Server and method for providing narrative and new chart based on chart for data

Abstract

To disclose a server and a method for providing a narrative and a new chart based on a chart for data.SOLUTION: A server according to the present disclosure receives statistical data, generates a first chart for visualizing a value of the statistical data, generates a first narrative for visualizing the content of analysis predicted by analyzing the first chart into a text based on the first chart and at least one statistical algorithm, and generates a new second chart for visualizing the values of the statistical data related to the first narrative.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to electronic devices and methods of operation thereof, and more particularly to a server and method for providing narratives and new charts based on charts for data. [Background technology]

[0002] Data analysis methods can be broadly divided into two categories. The first is automatic pattern recognition using traditional statistical techniques and machine learning algorithms. The second is exploratory data analysis, which is the process of quickly exploring various phenomena in given data in a business context without any hypotheses to find patterns. These two methods are not mutually exclusive, but rather complement each other to help understand data, draw conclusions, and uncover action items. However, it is difficult for users to perform such tasks. Statistics and machine learning are the domain of experts, and exploratory data analysis, i.e. the entire process of using data to draw charts, understanding the charts, and asking the next question based on the understanding derived, is not easy.

[0003] Therefore, education to develop the ability of in-house personnel to use data, known as "data literacy," is on the rise, but it is very difficult for busy employees to take time out of their day to learn data analysis. Educators must learn how to draw charts, that is, what kind of charts should be drawn in what situations and how they should be drawn. In order to draw the most appropriate chart for a given question, educators must understand what process should be followed in the software used to draw the chart. Educators must also understand how to arrange each element of data visualization (called aesthetics), such as the X-axis and Y-axis. Educators must also understand chart comprehension, that is, what facts should be extracted from a given chart and what conclusions should be drawn. Charts are mainly composed of numbers (information) and visual elements that correspond to the numbers, but educators must be able to understand what information is important, what the meaning of the information is, and how to analyze it in comparison with other information. Educators must be able to ask the next question, that is, the analysis derived from the chart will inevitably provoke additional questions. For example, given data, people usually have a "first question" that is tailored to their business context, but then they ask the second and third questions, "Why does that difference exist?", and then they have to go through a long process of tracing the logical flow to find the answer. However, the problem is that asking good questions that can find the factors that induce such differences requires long experience and skill. Therefore, even if there are good tools for visualization, the task of exploring, understanding, and drawing conclusions from data generated in the workplace (so-called EDA) is difficult for ordinary office workers. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Korean Patent No. 10-85014 (Published on April 30, 2019) Summary of the Invention [Problem to be solved by the invention]

[0005] The present disclosure has been made in consideration of the above circumstances, and its purpose is to provide a method and server for solving cost issues through artificial intelligence and developing person / aptitude questions that are suitable for individuals by additionally utilizing personal behavioral information, rather than presenting general questions.

[0006] The problems that the present disclosure is intended to solve are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0007] In one aspect, the server of the present disclosure includes a communication unit configured to communicate with a terminal, a memory storing algorithm data for at least one statistical algorithm, and a processor configured to provide a narrative and a new chart based on the chart for the data, the processor generates a first chart for visualizing values ​​of the first statistical data and values ​​of the second statistical data on a first coordinate axis indicating values ​​of the first statistical data and a second coordinate axis indicating values ​​of the second statistical data based on the first statistical data and the second statistical data received from the terminal via the communication unit, analyzes values ​​of the first statistical data and values ​​of the second statistical data in the first chart based on the first chart and the at least one statistical algorithm, generates at least one first narrative for visualizing in text the contents of the analysis predicted by analyzing the first chart while indicating which specific subcategory the information is about in the first chart, generates a new second chart for visualizing values ​​of the statistical data related to the first narrative based on the at least one first narrative, and provides the first chart, the first narrative, and the second chart to the terminal via the communication unit.

[0008] In another aspect, a method for providing a narrative and a new chart based on a chart for data of the present disclosure includes receiving first statistical data and second statistical data; generating a first chart based on the first statistical data and the second statistical data for visualizing values ​​of the first statistical data and values ​​of the second statistical data on a first coordinate axis indicating values ​​of the first statistical data and a second coordinate axis indicating values ​​of the second statistical data; analyzing values ​​of the first statistical data and values ​​of the second statistical data in the first chart based on the first chart and at least one statistical algorithm; generating at least one first narrative for visualizing in text the content of the analysis predicted by analyzing the first chart while indicating which specific subcategory the information is about in the first chart; generating a new second chart based on the at least one first narrative for visualizing values ​​of statistical data related to the first narrative; and providing the first chart, the first narrative, and the second chart. Effect of the Invention

[0009] The present disclosure has the effect of making it easier for users, even non-experts, to understand charts.

[0010] Another advantage of the present disclosure is that it allows users to achieve a high level of data understanding with a minimal investment of time, effort, and intelligence.

[0011] The effects of the present disclosure are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 illustrates a system according to the present disclosure. [Diagram 2] FIG. 2 is a diagram illustrating a configuration of a server in FIG. [Diagram 3] FIG. 1 is a flow diagram illustrating a method according to the present disclosure. [Figure 4]2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Diagram 5] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 6] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 7] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 8] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 9] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 10] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 11] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 12] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 13] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 14] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 15] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 16] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 17] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. [Figure 18] 2 is a diagram showing an example of a user interface of various embodiments provided by the server of FIG. 1. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] The same reference numerals refer to the same components throughout this disclosure. This disclosure does not describe all the components of the embodiments, and general content in the technical field to which this disclosure pertains or content that overlaps in the embodiments is omitted. The terms "part, module, member, block" used in the specification can be realized in software or hardware, and depending on the embodiment, multiple "parts, modules, members, blocks" may be realized as one component, or one "part, module, member, block" may include multiple components.

[0014] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, including connection via a wireless communication network.

[0015] Furthermore, when a part is described as "comprising" a certain component, this does not mean that it excludes other components, but that it may further include other components, unless specifically stated to the contrary.

[0016] Throughout this specification, when an element is referred to as being "on" another element, this includes not only when the element is in contact with the other element, but also when there is another element between the two elements.

[0017] The terms "first", "second", etc. are used to distinguish one component from another component, and the components are not limited to the terms described above.

[0018] The singular expression includes the plural expression unless the context clearly dictates otherwise.

[0019] In each step, the identifying numbers are used for convenience of description, and the identifying numbers do not describe the order of each step, and each step may be performed in a different order than specified, unless the context clearly dictates a particular order.

[0020] Hereinafter, the working principle and embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0021] In this specification, the term "device according to the present disclosure" includes all of the various devices that can perform computation and provide a result to a user. For example, the device according to the present disclosure may include any one of a computer, a server device, and a portable terminal.

[0022] Here, the computer may include, for example, a notebook computer, a desktop computer, a laptop computer, a tablet PC, a slate PC, etc. equipped with a web browser.

[0023] The server device is a server that communicates with external devices and processes information, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, a web server, etc.

[0024] The portable terminal may be, for example, a wireless communication device that ensures portability and mobility, and may include any kind of handheld-based wireless communication device such as a Personal Communication System (PCS), Global System for Mobile Communications (GSM), Personal Digital Cellular (PDC), Personal Handyphone System (PHS), Personal Digital Assistant (PDA), International Mobile Telecommunication (IMT)-2000, Code Division Multiple Access (CDMA)-2000, W-Code Division Multiple Access (W-CDMA), Wireless Broadband Internet (WiBro) terminal, a smartphone, etc., and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, a contact lens, or a head-mounted device (HMD).

[0025] The functions related to artificial intelligence according to the present disclosure operate via a processor and a memory. The processor may be configured with one or more processors. In this case, the one or more processors may be general-purpose processors such as CPU, AP, DSP (Digital Signal Processor), etc., graphic dedicated processors such as GPU, VPU (Vision Processing Unit), or artificial intelligence dedicated processors such as NPU. The one or more processors control the processing of input data according to predefined operating rules or artificial intelligence models stored in the memory. Alternatively, if the one or more processors are artificial intelligence dedicated processors, the artificial intelligence dedicated processors may be designed into a hardware structure specialized for processing a specific artificial intelligence model.

[0026] The predefined behavioral rules or artificial intelligence models are characterized by being generated through learning. Here, "generated through learning" means that a basic artificial intelligence model is trained by a learning algorithm using a large amount of learning data to generate predefined behavioral rules or artificial intelligence models that are set to execute a desired characteristic (or purpose). Such learning may be performed by the device itself on which the artificial intelligence according to the present disclosure is executed, or may be performed via a separate server and / or system. Examples of the learning algorithm include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the above examples.

[0027] The artificial intelligence model may be composed of a plurality of neural network layers. Each of the plurality of neural network layers has a plurality of weight values, and performs a neural network operation through an operation between a result of an operation of a previous layer and the plurality of weight values. The plurality of weight values ​​of the plurality of neural network layers may be optimized according to a learning result of the artificial intelligence model. For example, the plurality of weight values ​​may be updated so that a loss value or a cost value acquired in the artificial intelligence model during the learning process is reduced or minimized. The artificial neural network may include a deep neural network (DNN), such as a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or a deep Q-network, but is not limited to the above examples.

[0028] According to an exemplary embodiment of the present disclosure, the processor may realize artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that allows a machine to learn by replicating human biological neurons. Methodologies of artificial intelligence can be classified into supervised learning, in which input data and output data are both provided as training data according to a learning method, and an answer (output data) to a problem (input data) is determined; unsupervised learning, in which only input data is provided without output data, and an answer (output data) to a problem (input data) is not determined; and reinforcement learning, in which a reward is given from an external environment every time a certain action is taken in a current state, and learning is performed in a direction to maximize such reward. Furthermore, artificial intelligence methodologies can be categorized by architecture, which is the structure of the learning model, and the architectures of widely used deep learning technologies can be categorized into convolutional neural networks (CNNs), recurrent neural networks (RNNs), Transformers, generative adversarial networks (GANs), etc.

[0029] The device and system may include an artificial intelligence model. The artificial intelligence model may be one artificial intelligence model, or may be realized as multiple artificial intelligence models. The artificial intelligence model may be configured with a neural network (or an artificial neural network) and may include a statistical learning algorithm that mimics biological nerves in machine learning and cognitive science. A neural network may refer to a general model in which artificial neurons (nodes) that form a network with synaptic connections change the strength of synaptic connections through learning and have the ability to solve problems. Neurons in a neural network may include a combination of weight values ​​or biases. A neural network may include one or more layers that are configured with one or more neurons or nodes. As an example, the device may include an input layer, a hidden layer, and an output layer. The neural network that constitutes the device can infer a result to be predicted from an arbitrary input by changing the weight values ​​of neurons through learning.

[0030] The processor may generate a neural network, train or learn a neural network, perform a calculation based on received input data, generate an information signal based on the result of the calculation, or retrain a neural network. The neural network model may include, but is not limited to, various types of models such as a Convolution Neural Network (CNN) such as Google (registered trademark) Net, AlexNet, VGG Network, etc., a Region with Convolution Neural Network (R-CNN), a Region Proposal Network (RPN), a Recurrent Neural Network (RNN), a Stacking-based deep Neural Network (S-DNN), a State-Space Dynamic Neural Network (S-SDNN), a Deconvolution Network, a Deep Belief Network (DBN), a Restricted Boltzman Machine (RBM), a Fully Convolutional Network, a Long Short-Term Memory (LSTM) Network, and a Classification Network. The processor may include one or more processors for performing calculations according to the neural network model. For example, the neural network may include a deep neural network.

[0031] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Deep Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid It will be understood by those of ordinary skill in the art that the neural network may include, but is not limited to, any neural network, such as a Neural Network (NN), an Extreme Learning Machine (ELM), an Echo State Network (ESN), a Deep Residual Network (DRN), a Differentiable Neural Computer (DNC), a Neural Turning Machine (NTM), a Capsule Network (CN), a Kohonen Network (KN), and an Attention Network (AN).

[0032] According to an example embodiment of the present disclosure, the processor may be configured to support a wide variety of neural networks, including Convolution Neural Networks (CNNs), such as Google Net, AlexNet, VGG Network, Region with Convolution Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restricted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4 for Natural Language Processing, Visual Analytics, Visual Understanding, Video Synthesis, ResNet for Data Intelligence, Anomaly Detection, Prediction, Time-Series Various artificial intelligence structures and algorithms may be used, including but not limited to forecasting, optimization, recommendation, data creation, etc. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0033] FIG. 1 is a diagram showing a system according to the present disclosure, and FIG. 2 is a diagram showing a configuration of a server in FIG.

[0034] Referring to FIGS. 1 and 2, a system 100 may include a user terminal 110 and a server 120 .

[0035] The terminal 110 can request charts for data and narratives for the charts from the server 120. The terminal 110 can transmit various statistical data to the server 120. The terminal 110 is a wireless communication device that ensures portability and mobility, and can include all kinds of handheld-based wireless communication devices such as the above-mentioned Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC), and smartphones, as well as wearable devices such as watches and rings.

[0036] The server 120 can automatically generate charts for data, and convert the contents of analysis based on the generated charts into text or generate and provide a new chart. The server 120 can automatically generate a desired chart with just a click of the user. For example, the server 120 can provide various visualization charts in an intuitive user interface using variables desired by the user. The server 120 can provide analysis data based on charts. For example, the server 120 can provide visualization and analysis functions corresponding to questions desired by the user. For example, the server 120 can provide visualization and text of analysis contents corresponding to the charts. The server 120 can provide a screen split function for displaying detailed charts and a narrative for the detailed charts. For example, the server 120 can generate a primary narrative in response to a selection of a subcategory in the initially generated chart. For example, the server 120 can provide a screen split page with an N-th narrative in the form of gradually reducing the chart when the user selects a portion from the generated split page. N can be a natural number. For example, the server 120 may provide a function for gradually entering other narratives from a split screen function, and may provide statistical data in the form of a user interface for easy access by the user. The server 120 may provide a user interface for charts. For example, when a user selects a subgroup of a chart for a generated chart, the server 120 may provide the chart by visualizing it, and may provide a chart by the user selecting a desired variable, and may provide a user interface for expressing detailed charts and narratives for statistical data so that the user can gradually enter other narratives through split screen. The server 120 may provide a result by converting the analysis data for the generated chart into text through a comparison with a reference point.

[0037] The server 120 may include a communication unit 121, a memory 122, a processor 123, and a database 124.

[0038] The communication unit 121 can communicate with the terminal 110. In this case, the communication unit 121 can include a wireless communication module supporting various wireless communication methods such as Global System for Mobile Communication (GSM), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), universal mobile telecommunications system (UMTS), Time Division Multiple Access (TDMA), Long Term Evolution (LTE), 4G, 5G, and 6G, in addition to a Wifi (registered trademark) module and a WiBro (wireless broadband) module.

[0039] The memory 122 can store data for an algorithm or a program reproducing the algorithm for controlling the operation of the components in the device, and can be realized by at least one processor 123 that performs the above-mentioned operations using the data stored in the memory 122. Here, the memory 122 and the processor 123 can be realized on separate chips, or the memory 122 and the processor 123 can be realized on a single chip.

[0040] The memory 122 can store data supporting various functions of the device and programs for the operation of the processor 123, can store input / output data, and can store a number of application programs (or applications) run by the device, and data and commands for the operation of the device. At least some of these application programs can be downloaded from an external server via wireless communication.

[0041] Such memory 122 may include at least one of the following types of storage media: flash memory type, hard disk type, solid state disk type, silicon disk drive type, multimedia card micro type, card type memory (such as SD or XD memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. The memory 122 may also be a database separate from the device but connected by wire or wirelessly.

[0042] The memory 122 can store algorithm data and statistical data for at least one statistical algorithm.

[0043] The processor 123 can provide narratives and new charts based on the charts for the data.

[0044] The processor 123 may receive the first statistical data and the second statistical data from the terminal 110 via the communication unit 121. The processor 123 may generate a first chart based on the received first statistical data and second statistical data. The first chart may be for visualizing the value of the first statistical data and the value of the second statistical data on a first coordinate axis indicating the value of the first statistical data and a second coordinate axis indicating the value of the second statistical data. For example, the chart may be expressed as a graph. However, the chart is not limited thereto. The processor 123 may analyze the value of the first statistical data and the value of the second statistical data in the first chart based on the first chart and at least one statistical algorithm, and generate at least one first narrative from the first chart. The first narrative may be for visualizing the content of the analysis predicted by analyzing the first chart in text while indicating which specific subcategory the information in the first chart is related to. For example, the narrative may be a text of quantitative facts and key information included in the chart, such as "Sales this month have dropped sharply compared to sales last month," in sentences that are easy for users to understand and in a language that people normally use. The processor 123 may generate a new second chart for visualizing values ​​of statistical data related to the first narrative based on at least one first narrative. The processor 123 may provide the first chart, the first narrative, and the second chart to the terminal 110 via the communication unit 121.

[0045] In one embodiment, the processor 123 receives a screen splitting command from the terminal 110 via the communication unit 121, and in response to the screen splitting command, splits the first chart into multiple detailed charts for each detailed category, and provides the multiple detailed charts to the terminal 110 via the communication unit 121.

[0046] In one embodiment, the processor 123 receives a filtering command from the terminal 110 via the communication unit 121, and in response to the filtering command, filters the first chart only for a specific field, generates at least one second narrative for visualizing in text the content of the analysis analyzed and predicted from the filtered chart while indicating which specific part of the filtered chart is the information related to, and provides the filtered chart and the at least one second narrative to the terminal 110 via the communication unit 121.

[0047] In one embodiment, the processor 123 can receive a report generation command from the terminal 110 via the communication unit 121, and in response to the report generation command, generate a report including charts and a narrative, and provide the report to the terminal 110 via the communication unit 121.

[0048] In one embodiment, the processor 123 can receive variable input information requested by a user from the terminal 110 via the communication unit 121, use the variable input information to generate charts and narratives corresponding to the variables of the variable input information, and provide user interface information including the charts and narratives to the terminal 110 via the communication unit 121.

[0049] In one embodiment, the processor 123 can receive question information requested by a user from the terminal 110 via the communication unit 121, analyze the question in the question information to generate a chart and a narrative corresponding to the question, and provide user interface information including the chart and the narrative to the terminal 110 via the communication unit 121.

[0050] In one embodiment, the processor 123 can receive a request to generate a narrative for the second chart from the terminal 110 via the communication unit 121, and in response to the request, generate at least one second narrative for the second chart, and provide a split-screen page including the at least one second narrative to the terminal 110 via the communication unit 121.

[0051] In one embodiment, the processor 123 receives selection information indicating that a subgroup has been selected on a screen split page from the terminal 110 via the communication unit 121, and in response to the selection information, generates a new third chart in the first chart that corresponds to the selection information and is more specific than the first chart, and provides the third chart to the terminal 110 via the communication unit 121.

[0052] In one embodiment, the processor 123 can compare the analysis data for each of the generated charts with a reference point, convert the comparison results into text, and provide chart analysis data including the converted comparison results to the terminal 110 via the communication unit 121.

[0053] The database 124 can store a variety of data.

[0054] At least one component may be added or removed depending on the performance of the components shown in Figures 1 and 2. Also, it will be easily understood by those skilled in the art that the relative positions of the components may be changed depending on the performance or structure of the system.

[0055] FIG. 3 is a flow diagram illustrating a method according to the present disclosure.

[0056] Referring to Figure 3, the method of Figure 3 may be performed by the server 120 of Figures 1 and 2. The method of Figure 3 may be a method for providing narratives and new charts based on charts for data.

[0057] A step of receiving first and second statistical data is performed (S100).

[0058] A step of generating a first chart for visualizing values ​​of the first statistical data and values ​​of the second statistical data on a first coordinate axis showing values ​​of the first statistical data and a second coordinate axis showing values ​​of the second statistical data based on the first statistical data and the second statistical data is performed (S200).

[0059] A step of analyzing values ​​of first statistical data and values ​​of second statistical data in the first chart based on the first chart and at least one statistical algorithm is performed (S300).

[0060] A step of generating at least one first narrative for visualizing in text the content of the analysis analyzed and predicted from the first chart, while indicating which specific subcategory the information is about in the first chart, is performed (S400).

[0061] A step of generating a new second chart based on the at least one first narrative for visualizing values ​​of statistical data related to the first narrative is performed (S500).

[0062] A step of providing a first chart, a first narrative, and a second chart is performed (S600).

[0063] 4 to 18 are diagrams exemplarily illustrating various embodiments provided by the server of FIG. 1 in the form of user interfaces.

[0064] The present disclosure can capture such user dissatisfaction points through a cloud web-based data analysis tool (e.g., HEARTCOUNT) and provide various user-friendly functions, user interfaces, and user experiences that allow users to easily derive excellent insights with just a few clicks, even without specialized knowledge.

[0065] For example, the present disclosure may provide Smart Plot, with reference to Figure 4. Smart Plot may be a software tool that performs the core EDA (Exploratory Data Analysis) function of the present disclosure, helping users quickly draw desired charts with just a few clicks and interact with the chart elements to quickly understand data.

[0066] For example, the present disclosure can provide drill-down, with reference to Figure 5. Drill-down can be a software tool that allows a user to easily create pivot tables and visualization charts utilizing desired variables through an intuitive user interface.

[0067] 6, for example, the present disclosure may provide Ask Questions, which may be a software tool in which a user inputs a desired question and the server 120 automatically provides corresponding visualization charts and analysis functions.

[0068] With reference to Figures 7, 8, and 9, for example, the present disclosure can provide automated analysis functionality for performing functions such as regression analysis, decision trees, and comparative analysis of both populations with the click of a mouse and visual confirmation of interactive results.

[0069] For example, the present disclosure may provide an Explainer, which may be a software tool for automatically discovering key patterns from data and providing them in a user-friendly text format and corresponding visualizations.

[0070] This disclosure can combine dashboards and HEARTCOUNT to provide one product (e.g., HEARTCOUNT ABI (Analytic & BI (business intelligence))). BI, which is the first to discover changes in key indicators for business practitioners, cannot immediately provide an answer to the additional question, "So why is there that change?", so in order to get answers to such questions, they must request additional analysis / reporting materials from a data analyst / team. This can ultimately act as a bottleneck that increases the time to insight. When a change in a key indicator is discovered in BI, this disclosure allows the change in the indicator and related data to be additionally analyzed through EDA in HEARTCOUNT, laying the groundwork for practitioners who discover the change to directly track down the cause of the change (get-the-job-done). This disclosure can produce the best results when combined with an understanding of the current business context and a small amount of time and effort at the EDA level. The present disclosure can provide three core processes of EDA that allow users to draw charts, understand charts, and ask the next question with minimal time and effort, and derive appropriate results. For example, the present disclosure provides an effect of enabling users to understand charts by organizing and providing quantitative facts and core information contained in the charts in a sentence that is easy for users to understand (e.g., the narrative of the present disclosure as a language that people normally use). Explanations of charts can include, for example, simple phenomena of the charts, comparisons between the values ​​of the charts, and charts detailed through the lens of statistical / expert knowledge. The present disclosure can provide narratives for each of the simple phenomena of the charts, comparisons between the values ​​of the charts, and charts detailed through the lens of statistical / expert knowledge. The simple phenomena of the charts can be called descriptive information and can mean a simple description of the phenomenon. In the case of comparisons between the values ​​of the charts, the numbers included in the charts can be compared with other numbers to derive meaningful results.For example, the simple fact that "sales this month are 100,000 won" can have a richer meaning through comparison with the reference point that "sales this month are 20,000 won higher than the average sales level of 80,000 won." In the case of a chart examined through the lens of statistical / expert knowledge, this disclosure can mean providing a simple explanation that makes statistical / expert knowledge that is difficult for general users to grasp easy to understand. This disclosure can present "good questions" from the quantitative facts / core information of the chart and provide appropriate visualizations and answers corresponding to them. For example, this disclosure can provide an explanation of the chart, such as "When we divided the sales of each month at the product group level to understand the difference between last month's sales and this month's sales, we found that sales of electronic products dropped sharply this month compared to last month." When a user directly performs EDA, it is often difficult for the user to define what the user should look at among the many combinations of variables to get the correct answer to the question the user wants, i.e., what the second and third questions should be, rather than the first question. Therefore, the present disclosure can act as a pathfinder to provide the most appropriate "next step" or "next question" in the current situation, providing information that allows the conclusion to one question to naturally lead to the next question.

[0071] 11 and 12, when a user desires to derive an understanding of the chart provided by the server 120, the user can click the "Generate Narratives" button. The server 120 can confirm what kind of chart the chart is and what main information is included in the chart. The server 120 can provide various user interface information for additional questions that the user can ask through the bar chart. The server 120 can provide a bar chart to allow the user to confirm the difference between two groups (entities) through the "height difference". The server 120 can allow the user to confirm the difference between "Consumer" and "Corporate" in the bar chart of FIG. 11 through numbers and a table. Instead of the user manually searching the EDA tool directly to better understand the difference between the two bars, the user can press the "Understanding difference" button as shown in FIG. 11 and 12, and the server 120 can automatically perform an operation of comparing the difference between the two bars. In the case of "Consumer" and "Corporate" in FIG. 11, the server 120 can provide the result with the largest difference when "Category" in FIG. 12 is "Technology" (i.e., "Consumer">"Corporate"). The server 120 can generate a new narrative for the corresponding case. The server 120 can automatically and appropriately convert the visualization chart on the right side of FIG. 12 according to the newly generated narrative and can also provide related table information. When the user clicks on each narrative, the server 120 can highlight the corresponding part in the chart to emphasize the connection between the text and the chart elements. This allows the user to understand the chart more easily. The user can convert the variable name (Category), variable value (Technology), etc. to other values ​​by clicking the mouse. This allows the user to understand the same perspective (understanding the difference between Consumer and Corporate) by using other values ​​(e.g., Home Office instead of Technology).

[0072] The server 120 of the present disclosure can automatically generate a chart desired by the user with just a click of the user and provide analysis data based on the chart. In this way, the server 120 can provide a narrative that can be analyzed for each chart in parallel with the chart. The server 120 can generate a factual narrative in the chart in an interactive manner. With reference to FIG. 13, for example, the server 120 can automatically generate a chart in which the horizontal axis is order priority and the vertical axis is profit (average) in response to a user request and transfer the chart to the user's terminal 110 so that the chart is displayed on the user's terminal 110. In this case, the narrative can be, but is not limited to, "The overall average of Profit is 28.6.", "Medium recorded the second highest average of Sales (31.59) among Order Priority, which is higher than the overall average by 2.99", etc. If a user is interested in Medium and clicks on Medium on the screen of the terminal 110, the server 120 can generate a separate image that highlights a bar graph corresponding to Medium in the chart. If a user clicks on a word or phrase of a particular narrative on the screen of the terminal 110, the server 120 can generate a separate image of a graph corresponding to the word of the narrative in the chart.

[0073] In order to prevent a user from over-analyzing or misinterpreting a factual narrative in a chart, the server 120 of the present disclosure may analyze the next question (or subsequent question, predicted question, etc.) that can help the user to find the insight desired in a given context (e.g., a chart, etc.) and provide a statistical analysis (Expert Advice). With reference to FIG. 14 and FIG. 15, for example, the chart and the narrative may be displayed as a comparison of averages of a simple bar chart. The server 120 may provide Expert Advice to the user's terminal 110 using a separate icon in the chart and the narrative (e.g., a number and a "+" display as shown in FIG. 14, see the number display as shown in FIG. 15). The user may obtain additional insights on the corresponding content by clicking on the corresponding symbol display, etc. The additional insights may include, for example, an approach (e.g., a T-test, etc.) that may be the next appropriate question. As shown in Figure 14, additional statistical analysis and advice can be presented as an analytical question, such as "Can this be considered a statistically significant difference?" In this case, if necessary, you can switch to a visualized chart and generate a corresponding chart, narrative, and explanatory text. In addition, by providing statistical analysis (expert advice) that matches each value, users who are not statistical experts can create new plots by referring to the statistical analysis.

[0074] The server 120 of the present disclosure can automatically calculate factors that significantly contributed to the difference in the index and present them to the user in text and chart. With reference to FIG. 16 and FIG. 17, for example, the chart can be a bar chart showing the average employee satisfaction by job group. The primary narrative can be about management support for manufacturing production. The variable that best explains the difference in satisfaction between the two job groups can be the recruitment path. Therefore, the user can select the variable recruitment path through a menu called "variable selection for understanding the difference". Specific values ​​of the variable recruitment path can include, for example, "recruitment path: overseas", "recruitment path: intern", etc. In this case, the server 120 can generate and display the corresponding narrative using an algorithm corresponding to the variable selected by the user, as shown in FIG. 17. As shown in FIG. 17, the narrative may include, "When the hiring route is overseas, the average employee satisfaction of manufacturing production (50.19) is about 3.83 more than that of management support (46.36) (0.08 times)." or "The number of overseas records of manufacturing production (40) is about 3.33 times that of management support (12)." For example, when the specific values ​​of the variable "hiring route" are "overseas" and "interns", the server 120 can calculate a value indicating the difference in satisfaction between the two occupational groups and select the value of the variable with the largest difference between the two occupational groups, for example, "overseas". The user may be interested in the analysis of the value of "overseas" and another variable "hiring route", for example, "interns". In this case, the user can select another value of "hiring route". In this case, the server 120 can change the corresponding chart and narrative in response to the user's selection. However, without being limited thereto, instead of the user selecting the variable "recruitment route: overseas" through a menu called "variable selection for understanding the difference", the server 120 can directly calculate the difference in satisfaction between the two occupational groups for all combinations of values ​​of all variables (e.g., age, gender, recruitment route, region, etc.) and recommend the variable (e.g., core variable) with the largest corresponding difference and the value of the core variable to the user. As a method of providing the user with the variable with the largest corresponding difference and its value, for example, "I calculated it and found that the difference between the two occupational groups was the largest for gender...and among them, it was largest for gender: female.A user interface including text information such as "Try to understand the difference in recruitment path variables" can be provided to the user. This has the effect of enabling the user to achieve a high level of data understanding.

[0075] The server 120 of the present disclosure can generate a report file including all factual information in response to a user's request, and transfer the report file to the terminal 110 so that the user can check the report via the terminal 110. For example, with reference to FIG. 18, the user can click on a particular narrative. The server 120 can store pair data including a detailed chart corresponding to the narrative clicked on the chart and the narrative in response to the user's input. That is, the user can select and bookmark a core narrative through an application (e.g., a Chart-to-Narrative) function provided by the server 120 of the present disclosure. When the user commands the generation of a report, the server 120 can create a report file including the stored data (e.g., the narrative and the corresponding detailed chart) according to a preset report format. In some implementations, the server 120 can generate a report file by using a generative artificial intelligence model (e.g., GPT, etc.) to perform prompt engineering (e.g., {narrative_id:n_1, chart_id:c_1}) to switch the bookmarks into a report format. In this way, the bookmarked core narratives and corresponding charts can be provided to the user in the form of a report.

[0076] The present disclosure has the advantage of enabling users to achieve a high level of data understanding with a minimal investment of time, effort and intelligence.

[0077] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing instructions executable by a computer. The instructions may be stored in the form of program code, which, when executed by a processor, generates program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0078] The computer-readable recording medium includes any type of recording medium in which computer-readable instructions are stored, such as a read only memory (ROM), a random access memory (RAM), a magnetic tape, a magnetic disk, a flash memory, an optical data storage device, and the like.

[0079] As described above, the disclosed embodiments have been described with reference to the accompanying drawings. Those skilled in the art will understand that the present disclosure may be embodied in forms different from the disclosed embodiments without changing the technical idea or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted as being limited.

Claims

1. A communication unit configured to communicate with a terminal; a memory for storing algorithm data for at least one statistical algorithm; a processor configured to provide a narrative and a new chart based on the chart for the data; The processor, generating a first chart for visualizing values ​​of the first statistical data and the second statistical data on a first coordinate axis indicating a value of the first statistical data and a second coordinate axis indicating a value of the second statistical data, based on the first statistical data and the second statistical data received from the terminal via the communication unit; Based on the first chart and the at least one statistical algorithm, analyze the value of the first statistical data and the value of the second statistical data in the first chart, and generate at least one first narrative for visualizing in text the content of the analysis predicted by the first chart while indicating which specific subcategory the information is about in the first chart; generating a new second chart based on the at least one first narrative for visualizing values ​​of statistical data related to the first narrative; A server that provides the first chart, the first narrative, and the second chart to the terminal via the communication unit.

2. The processor, receiving a screen division command from the terminal via the communication unit; In response to the screen division command, dividing the first chart into a plurality of detail charts for each detail category; The server according to claim 1 , wherein the plurality of detailed charts are provided to the terminal via the communication unit.

3. The processor, receiving a filtering command from the terminal via the communication unit; filtering the first chart only for a particular field in response to the filtering command; generating at least one second narrative for visualizing in text the content of an analysis predicted from the filtered chart while indicating which specific portion of the filtered chart is the information; The server according to claim 2 , characterized in that the filtered chart and the at least one second narrative are provided to the terminal via the communication unit.

4. The processor, receiving a report creation command from the terminal via the communication unit; generating a report including charts and a narrative in response to said report generation command; The server according to claim 3 , wherein the report is provided to the terminal via the communication unit.

5. The processor, receiving variable input information requested by a user from the terminal via the communication unit; using said variable input information to generate charts and narratives corresponding to variables of said variable input information; The server according to claim 4 , further comprising: a communication unit configured to provide user interface information including the chart and the narrative to the terminal.

6. The processor, receiving question information requested by a user from the terminal via the communication unit; Analyzing questions from the inquiry information to generate charts and narratives corresponding to the questions; The server according to claim 5 , further comprising: a communication unit configured to provide user interface information including the chart and the narrative to the terminal.

7. The processor, receiving a request to generate a narrative for the second chart from the terminal via the communication unit; generating at least one second narrative for the second chart in response to the request; The server according to claim 6, characterized in that it provides the terminal with a split-screen page including the at least one second narrative via the communication unit.

8. The processor, receiving selection information from the terminal via the communication unit, the selection information indicating that a lower group has been selected on the screen division page; In response to the selection information, generate a new third chart in the first chart that corresponds to the selection information and is more specific than the first chart; The server according to claim 7 , wherein the third chart is provided to the terminal via the communication unit.

9. The processor, Compare the analytical data for each of the generated charts with a reference point; The comparison results are converted into text, The server according to claim 8 , wherein the server provides the terminal with chart analysis data including the comparison result converted into text via the communication unit.

10. 1. A method for providing narrative and new charts based on charts for data, comprising: receiving first statistical data and second statistical data; generating a first chart based on the first statistical data and the second statistical data for visualizing values ​​of the first statistical data and values ​​of the second statistical data on a first coordinate axis indicating values ​​of the first statistical data and a second coordinate axis indicating values ​​of the second statistical data; analyzing the first statistical data value and the second statistical data value in the first chart based on the first chart and the at least one statistical algorithm; generating at least one first narrative for visualizing in text the content of an analysis predicted from the first chart while indicating which specific subcategory the information is about in the first chart; generating a new second chart based on the at least one first narrative for visualizing values ​​of statistical data associated with the first narrative; providing the first chart, the first narrative, and the second chart; The method includes:

Images