc. Specifically, the device displays the improvement measures on the user interface based on the received data.

[1580] Step 9:

[1581] Users can then provide additional feedback and suggestions for the proposed improvements, creating a feedback loop that continually refines the actual campaign.

[1582] Through the above steps, the present invention can effectively collect and analyze customer feedback, and generate and present specific improvement measures.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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).

[1590] 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.

[1591] 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."

[1592] 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.

[1593] 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).

[1594] 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.

[1595] 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.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] 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.

[1602] 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.

[1603] 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.

[1604] The following is further disclosed regarding the above embodiment.

[1605] (Claim 1)

[1606] A means of receiving feedback and requests from customers;

[1607] A means of storing received feedback and requests in a database;

[1608] A means of analyzing stored feedback and requests using natural language processing;

[1609] A means for generating improvement measures and policies based on the analysis results;

[1610] A means to visually present the generated improvement measures and initiatives to the customer,

[1611] Marketing campaign optimization system including.

[1612] (Claim 2)

[1613] 10. The system of claim 1, further comprising means for consolidating feedback received from customers and performing trend analysis.

[1614] (Claim 3)

[1615] 10. The system of claim 1, further comprising means for receiving and reanalyzing additional feedback from the customer regarding the generated improvements and measures.

[1616] "Example 1"

[1617] (Claim 1)

[1618] A means of receiving feedback and requests from customers;

[1619] a means for storing received feedback and requests in an information repository;

[1620] A means of analyzing stored feedback and requests using natural language processing;

[1621] A means of generating improvement measures and policies based on the analysis results using an AI model, and

[1622] A means to visually present the generated improvement measures and initiatives to the customer,

[1623] A system including:

[1624] (Claim 2)

[1625] 10. The system of claim 1, further comprising means for consolidating feedback received from customers and performing trend analysis.

[1626] (Claim 3)

[1627] 10. The system of claim 1, further comprising means for receiving and reanalyzing additional feedback from the customer regarding the generated improvements and measures.

[1628] "Application Example 1"

[1629] (Claim 1)

[1630] A means of receiving feedback and requests from customers;

[1631] A means of storing received feedback and requests in a database;

[1632] A means of analyzing stored feedback and requests using natural language processing;

[1633] A means for generating improvement measures and policies based on the analysis results;

[1634] A means to visually present the generated improvement measures and initiatives to the customer,

[1635] A means to improve recommendation algorithms based on feedback and make optimal product suggestions to individual customers,

[1636] A system including:

[1637] (Claim 2)

[1638] 10. The system of claim 1, further comprising means for consolidating feedback received from customers and performing trend analysis.

[1639] (Claim 3)

[1640] 10. The system of claim 1, further comprising means for receiving and reanalyzing additional feedback from the customer regarding the generated improvements and measures.

[1641] "Example 2: Combining Emotion Engines"

[1642] (Claim 1)

[1643] A means of receiving feedback and requests from customers;

[1644] A means of storing received feedback and requests in a database;

[1645] A means of analyzing stored feedback and requests using natural language processing;

[1646] A means of recognizing the emotions of feedback and requests;

[1647] A means for generating remedial measures based on the analysis results of natural language processing and emotion recognition;

[1648] a means for visually presenting the generated improvements;

[1649] A system including:

[1650] (Claim 2)

[1651] 10. The system of claim 1, further comprising means for consolidating feedback received from customers and performing trend analysis.

[1652] (Claim 3)

[1653] 10. The system of claim 1, further comprising means for receiving and reanalyzing additional feedback from the customer regarding the generated improvements and measures.

[1654] "Application example 2 when combining emotion engines"

[1655] (Claim 1)

[1656] A means of receiving feedback and requests from customers;

[1657] A means of storing received feedback and requests in a database;

[1658] A means of analyzing stored feedback and requests using natural language processing;

[1659] A means for generating improvement measures and policies based on the analysis results;

[1660] A means to visually present the generated improvement measures and initiatives to the customer,

[1661] A means to efficiently collect and present customer feedback using smart devices;

[1662] A system including:

[1663] (Claim 2)

[1664] 10. The system of claim 1, further comprising means for consolidating feedback received from customers and performing trend analysis.

[1665] (Claim 3)

[1666] 10. The system of claim 1, further comprising means for receiving and reanalyzing additional feedback from the customer regarding the generated improvements and measures. [Explanation of symbols]

[1667] 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 receiving feedback and requests from customers; A means of storing received feedback and requests in a database; A means of analyzing stored feedback and requests using natural language processing; A means for generating improvement measures and policies based on the analysis results; A means to visually present the generated improvement measures and initiatives to the customer, Marketing campaign optimization system including.

2. 10. The system of claim 1, further comprising means for synthesizing feedback received from customers and performing trend analysis.

3. 10. The system of claim 1, further comprising means for receiving and reanalyzing additional feedback from the customer regarding the generated improvements and measures.

Images