Analyze labels in visualization based on dataset characteristics

Abstract

Embodiments relate to visualization of management data. A visualization can be provided that includes one or more tags associated with values ​​from a data source. Tags of interest can be determined from the one or more tags. An evaluation model can be used to generate evaluation results for the evaluation model based on the tags of interest and data from the data source, such that each evaluation result can be associated with a score based on a best fit to the data from the data source and the value of the tag of interest. The evaluation results can be ranked based on their association with the scores. A report can be provided that includes a ranked list of the evaluation results.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is a utility patent application based upon previously filed U.S. Provisional Patent Application No. 62 / 862,349, filed on June 17, 2019, which hereby claims the benefit of the filing date thereof under 35 U.S.C. §119(e), and is further incorporated by reference in its entirety. Technical Field

[0003] The present invention relates generally to data visualization and, more particularly, but not exclusively, to automatically explaining the reasons for values ​​in a visualization. Background Art

[0004] Organizations are generating and collecting increasing amounts of data. This data can be associated with different parts of the organization (e.g., consumer activity, manufacturing activities, customer service, server logs, etc.). For various reasons, such organizations may struggle to effectively leverage their vast data collections. In some cases, the sheer volume of data can make it difficult to effectively leverage the collected data to improve business practices. In some cases, organizations use various tools to generate visualizations of some or all of this data. Using visualizations to represent this data can enable organizations to improve their understanding of key business operations and help them monitor key performance indicators. However, in some cases, visualizations may include tags, signals, values, etc. that may appear inappropriate or anomalous. In some cases, determining the source or otherwise analyzing the origin or cause of these tags may require an inadequate understanding of the underlying data used to generate the visualization. Unfortunately, this may require organizations to direct skilled or specialized data analysts to review the visualizations and data to determine why a tag may have a given value. Furthermore, in some cases, even if users have the skills or technical background to perform their own analysis, the underlying data may be sensitive or inaccessible to users reviewing the visualizations. Therefore, the present invention addresses these and other concerns. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] Non-limiting and non-exhaustive embodiments of the present invention are described with reference to the following drawings. In the drawings, like reference numerals refer to like parts throughout the various figures unless otherwise specified. For a better understanding of the described innovation, reference is made to the following detailed description of various embodiments, which is to be read in conjunction with the accompanying drawings, wherein:

[0006] Figure 1 shows a system environment in which various embodiments may be implemented;

[0007] Figure 2 An illustrative embodiment of a client computer is shown;

[0008] Figure 3 A schematic embodiment of a network computer is shown;

[0009] Figure 4 shows a logical architecture of a system for analyzing tags in a visualization based on data characteristics according to one or more of various embodiments;

[0010] Figure 5 shows a logical representation of a portion of a visualization according to one or more of various embodiments;

[0011] Figure 6 shows a logical representation of a portion of a marking evaluation system according to one or more of various embodiments;

[0012] Figure 7 shows a logical representation of a portion of a user interface for analyzing markers in a visualization based on data characteristics according to one or more of various embodiments;

[0013] Figure 8 shows an overview flow chart of a process for analyzing tags in a visualization based on data features according to one or more of various embodiments;

[0014] Figure 9 A flowchart illustrating a process for analyzing tags using an evaluation model according to one or more of various embodiments;

[0015] Figure 10 A flowchart illustrating a process for adapting filtering or ranking of an evaluation model based on monitoring user interactions according to one or more of various embodiments is shown;

[0016] Figure 11 A flowchart illustrating a process for generating an expected value distribution for evaluating a model according to one or more of various embodiments; and

[0017] Figure 12 A flow chart illustrating a process for comparing results of evaluation models according to one or more of various embodiments is shown. DETAILED DESCRIPTION

[0018] Various embodiments will be described more fully below with reference to the accompanying drawings, which form a part of the present invention and show, by way of illustration, specific exemplary embodiments in which the present invention may be implemented. However, the embodiments may be implemented in many different forms and should not be construed as limited to the embodiments described herein; rather, these embodiments are provided so that the disclosure will be thorough and complete and will fully convey the scope of the embodiments to those skilled in the art. Various embodiments may be, among other things, methods, systems, media, or devices. Thus, various embodiments may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware aspects. Therefore, the detailed description below should not be construed as limiting.

[0019] Throughout the specification and claims, unless the context clearly dictates otherwise, the following terms take on the meanings explicitly associated herein. As used herein, the phrase "in one embodiment" does not necessarily refer to the same embodiment (although it may). Additionally, as used herein, the phrase "in another embodiment" does not necessarily refer to a different embodiment (although it may). Thus, as described below, various embodiments may be readily combined without departing from the scope or spirit of the invention.

[0020] Additionally, as used herein, the term "or" is an inclusive "or" operator and is equivalent to the term "and / or," unless the context clearly dictates otherwise. The term "based on" is not exclusive and allows for being based on other factors not described, unless the context clearly dictates otherwise. Additionally, throughout this specification, the meanings of "a," "an," and "the" include plural references. The meaning of "in" includes "in which" and "on which."

[0021] For example, in the embodiments, the following terms are also used herein according to the corresponding meanings, unless the context clearly indicates otherwise.

[0022] The term "engine" as used herein refers to the logic contained in hardware or software instructions, which can be written in a programming language such as C, C++, Objective-C, COBOL, Java TM , PHP, Perl, JavaScript, Ruby, VBScript, Microsoft.NET TMLanguages ​​such as C#, etc. The engine can be compiled into an executable program or written in a declarative programming language. The software engine can be called from other engines or from itself. The engine described herein refers to one or more logical modules, which can be merged with other engines or applications, or can be divided into sub-engines. The engine can be stored in a non-transitory computer-readable medium or computer storage device and stored and executed by one or more general-purpose computers, thereby creating a special-purpose computer configured to provide the engine.

[0023] As used herein, the term "data source" refers to a database, application, service, file system, or similar object that stores or provides information to an organization. Examples of data sources include RDBMS databases, graph databases, spreadsheets, file systems, document management systems, and local or remote data streams. In some cases, data sources are organized around one or more tables or table-like structures. In other cases, data sources are organized as graphs or graph-like structures.

[0024] As used herein, the term "data model" refers to one or more data structures that provide a representation of an underlying data source. In some cases, a data model can provide a view of a data source for a particular application. A data model can be considered a view or interface to an underlying data source. In some cases, a data model can be directly mapped to a data source (e.g., effectively a logical pass-through). Additionally, in some cases, a data model may be provided by a data source. In some cases, a data model can be considered an interface to a data source. A data model enables an organization to organize or present information from a data source in a manner that is more convenient, more meaningful (e.g., easier to reason about), more secure, etc.

[0025] As used herein, the term "data object" refers to one or more entities or data structures that comprise a data model. In some cases, a data object can be considered a part of a data model. A data object can represent an individual instance of an item or a class or type of item.

[0026] As used herein, the term "panel" refers to an area within a graphical user interface (GUI) that has a defined geometric shape (e.g., x, y, z order) within the GUI. A panel can be arranged to display information to a user or to host one or more interactive controls. Configuration information, including dynamic rules, can be used to define the geometric shape or style associated with a panel. In addition, in some cases, a user can perform operations on one or more panels, such as moving, showing, hiding, resizing, reordering, etc.

[0027] As used herein, a "visual model" refers to one or more data structures representing one or more representations of a data model that may be suitable for use in a visualization displayed on one or more hardware displays. A visual model may define styles or user interface characteristics that may be available to unauthorized users.

[0028] As used herein, the term "display object" refers to one or more data structures that comprise a visualization model. In some cases, a display object may be considered part of a visualization model. A display object may represent a single instance of an item or an entire class or category of items that can be displayed in a visualization. In some embodiments, display objects may be considered or referred to as views because they provide views of certain portions of a data model.

[0029] As used herein, the term "marker" refers to a unique or otherwise identifiable portion of a visualization that can correspond to a specific value or result in the visualization. For example, if the visualization includes a bar graph, one or more bars can be considered a marker. Similarly, if the visualization includes a line graph, a location on the graph can be considered a marker.

[0030] As used herein, the term "marker of interest" refers to a mark in a visualization that is selected from other marks included in the visualization. In some cases, the marks in the visualization may include one or more interactive features that enable a user to select or identify one or more marks of interest from the marks comprising the visualization. For example, a user may select a mark of interest by right-clicking the mouse button while the mouse pointer is hovering over the mark. In some cases, the mark of interest may be selected by searching, filtering, etc.

[0031] As used herein, the term "configuration information" refers to information that may include rule-based policies, pattern matching, scripts (e.g., computer-readable instructions), etc., which may be provided from various sources, including configuration files, databases, user input, built-in defaults, etc., or a combination thereof.

[0032] The following briefly describes embodiments of the present invention in order to provide a basic understanding of some aspects of the invention. This brief description is not intended as an extensive overview. It is not intended to identify key or critical elements, nor is it intended to delineate or otherwise narrow the scope. Its purpose is simply to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.

[0033] Briefly stated, various embodiments are directed to managing the visualization of data using one or more processors that execute one or more instructions to perform operations as described herein.

[0034] In one or more of the various embodiments, one or more visualizations based on data from a data source can be provided such that the one or more visualizations include one or more tags that can be associated with one or more values ​​from the data source.

[0035] In one or more of the various embodiments, a marker of interest can be determined from the one or more markers based on one or more features, one or more visualizations of the one or more markers, etc. In one or more of the various embodiments, determining the marker of interest can include: automatically analyzing one or more values ​​associated with the one or more markers; and determining the marker of interest based on the automatic analysis.

[0036] In one or more of the various embodiments, one or more evaluation models may be used to generate one or more evaluation results for the one or more evaluation models based on the marker of interest and the data from the data source, such that each evaluation result is associated with one or more scores based on the best fit to the data from the data source and the value of the marker of interest. In one or more of the various embodiments, generating the one or more evaluation results may include: generating one or more natural language narratives describing one or more characteristics of the marker of interest based on its evaluation and the one or more narrative templates; and including the one or more natural language narratives in the one or more evaluation results.

[0037] In one or more of the various embodiments, one or more assessment results can be ranked based on their association with one or more scores.

[0038] In one or more of the various embodiments, a report can be provided that includes a ranked list of the one or more evaluation results. In one or more of the various embodiments, providing the report can include generating one or more other visualizations that can be associated with the one or more evaluation models, the one or more evaluation results, the markers of interest, etc.

[0039] In one or more of the various embodiments, feedback information associated with the report can be monitored. In one or more of the various embodiments, one or more other scores based on the feedback information can be provided. In one or more of the various embodiments, the one or more other scores can be used to determine one or more modifications to one or more evaluation results.

[0040] In one or more of the various embodiments, one or more assessment results can be filtered based on one or more scores such that each assessment result associated with a score that may be less than a defined threshold is excluded from the report.

[0041] In one or more of the various embodiments, data associated with tags of interest included in the data source and omitted from the visualization can be evaluated. Thus, in some embodiments, a portion of one or more evaluation results can be generated based on the evaluation.

[0042] Graphical operating environment

[0043] Figure 1 Components of one embodiment of an environment in which embodiments of the present invention may be practiced are shown. Not all components may be required to implement the present invention, and the arrangement and type of components may be varied without departing from the spirit or scope of the present invention. As shown, Figure 1 The system 100 includes a local area network (LAN) / wide area network (WAN)—(network) 110 , a wireless network 108 , client computers 102 - 105 , a visualization server computer 116 , a data source server computer 118 , and the like.

[0044] The following combination Figure 2 At least one embodiment of the client computers 102 to 105 is described in more detail. In one embodiment, at least some of the client computers 102 to 105 can operate on one or more wired or wireless networks, such as network 108 or 110. Generally, the client computers 102 to 105 can include almost any computer that can communicate over a network to send and receive information, perform various online activities, offline actions, etc. In one embodiment, one or more of the client computers 102 to 105 can be configured to operate within an enterprise or other entity to perform various services for the enterprise or other entity. For example, the client computers 102 to 105 can be configured to operate as a web server, firewall, client application, media player, mobile phone, game console, desktop computer, etc. However, the client computers 102 to 105 are not limited to these services and can also be used for end-user computing in other embodiments, for example. It should be recognized that more or less client computers (such as Figure 1 ) may be included in a system such as described herein, and embodiments are therefore not limited by the number or type of client computers employed.

[0045] Computers that can operate as client computers 102 may include computers that are typically connected using wired or wireless communication media, such as personal computers, multiprocessor systems, microprocessor-based or programmable electronic devices, network PCs, and the like. In some embodiments, client computers 102 to 105 may include virtually any portable computer capable of connecting to another computer and receiving information, such as laptop computer 103, mobile computer 104, tablet computer 105, and the like. However, portable computers are not so limited and may also include other portable computers, such as cellular phones, display pagers, radio frequency (RF) devices, infrared (IR) devices, personal digital assistants (PDAs), handheld computers, wearable computers, integrated devices that combine one or more of the foregoing computers, and the like. Thus, client computers 102 to 105 generally range in capabilities and features. Furthermore, client computers 102 to 105 may access a variety of computing applications, including browsers or other web-based applications.

[0046] The client computer that enables the web may include a browser application that is configured to send requests and receive responses through the web. The browser application can be configured to use almost any web-based language to receive and display graphics, text, multimedia, etc. In one embodiment, the browser application is enabled to use JavaScript, Hypertext Markup Language (HTML), Extensible Markup Language (XML), JavaScript Object Notation (JSON), Cascading Style Sheets (CSS), etc. or a combination thereof to display and send messages. In one embodiment, the user of the client computer can use the browser application to perform various activities through the network (online). However, another application may also be used to perform various online activities.

[0047] The client computers 102 to 105 may also include at least one other client application configured to receive or send content to or from another computer. The client application may include the ability to send or receive content, etc. The client application may also provide information identifying itself, including type, capabilities, name, etc. In one embodiment, the client computers 102 to 105 may uniquely identify themselves by any of a variety of mechanisms, including an Internet Protocol (IP) address, telephone number, mobile identification number (MIN), electronic serial number (ESN), client certificate, or other device identifier. Such information may be provided in one or more network packets, etc., and sent between other client computers, the visualization server computer 116, the data source server computer 118, or other computers.

[0048] The client computers 102 to 105 may also be configured to include a client application that enables an end user to log into an end user account, which may be managed by another computer (e.g., the visualization server computer 116, the data source server computer 118, etc.). In one non-limiting example, such an end user account may be configured to enable the end user to manage one or more online activities, including, in one non-limiting example, project management, software development, system administration, configuration management, search activities, social networking activities, browsing various websites, communicating with other users, etc. In addition, the client computer may be arranged to enable the user to display reports, interactive user interfaces, or results provided by the visualization server computer 116, the data source server computer 118.

[0049] The wireless network 108 is configured to couple the client computers 103 to 105 and their components to the network 110. The wireless network 108 may include any of a variety of wireless sub-networks, which may further encompass independent ad-hoc networks, etc., to provide infrastructure-oriented connectivity for the client computers 103 to 105. Such sub-networks may include mesh networks, wireless LAN (WLAN) networks, cellular networks, etc. In one embodiment, the system may include more than one wireless network.

[0050] The wireless network 108 may also include an autonomous system of terminals, gateways, routers, etc. connected by wireless radio links, etc. These connectors may be configured to move freely and randomly and organize themselves arbitrarily so that the topology of the wireless network 108 may change rapidly.

[0051] The wireless network 108 may further employ a plurality of access technologies, including second (2G), third (3G), fourth (4G), and fifth (5G) generation radio access for cellular systems, WLAN, wireless router (WR) mesh networks, and the like. Access technologies such as 2G, 3G, 4G, 5G, and future access networks may enable mobile computers (e.g., client computers 103 to 105 with varying degrees of mobility) to have wide-area coverage. In one non-limiting example, the wireless network 108 may implement radio connectivity through radio network access, such as Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Enhanced Data GSM Environment (EDGE), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Wideband Code Division Multiple Access (WCDMA), High Speed ​​Downlink Packet Access (HSDPA), Long Term Evolution (LTE), and the like. In essence, the wireless network 108 may include virtually any wireless communication mechanism by which information may be transmitted between the client computers 103 to 105 and another computer, network, cloud-based network, cloud instance, and the like.

[0052] The network 110 is configured to couple the network computer to other computers, including a visualization server computer 116, a data source server computer 118, the client computer 102, and the client computers 103 to 105, via a wireless network 108 or the like. The network 110 can use any form of computer-readable media to transmit information from one electronic device to another. Furthermore, the network 110 can include the Internet in addition to a local area network (LAN), a wide area network (WLAN), a direct connection such as via a universal serial bus (USB) port, an Ethernet port, other forms of computer-readable media, or any combination thereof. On a set of interconnected LANs, including those based on different architectures and protocols, a router acts as a link between the LANs, enabling messages to be sent from one LAN to another. In addition, the communication links within a LAN typically include twisted pairs or coaxial cables, while the communication links between networks can utilize analog telephone lines, dedicated digital lines including all or part of T1, T2, T3 and T4, or other carrier mechanisms, including, for example, electronic carriers, integrated services digital networks (ISDN), digital subscriber lines (DSL), wireless links including satellite links, or other communication links known to those skilled in the art. In addition, the communication links can further utilize any of a variety of digital signaling technologies, including but not limited to, for example, DS-0, DS-1, DS-2, DS-3, DS-4, OC-3, OC-12, OC-48, etc. In addition, remote computers and other related electronic devices can be remotely connected to the LAN or WAN via a modem and a temporary telephone link. In one embodiment, the network 110 can be configured to transmit Internet Protocol (IP) information.

[0053] Furthermore, communication media generally contains computer-readable instructions, data structures, program modules or other transport mechanisms, and includes any non-transient or transient information transfer media. For example, communication media includes wired media such as twisted pair, coaxial cable, optical fiber, waveguides and other wired media, and wireless media such as acoustic, RF, infrared and other wireless media.

[0054] In addition, the following combination Figure 3 One embodiment of the visualization server computer 116 and the data source server computer 118 is described in more detail. Figure 1The visualization server computer 116, the data source server computer 118, and the like are each shown as a single computer, but the innovations and embodiments are not limited thereto. For example, one or more functions of the visualization server computer 116, the data source server computer 118, and the like can be distributed across one or more different network computers. Furthermore, in one or more embodiments, the visualization server computer 116, the data source server computer 118 can be implemented using multiple network computers. Furthermore, in one or more of the various embodiments, the visualization server computer 116, the data source server computer 118, and the like can be implemented using one or more cloud instances in one or more cloud networks. Therefore, these innovations and embodiments should not be construed as limited to a single environment, and other configurations and architectures are also contemplated.

[0055] Illustrative client computer

[0056] Figure 2 One embodiment of a client computer 200 is shown, which may include more or fewer components than those shown. The client computer 200 may represent, for example, Figure 1 One or more embodiments of a mobile computer or client computer are shown.

[0057] The client computer 200 may include a processor 202 in communication with a memory 204 via a bus 228. The client computer 200 may also include a power supply 230, a network interface 232, an audio interface 256, a display 250, a keypad 252, an illuminator 254, a video interface 242, an input / output interface 238, a tactile interface 264, a global positioning system (GPS) receiver 258, an open gesture interface 260, a temperature interface 262, a camera 240, a projector 246, a pointing device interface 266, a processor-readable fixed storage device 234, and a processor-readable removable storage device 236. The client computer 200 may optionally communicate with a base station (not shown) or directly with another computer. In one embodiment, although not shown, a gyroscope may be used within the client computer 200 to measure or maintain the orientation of the client computer 200.

[0058] The power supply 230 can provide power to the client computer 200. Rechargeable batteries or non-rechargeable batteries can be used to provide power. Power can also be provided by an external power source, such as an AC adapter or a powered docking station that replenishes or recharges the battery.

[0059] The network interface 232 includes circuitry for coupling the client computer 200 to one or more networks and is configured for use with one or more communication protocols and technologies, including, but not limited to, protocols and technologies that implement any portion of the OSI model, for mobile communications (GSM), CDMA, Time Division Multiple Access (TDMA), UDP, TCP / IP, SMS, MMS, GPRS, WAP, UWB, WiMax, SIP / RTP, GPRS, EDGE, WCDMA, LTE, UMTS, OFDM, CDMA2000, EV-DO, HSDPA, or any of a variety of other wireless communication protocols. The network interface 232 is sometimes referred to as a transceiver, transceiver device, or network interface card (NIC).

[0060] The audio interface 256 can be arranged to generate and receive audio signals, such as the sound of a human voice. For example, the audio interface 256 can be coupled to a speaker and a microphone (not shown) to enable communication with others or to generate audio confirmations for certain actions. The microphone in the audio interface 256 can also be used to input or control the client computer 200, for example, using voice recognition, detecting touch based on sound, etc.

[0061] The display 250 may be a liquid crystal display (LCD), gas plasma, electronic ink, light emitting diode (LED), organic LED (OLED), or any other type of light reflective or light transmissive display that may be used with a computer. The display 250 may also include a touch interface 244 that is arranged to receive input from an object such as a stylus or a finger from a human hand and may sense touch or gestures using resistive, capacitive, surface acoustic wave (SAW), infrared, radar, or other technologies.

[0062] Projector 246 may be a remote handheld projector or an integrated projector capable of projecting an image on a remote wall or any other reflective object such as a remote screen.

[0063] The video interface 242 can be arranged to capture video images, such as still photos, video clips, infrared video, etc. For example, the video interface 242 can be coupled to a digital camera, a webcam, etc. The video interface 242 can include a lens, an image sensor, and other electronics. The image sensor can include a complementary metal oxide semiconductor (CMOS) integrated circuit, a charge coupled device (CCD), or any other integrated circuit for sensing light.

[0064] The keypad 252 may include any input device arranged to receive input from a user. For example, the keypad 252 may include a button numeric dial or a keyboard. The keypad 252 may also include command buttons associated with selecting and sending images.

[0065] Illuminator 254 can provide a status indication or provide light. Illuminator 254 can remain activated for a specific period of time or in response to an event message. For example, when illuminator 254 is activated, it can backlight the buttons on keypad 252 and remain on while the client computer is powered. In addition, when a specific action is performed (such as dialing another client computer), illuminator 254 can backlight these buttons in various modes. Illuminator 254 can also illuminate a light source positioned within a transparent or translucent housing of the client computer in response to an action.

[0066] Additionally, the client computer 200 may include a hardware security module (HSM) 268 for providing additional tamper-proofing for generating, storing, or using security / cryptographic information such as keys, digital certificates, passwords, passphrases, two-factor authentication information, etc. In some embodiments, the hardware security module may be configured to support one or more standard public key infrastructures (PKIs) and may be configured to generate, manage, or store key pairs, etc. In some embodiments, the HSM 268 may be a standalone computer; in other cases, the HSM 268 may be configured as a hardware card that may be added to the client computer.

[0067] The client computer 200 may also include an input / output interface 238 for communicating with external peripheral devices or other computers such as other client computers and network computers. Peripheral devices may include audio headsets, virtual reality helmets, display glasses, remote speaker systems, remote speaker and microphone systems, etc. The input / output interface 238 may utilize one or more technologies such as Universal Serial Bus (USB), infrared, WiFi, WiMax, Bluetooth, etc. TM wait.

[0068] The input / output interface 238 may also include one or more sensors for determining geographic location information (e.g., GPS), monitoring power conditions (e.g., voltage sensor, current sensor, frequency sensor, etc.), monitoring weather (e.g., thermostat, barometer, anemometer, humidity detector, precipitation scale, etc.), etc. The sensor may be one or more hardware sensors that collect or measure data external to the client computer 200.

[0069] The tactile interface 264 can be arranged to provide tactile feedback to the user of the client computer. For example, the tactile interface 264 can be used to vibrate the client computer 200 in a particular manner when another user of the computer is calling. The temperature interface 262 can be used to provide a temperature measurement input or a temperature change output to the user of the client computer 200. The open gesture interface 260 can sense the physical gestures of the user of the client computer 200, for example, by using a single or stereo camera, radar, a gyroscope sensor within a computer held or worn by the user, etc. The camera 240 can be used to track the physical eye movements of the user of the client computer 200.

[0070] The GPS transceiver 258 can determine the physical coordinates of the client computer 200 on the surface of the earth, which typically outputs the location as latitude and longitude values. The GPS transceiver 258 can also use other geolocation mechanisms, including but not limited to triangulation, assisted GPS (AGPS), enhanced observed time difference (E-OTD), cell identifier (CI), service area identifier (SAI), enhanced timing advance (ETA), base station subsystem (BSS), etc., to further determine the physical location of the client computer 200 on the surface of the earth. It should be understood that under different conditions, the GPS transceiver 258 can determine the physical location of the client computer 200. However, in one or more embodiments, the client computer 200 can provide other information that can be used to determine the physical location of the client computer through other components, including, for example, a media access control (MAC) address, an IP address, etc.

[0071] In at least one of the various embodiments, applications such as operating system 206, other client applications 224, web browser 226, etc. can be arranged to use geographic location information to select one or more localization features, such as time zone, language, currency, calendar format, etc. Localization functionality can be used for display objects, data models, data objects, user interfaces, reports, and internal processes or databases. In at least one of the various embodiments, the geographic location information used to select the location information can be provided by GPS 258. In addition, in some embodiments, the geographic location information can include information provided via a network such as wireless network 108 or network 111 using one or more geolocation protocols.

[0072] A human interface component can be a peripheral device that is physically separate from the client computer 200 and allows remote input or output to the client computer 200. For example, information that is routed through a human interface component such as the display 250 or the keypad 252 as described herein can instead be routed to an appropriate human interface component located remotely via the network interface 232. Examples of human interface peripheral components that can be remote include, but are not limited to, audio devices, pointing devices, keypads, displays, cameras, projectors, and the like. These peripheral components can be connected to a computer via, for example, Bluetooth. TM 、ZigBee TM A non-limiting example of a client computer having such a peripheral human-machine interface component is a wearable computer, which may include a remote micro-projector and one or more cameras in remote communication with a separately located client computer to sense a user's gesture toward a portion of an image projected by the micro-projector onto a reflective surface (e.g., a wall or a user's hand).

[0073] The client computer may include a web browser application 226 configured to receive and send web pages, web-based messages, graphics, text, multimedia, etc. The browser application of the client computer may use virtually any programming language, including Wireless Application Protocol messaging (WAP), etc. In one or more embodiments, the browser application is enabled to use Handheld Device Markup Language (HDML), Wireless Markup Language (WML), WMLScript, JavaScript, Standard Generalized Markup Language (SGML), Hypertext Markup Language (HTML), Extensible Markup Language (XML), HTML5, etc.

[0074] The memory 204 may include RAM, ROM, or other types of memory. The memory 204 illustrates an example of a computer-readable storage medium (device) for storing information such as computer-readable instructions, data structures, program modules, or other data. The memory 204 may store a BIOS 208 for controlling the low-level operation of the client computer 200. The memory may also store an operating system 206 for controlling the operation of the client computer 200. It should be understood that this component may include a general-purpose operating system, such as a version of UNIX, or Linux. TM , or a dedicated client computer communication operating system, such as Windows Phone TM ,or Operating system. The operating system may include or interface with a Java virtual machine module that enables control of hardware components or operating system operations through Java application programs.

[0075] Memory 204 may also include one or more data stores 210 that client computer 200 may utilize to store applications 220 or other data. For example, data stores 210 may also be used to store information describing various capabilities of client computer 200. This information may then be provided to another device or computer based on any of a variety of methods, including being sent as part of a header during a communication, being sent upon request, and the like. Data stores 210 may also be used to store social network information, including address books, friend lists, aliases, user profile information, and the like. Data stores 210 may also include program code, data, algorithms, and the like for use by a processor, such as processor 202, to take and execute actions. In one embodiment, at least some of data stores 210 may also be stored on another component of client computer 200, including, but not limited to, a non-transitory processor-readable removable storage device 236, a processor-readable fixed storage device 234, or even external to the client computer.

[0076] Applications 220 may include computer-executable instructions that, when executed by client computer 200, may send, receive, or otherwise process instructions and data. Applications 220 may include, for example, a client visualization engine 222, other client applications 224, a web browser 226, etc. The client computer may be arranged to exchange communications with one or more servers.

[0077] Other examples of applications include calendars, search programs, email client applications, IM applications, SMS applications, Voice over Internet Protocol (VOIP) applications, contact managers, task managers, transcoders, database programs, word processing programs, security applications, spreadsheet programs, games, search programs, visualization applications, and the like.

[0078] In addition, in one or more embodiments (not shown), the client computer 200 may include an embedded logic hardware device instead of a CPU, such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a programmable array logic (PAL), etc., or a combination thereof. The embedded logic hardware device can directly execute its embedded logic to perform an action. In addition, in one or more embodiments (not shown), the client computer 200 may include one or more hardware microcontrollers instead of a CPU. In one or more embodiments, the one or more microcontrollers can directly execute their own embedded logic to perform an action and access their own internal memory and their own external input and output interfaces (e.g., hardware pins or wireless transceivers) to perform an action, such as a system on a chip (SOC), etc.

[0079] Illustrative Network Computer

[0080] Figure 3 One embodiment of a network computer 300 is shown, which may be included in a system implementing one or more of the various embodiments. The network computer 300 may include Figure 3 The components shown in FIG may be more or less than those shown. However, the components shown are sufficient to disclose an illustrative embodiment for practicing these innovations. The network computer 300 may represent, for example, Figure 1 An embodiment of at least one of the visualization server computer 116, the data source server computer 118, etc.

[0081] A network computer, such as network computer 300, may include a processor 302 that can communicate with memory 304 via bus 328. In some embodiments, processor 302 may be composed of one or more hardware processors, or one or more processor cores. In some cases, one or more of the one or more processors may be dedicated processors designed to perform one or more dedicated actions, such as those described herein. Network computer 300 also includes a power supply 330, a network interface 332, an audio interface 356, a display 350, a keyboard 352, an input / output interface 338, a processor-readable fixed storage device 334, and a processor-readable removable storage device 336. Power supply 330 provides power to network computer 300.

[0082] The network interface 332 includes circuitry for coupling the network computer 300 to one or more networks and is configured for one or more communication protocols and technologies, including, but not limited to, protocols and technologies that implement any portion of the Open Systems Interconnection model (OSI model), Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), User Datagram Protocol (UDP), Transmission Control Protocol / Internet Protocol (TCP / IP), Short Message Service (SMS), Multimedia Message Service (MMS), General Packet Radio Service (GPRS), WAP, Ultra-Wideband (UWB), IEEE 802.16 Worldwide Interoperability for Microwave Access (WiMax), Session Initiation Protocol / Real-Time Transport Protocol (SIP / RTP), or various other wired and wireless communication protocols. The network interface 332 is sometimes referred to as a transceiver, transceiver device, or network interface card (NIC). The network computer 300 optionally communicates with a base station (not shown) or directly with another computer.

[0083] The audio interface 356 is arranged to generate and receive audio signals, such as the sound of a human voice. For example, the audio interface 356 can be coupled to a speaker and a microphone (not shown) to enable communication with others or to generate audio confirmations for certain actions. The microphone in the audio interface 356 can also be used for input or control of the network computer 300, for example using voice recognition.

[0084] Display 350 can be a liquid crystal display (LCD), gas plasma, electronic ink, light emitting diode (LED), organic LED (OLED), or any other type of light reflective or light transmissive display that can be used with a computer. In some embodiments, display 350 can be a handheld projector or pico projector capable of projecting an image onto a wall or other object.

[0085] The network computer 300 may also include a Figure 3 The input / output interface 338 can be used to communicate with a computer or external device not shown in the figure. The input / output interface 338 can use one or more wired or wireless communication technologies, such as USB TM 、Firewire TM , WiFi, WiMax, Thunderbolt TM , infrared, Bluetooth TM 、ZigBee TM , serial port, parallel port, etc.

[0086] In addition, the input / output interface 338 may also include one or more sensors for determining geographic location information (e.g., GPS), monitoring power conditions (e.g., voltage sensor, current sensor, frequency sensor, etc.), monitoring weather (e.g., thermostat, barometer, anemometer, humidity detector, precipitation scale, etc.), etc. The sensor can be one or more hardware sensors that collect or measure data external to the network computer 300. The human interface component can be physically separated from the network computer 300, allowing remote input or output to the network computer 300. For example, information routed through a human interface component such as the display 350 or keyboard 352 as described herein can instead be routed through the network interface 332 to an appropriate human interface component located elsewhere on the network. The human interface component includes any component that allows a computer to obtain input from or send output to a human user of the computer. Thus, a pointing device such as a mouse, stylus, trackball, etc. can communicate through the pointing device interface 358 to receive user input.

[0087] The GPS transceiver 340 can determine the physical coordinates of the network computer 300 on the surface of the Earth, typically outputting the location as latitude and longitude values. The GPS transceiver 340 can also use other geolocation mechanisms, including but not limited to triangulation, assisted GPS (AGPS), enhanced observed time difference (E-OTD), cell identifier (CI), service area identifier (SAI), enhanced timing advance (ETA), base station subsystem (BSS), etc., to further determine the physical location of the network computer 300 on the surface of the Earth. It should be understood that under different conditions, the GPS transceiver 340 can determine the physical location of the network computer 300. However, in one or more embodiments, the network computer 300 can provide other information that can be used to determine the physical location of the client computer through other components, including, for example, a media access control (MAC) address, an IP address, etc.

[0088] In at least one of the various embodiments, applications such as operating system 306, assessment engine 322, visualization engine 324, modeling engine 326, other applications 329, and the like can be arranged to utilize geographic location information to select one or more location characteristics, such as time zone, language, currency, currency format, calendar format, and the like. Localization functionality can be used for user interfaces, dashboards, visualizations, reports, and internal processes or databases. In at least one of the various embodiments, the geographic location information used to select location information can be provided by GPS 340. Furthermore, in some embodiments, the geographic location information can include information provided via a network, such as wireless network 108 or network 111, using one or more geolocation protocols.

[0089] Memory 304 may include random access memory (RAM), read-only memory (ROM), or other types of memory. Memory 304 illustrates an example of a computer-readable storage medium (device) for storing information such as computer-readable instructions, data structures, program modules, or other data. Memory 304 stores a basic input / output system (BIOS) 308 for controlling the low-level operation of network computer 300. Memory also stores an operating system 306 for controlling the operation of network computer 300. It should be understood that this component may include a general-purpose operating system, such as a version of UNIX or LINUX™, or a specialized operating system, such as Microsoft Corporation's BIOS. operating system, or Apple Corporation's Operating system. The operating system may include, or interface with, one or more virtual machine modules, such as a Java virtual machine module that allows Java applications to control hardware components or operating system operations. Other runtime environments may also be included.

[0090] Memory 304 may also include one or more data stores 310, which may be used by network computer 300 to store application programs 320 or other data. For example, data stores 310 may also be used to store information describing various capabilities of network computer 300. This information may then be provided to another device or computer based on any of a variety of methods, including being sent as part of a header during communication, being sent upon request, and the like. Data stores 310 may also be used to store social network information, including address books, friend lists, aliases, user profile information, and the like. Data stores 310 may also include program code, data, algorithms, and the like for use by a processor, such as processor 302, to perform and execute actions, such as those described below. In one embodiment, at least some of data stores 310 may also be stored on another component of network computer 300, including, but not limited to, non-transitory media within processor-readable removable storage device 336, processor-readable fixed storage device 334, or any other computer-readable storage device within network computer 300 or even external to network computer 300. The data storage 310 may include, for example, a data model 314 , a data source 316 , a visualization model 318 , an evaluation model 319 , and the like.

[0091] Applications 320 may include computer-executable instructions that, when executed by network computer 300, send, receive, or otherwise process messages (e.g., SMS, Multimedia Messaging Service (MMS), Instant Messaging (IM), email, or other messages), audio, video, and enable telecommunications with another user of another mobile computer. Other examples of applications include calendars, search programs, email client applications, IM applications, SMS applications, Voice over Internet Protocol (VOIP) applications, contact managers, task managers, transcoders, database programs, word processing programs, security applications, spreadsheet programs, games, search programs, and the like. Applications 320 may include an evaluation engine 322, a visualization engine 324, a modeling engine 326, other applications 329, and the like, which may be arranged to perform actions for the embodiments described below. In one or more of the various embodiments, one or more applications may be implemented as a module or component of another application. Additionally, in one or more of the various embodiments, an application may be implemented as an operating system extension, module, plug-in, and the like.

[0092] In addition, in one or more of the various embodiments, the assessment engine 322, visualization engine 324, modeling engine 326, other applications 329, etc. can operate in a cloud-based computing environment. In one or more of the various embodiments, these applications and other applications, including the management platform, can be executed within a virtual machine or virtual server (which can be managed in a cloud-based computing environment). In one or more of the various embodiments, in this context, applications can flow from one physical network computer within the cloud-based environment to another physical network computer based on performance and scaling considerations automatically managed by the cloud computing environment. Likewise, in one or more of the various embodiments, virtual machines or virtual servers dedicated to the assessment engine 322, visualization engine 324, modeling engine 326, other applications 329, etc. can be automatically provisioned and decommissioned.

[0093] Furthermore, in one or more of the various embodiments, the assessment engine 322, visualization engine 324, modeling engine 326, other applications 329, etc. may be located in virtual servers running in a cloud-based computing environment rather than being tied to one or more specific physical network computers.

[0094] Additionally, the network computer 300 may include a hardware security module (HSM) 360 for providing additional tamper-proofing for generating, storing, or using security / cryptographic information such as keys, digital certificates, passwords, passphrases, two-factor authentication information, and the like. In some embodiments, the hardware security module may be configured to support one or more standard public key infrastructures (PKIs) and may be configured to generate, manage, or store key pairs, etc. In some embodiments, the HSM 360 may be a standalone network computer; in other cases, the HSM 360 may be configured as a hardware card that may be installed in the network computer.

[0095] In addition, in one or more embodiments (not shown), the network computer 300 may include an embedded logic hardware device instead of a CPU, such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a programmable array logic (PAL), etc., or a combination thereof. The embedded logic hardware device can directly execute its embedded logic to perform an action. In addition, in one or more embodiments (not shown), the network computer may include one or more hardware microcontrollers instead of a CPU. In one or more embodiments, one or more microcontrollers can directly execute their own embedded logic to perform an action and access their own internal memory and their own external input and output interfaces (e.g., hardware pins or wireless transceivers) to perform an action, such as a system on a chip (SOC).

[0096] Descriptive Logical System Architecture

[0097] Figure 4 The logical architecture of a system 400 for analyzing tags in a visualization based on data features is shown, according to one or more of various embodiments. In one or more of the various embodiments, system 400 can be composed of various components, including: one or more modeling engines, such as modeling engine 402; one or more visualization engines, such as visualization engine 404; one or more visualizations, such as visualization 406; one or more data sources, such as data source 410; one or more visualization models, such as visualization model 408; or one or more evaluation engines, such as evaluation engine 412.

[0098] In one or more of the various embodiments, modeling engine 402 can be arranged to enable a user to design one or more visualization models that can be provided to visualization engine 404. Thus, in one or more of the various embodiments, visualization engine 404 can be arranged to generate one or more visualizations based on the visualization models.

[0099] In one or more of the various embodiments, the modeling engine may be arranged to access one or more data sources, such as data source 410. In some embodiments, the modeling engine may be arranged to include a user interface that enables a user to browse various data source information, data objects, etc. to design a visualization model that can be used to generate visualizations of the information stored in the data source.

[0100] Thus, in some embodiments, a visualization model can be designed to provide visualizations that include charts, drawings, graphs, tables, graphics, styles, descriptive text, interactive elements, user interface features, etc. In some embodiments, a graphical user interface can be provided to users that enables them to interactively design the visualization model such that various elements or display objects in the visualization model can be associated with data from one or more data sources, such as data source 410.

[0101] In one or more of the various embodiments, a data source such as data source 410 may include one or more of a database, data store, file system, etc., which may be located locally or remotely. In some embodiments, the data source may be provided by another service on a network. In some embodiments, there may be one or more components (not shown) that filter or otherwise provide administrative views or administrative access to the data in the data source.

[0102] In one or more of the various embodiments, the visualization model may be stored in one or more data stores, such as visualization model store 408. In this example, for some embodiments, visualization model store 408 represents one or more databases, file systems, etc. for storing, protecting, or indexing visualization models.

[0103] In one or more of the various embodiments, a visualization engine, such as visualization engine 404 , may be arranged to parse or otherwise interpret visualization models and data from data sources to generate one or more visualizations that may be displayed to a user.

[0104] In one or more of the various embodiments, an evaluation engine, such as evaluation engine 412, can be arranged to evaluate or otherwise assess markers in a visualization. Thus, in some embodiments, the evaluation engine can be arranged to automatically provide a statistical description of the value of a particular data point (e.g., a marker) even if the data used for the description has been omitted from the visualization. In some embodiments, the evaluation engine can be arranged to automatically pull in additional data from a data source associated with the visualization and assess its relevance using a statistical model, such as an evaluation model. In one or more of the various embodiments, descriptions of the markers can be conveyed to the user as text strings and interactive visualizations, as will be discussed further.

[0105] In one or more of the various embodiments, the evaluation engine can enable a user to select one or more tags of interest from the visualization. Thus, in some embodiments, the visualization engine can be arranged to generate a visualization that includes an interactive user interface feature that enables a user to select a tag of interest. For example, in one or more of the various embodiments, the visualization engine can be arranged to include an Evaluate This Tag command in a right-click context menu. Thus, in some embodiments, a user can right-click a display object representing a tag of interest to pop up a context menu, and then select the Evaluate This Tag command from the context menu. In other embodiments, a user can search for a tag of interest using a name or tag associated with the tag.

[0106] Figure 5A logical representation of a portion of visualization 500 is shown according to one or more of various embodiments. As described above, a visualization engine can be arranged to use a visualization model and data to generate a visualization, such as visualization 500. In this example, visualization 500 represents a bar chart showing sales revenue by day of the week. One of ordinary skill in the art will understand that a visualization model or visualization engine can be arranged to generate many different types of visualizations for various purposes based on the design goals of a user or organization. Visualization 500 is presented here as a non-limiting example to help provide clarity in the description of these innovations. One of ordinary skill in the art will understand that this example is at least sufficient to disclose the innovations herein, and that a visualization engine or visualization model can be arranged to generate many different visualizations for many different purposes in many fields.

[0107] In this example, visualization 500 includes a marker 502 representing revenue earned on Sundays. Thus, in this example, if marker 502 appears significantly lower than the other markers in visualization 500, marker 502 may appear to be an anomalous result.

[0108] In this example, tag 502 may be determined to be a tag of interest because it may appear unusual compared to other tags that may be associated with revenue values ​​for other days of the week. In some embodiments, a user may be enabled to identify one or more tags of interest that appear interesting or unusual. Furthermore, in some embodiments, the evaluation engine may be arranged to automatically identify one or more tags of interest based on automatically identifying tags that may be unusual or statistical outliers.

[0109] In some embodiments, if a marker can be identified as a marker of interest, the evaluation engine can be arranged to automatically perform one or more actions to analyze the marker of interest to provide an explanation of the significant difference. In some cases, the analysis performed by the evaluation engine can determine that the marker of interest may be within the expected range, rather than an anomaly.

[0110] Figure 6 A logical representation of a portion of a marker evaluation system 600 is shown according to one or more of various embodiments. In one or more of the various embodiments, the system 600 can include one or more components, such as an evaluation engine 602, an evaluation model 604, a visualization model 606, a data source 608, markers of interest 610, and evaluation results 612. In some embodiments, evaluation results, such as evaluation results 612, can be arranged to include a confidence score 614 or a narrative 616.

[0111] In one or more of the various embodiments, the evaluation engine 602 can be arranged to evaluate the marker of interest 610 based on the evaluation model 604. In one or more of the various embodiments, the evaluation model can be arranged to include one or more heuristic or machine learning evaluators that can be executed to classify the marker of interest.

[0112] As discussed herein, the evaluation engine can be arranged to employ one or more evaluation models and provide one or more reports regarding the extent to which a given evaluation model matches (or classifies) a token of interest. Thus, in this example, the evaluation results 612 include a score, such as a confidence score 614, and a natural language narrative 616.

[0113] In one or more of the various embodiments, the evaluation models can be arranged to provide scores that represent the extent to which they describe the markers of interest. In some embodiments, the evaluation engine can be arranged to execute or apply the evaluation model to perform various evaluations of the markers of interest, visualization models, or data sources to classify the markers of interest. In some embodiments, a confidence score representing the degree of fit of the markers of interest to the evaluation model can be provided by the evaluation model. For example, evaluation model A can be arranged to perform ten tests or evaluate ten conditions, which provide a score comprising ten points for each matching condition. Similarly, in some embodiments, the evaluation model can execute or apply a classifier that provides a confidence score.

[0114] In one or more of the various embodiments, different evaluation models may employ different scoring criteria. Thus, in some embodiments, the evaluation engine may be arranged to weight or normalize the confidence scores provided by the different evaluation models. In some embodiments, the specific normalization rules or weighting rules for normalizing or weighting the evaluation model confidence scores may be provided via configuration information.

[0115] Additionally, in one or more of the various embodiments, the assessment model can be arranged to provide a natural language narrative, such as narrative 616. In some embodiments, the natural language narrative can be used in a user interface or in a report that can be provided to a user to illustrate the assessment of the marker of interest for a given assessment model. In some embodiments, the narrative can be based on a template that enables labels, units, values, etc. (which can be associated with the marker of interest or the visualization model) to be included in the user interface or report information.

[0116] In one or more of the various embodiments, the evaluation model can be designed or customized to evaluate one or more statistical characteristics of data associated with the marker of interest. Thus, in one or more of the various embodiments, the evaluation engine can be arranged to apply the one or more evaluation models to evaluate whether the data associated with the marker of interest has one or more statistical characteristics targeted by the evaluation model. In some embodiments, the evaluation model can be arranged to provide a confidence score in the form of a self-rating that represents how closely the data associated with the marker of interest matches or otherwise evaluates the statistical characteristics that the evaluation model can be designed to match or otherwise evaluate.

[0117] In one or more of the various embodiments, one or more evaluation models can focus on general, well-known, or common statistical features that can be expected to be associated with a marker of interest.

[0118] In addition, in one or more of the various embodiments, one or more evaluation models can be customized or directed to a specific problem domain or business domain. For example, an evaluation model for financial information may be different from an evaluation model for employee information. Similarly, for example, an evaluation model for the automotive industry may be arranged differently from an evaluation model for the cruise (ship) industry. In addition, in one or more of the various embodiments, one or more evaluation models can be customized for a specific data source, or a visualization model can be customized for a specific organization or user. Therefore, in one or more of the various embodiments, the evaluation models can be stored in a data storage device so that they can be configured independently of each other.

[0119] In one or more of the various embodiments, the assessment engine may be arranged to generate or maintain profiles of one or more assessment models. In some embodiments, the profiles may be arranged to track information that can be used to adapt assessment model results to specific organizations, users, problem domains, etc.

[0120] Thus, in one or more of the various embodiments, the evaluation engine may be arranged to use user activity information or user feedback to automatically construct an evaluation model profile that can be used to modify or customize the evaluation report. For example, if users of an organization consistently report mismatches between markers of interest and evaluation results, the evaluation engine may be arranged to introduce a weighting rule that increases or decreases the effective confidence score used to rank the organization's evaluation results based on the user feedback information.

[0121] In one or more of the various embodiments, if a user selects a marker of interest in a visualization, the evaluation engine can determine one or more evaluation models and apply them to the marker of interest and its associated visualization model or data source. Therefore, non-limiting examples of evaluation models will be discussed below. For the sake of brevity and clarity, this discussion is limited to a few examples; however, one of ordinary skill in the art will appreciate that other evaluation models incorporating other or additional evaluation strategies are contemplated.

[0122] Number of Rows: The evaluation model can be arranged to determine whether there may be an unusually high or low number of data values ​​or data records that contribute to the value represented by the mark of interest, compared to other marks in the visualization. For example, in some cases, if the value of the mark of interest appears high compared to other marks, this may be explained because the number of underlying records contributing to the mark of interest may be higher than for the other marks.

[0123] Row Metrics: The evaluation model can be used to determine whether the average value in the row clustered around the mark of interest is high compared to the other marks in the visualization. For example, in some cases, if the value of the mark of interest appears high compared to other marks, this might be explained because the underlying records contributing to the mark of interest may have higher-than-average values ​​compared to the underlying records for the other marks.

[0124] Unvisualized Dimensions: You can arrange the evaluation model to assess whether the data records involving the mark of interest differ from other rows in some dimension not included in the visualization the user sees. For example, store X may have a high average order value because it sells diamonds, while most other stores do not. Furthermore, other stores that sell diamonds also have high average order values.

[0125] Visualization Dimensions: The evaluation model can be arranged to assess whether the data records involved in the marker of interest differ from other data records along some dimension included in the visualization. For example, total sales for store X were high in 2015, but this was part of an overall trend in sales by store rather than geographic region, which is related to the difference between the marker of interest and other markers.

[0126] An outlier: The evaluation model can be configured to determine whether a single outlier may exist in the data records associated with the marker of interest, which may cause the marker of interest to appear different from other markers in the visualization. Thus, in some embodiments, this may suggest that the single data record may be worth further investigation. For example, Region X may have high sales on 2018-04-28 because an anomalous order Y occurred on that day.

[0127] Multiple Outliers: The evaluation model can be configured to determine if there are multiple outliers that could collectively cause the marker of interest to appear different from the other markers in the visualization. This finding could suggest a missing underlying factor. For example, Region X may have high sales on 2018-04-28 because orders Y1, Y2, and Y3 all occurred in that region on that day. Such a result might warrant further investigation.

[0128] Intermediate Aggregation: The evaluation model can be arranged to determine whether a subset of data records associated with a tag value of interest produces values ​​that are inconsistent or unlikely compared to the entire set of data records or to other subsets of data records. For example, the evaluation model might report that Region X had high sales on 2018-04-28 because Store Y is in Region X and it had high sales on that day, but Store Y did not have a single order that dominated the sales.

[0129] Figure 7 A logical representation of a portion of a user interface 700 for analyzing markers in a visualization based on data features is shown according to one or more of various embodiments. In some embodiments, the user interface 700 can be arranged to include one or more panels, such as panel 702, panel 704, panel 706, panel 708, instructions 710, and the like.

[0130] In this example, for one or more of various embodiments, panel 702 can be arranged to display a hierarchical list of descriptions of the markers of interest analyzed by the evaluation engine. In some embodiments, each description item can include a natural language narrative that provides a potential description of the value associated with the marker of interest determined by the evaluation engine. Similarly, in some embodiments, if the evaluation engine may be unable to determine a possible description, panel 702 can be arranged to display a narrative to that effect.

[0131] In one or more of the various embodiments, the text of the instructional narrative can be based on a template such that field names or labels that can be associated with the tag or the description of the tag can be included in the instructional narrative.

[0132] In one or more of the various embodiments, panel 704 can be arranged to include additional descriptions or visualizations that can be associated with the markers analyzed by the evaluation engine. In some embodiments, a panel such as panel 706 can include additional description narratives associated with the marker, or one or more visualizations that can help explain the marker to the user. Additionally, in some embodiments, a panel such as panel 708 can include visualizations that help explain the marker. For example, panel 708 can include one or more alternative visualizations that help explain why the marker is abnormal.

[0133] In one or more of the various embodiments, the assessment engine, visualization engine, etc. can be configured to use specific visualization models or explanatory text / narrative templates for different assessment models. In some embodiments, the visualization model or explanatory text / narrative template for the assessment model can be defined in the configuration information. Thus, the explanatory text / narrative text or visualization included in the user interface 700 can be tailored to a specific organization, scenario, etc.

[0134] In one or more of the various embodiments, the assessment engine or visualization engine can be arranged to determine, via configuration information, some or all of the content or style of user interface 700. Thus, in some embodiments, narrative instruction text or templates, panel layouts, visualizations, etc. can be configured differently depending on the needs of an organization, user, etc.

[0135] Common operations

[0136] Figures 8 to 12 Represents a general operation for analyzing markers in a visualization based on data features according to one or more of various embodiments. In one or more of various embodiments, in combination Figures 8 to 12 The described processes 800, 900, 1000, 1100 and 1200 may be performed by a single network computer (or network monitoring computer) (e.g. Figure 3 In other embodiments, these processes or parts thereof may be implemented or executed by one or more processors on a network computer (e.g., a network computer 300). Figure 3 In other embodiments, the processes or portions thereof may be implemented by or executed on one or more virtualized computers, such as virtualized computers in a cloud-based environment. However, the embodiments are not limited thereto, and various combinations of network computers, client computers, etc. may be used. In addition, in one or more of the various embodiments, in combination with Figures 8 to 12 The described process can be used to combine Figures 4 to 7 At least one of the various embodiments or architectures described above, wherein the marking in the visualization is based on the analysis of data characteristics. In addition, in one or more of the various embodiments, some or all of the actions performed by processes 800, 900, 1000, 1100, and 1200 can be partially performed by the evaluation engine 322, the visualization engine 324, and the modeling engine 326 of one or more processors of one or more network computers.

[0137] Figure 8A flowchart overview of a process 800 for analyzing markers in a visualization based on data features is shown, according to one or more of various embodiments. Following a start block, in one or more of various embodiments, a visualization engine may be arranged to generate one or more visualizations based on one or more visualization models or data sources at block 802. As described above, a visualization system may be arranged to include one or more modeling engines, one or more data sources, one or more visualization engines, etc., which may be arranged to generate visualizations based on one or more visualization models and data provided by one or more data sources.

[0138] In one or more of the various embodiments, the evaluation engine may be arranged to determine one or more markers of interest in the one or more visualizations at block 804. In some embodiments, a user may select a marker of interest.

[0139] In one or more of the various embodiments, the evaluation engine may be arranged to automatically identify one or more tags in a visualization that may be inconsistent with other tags. In some embodiments, the evaluation engine may be arranged to perform actions to perform one or more heuristic evaluations to determine whether one or more tags can be identified as tags of interest. In some embodiments, the evaluation engine may be arranged to highlight or otherwise indicate which tags may be tags of interest in the visual user interface. The specific style of indicating tags of potential interest may vary depending on the organization and configuration information.

[0140] In some embodiments, markers of interest automatically determined by the evaluation engine can be considered potential markers of interest. Thus, in some embodiments, a user can be enabled to confirm whether a potential marker of interest should be evaluated by the evaluation engine.

[0141] In one or more of the various embodiments, the evaluation engine may be arranged to analyze the one or more markers of interest based on the one or more evaluation models at block 806. In one or more of the various embodiments, the evaluation engine may be arranged to execute the one or more evaluation models to evaluate the markers of interest to determine descriptions that may provide insight into how characteristics of the underlying data / data source contribute to the markers of interest.

[0142] At block 808, in one or more of the various embodiments, the assessment engine may be arranged to generate one or more assessment reports, which may include one or more visualizations or one or more explanatory narratives associated with the one or more markers. As described above, in some embodiments, the assessment report may include an interactive user interface that enables a user to review the assessment results, which may include an explanatory narrative that may describe one or more characteristics of the markers of interest.

[0143] Next, in one or more of the various embodiments, control may be returned to the calling process.

[0144] Figure 9 A flow chart of a process 900 for analyzing tags using an evaluation model is shown, according to one or more of various embodiments. Following a start block, at block 902, in one or more of various embodiments, an evaluation engine may be one or more evaluation models and one or more tags of interest. As described above, in some embodiments, one or more evaluation models may be defined for evaluating tags. Thus, in some embodiments, the evaluation engine may be arranged to obtain one or more evaluation models from a data store, etc. In some embodiments, the evaluation engine may be arranged to determine a particular evaluation model based on rules, conditions, etc., which may be provided via configuration information.

[0145] At block 904, in one or more of the various embodiments, the evaluation engine may be arranged to evaluate one or more evaluation models based on the indicia, the visualization model, the data source, etc. In one or more of the various embodiments, the evaluation model may include or be associated rules, conditions, computer-readable instructions, etc. that the evaluation engine may execute or apply to evaluate the indicia.

[0146] At decision block 906, in one or more of various embodiments, if there may be more evaluation models to evaluate, control may loop back to block 904; otherwise, control may flow to block 908. In some embodiments, the evaluation engine may be arranged to prematurely terminate the evaluation by omitting or skipping one or more evaluation models. For example, in some embodiments, the evaluation engine may be configured to stop evaluating additional evaluation models if it is deemed that the previously evaluated evaluation models provide sufficient descriptions of the markers of interest.

[0147] Thus, in one or more of the various embodiments, the assessment engine may be arranged to associate a confidence score with the assessment result provided by the assessment model. In some embodiments, the assessment model may be arranged to provide a confidence score indicating the degree to which the assessment model matches or describes the tag.

[0148] Furthermore, in one or more of the various embodiments, the assessment engine can be arranged to maintain another set of confidence scores that can be combined with the confidence scores provided by the assessment model. Thus, in some embodiments, the overall confidence score for the assessment of a marker can be a combination of the score provided by the assessment model and the score provided by the assessment engine.

[0149] For example, in some embodiments, the confidence score provided by the assessment engine can be generated based on other factors or metrics that are not available or relevant to the assessment model. In some embodiments, such factors or metrics can be based on user feedback, organizational needs (e.g., configuration information), metrics associated with organizational or community activities, etc.

[0150] In one or more of the various embodiments, the evaluation engine may be arranged to filter and sort the results provided by the evaluation model at block 908. In one or more of the various embodiments, the evaluation model may be arranged to provide one or more confidence scores representing its own assessment of how closely the description provided by the model matches the label.

[0151] Furthermore, in one or more of the various embodiments, the assessment engine may be arranged to modify the confidence score provided by the assessment model to provide a final confidence score.

[0152] Thus, in one or more of the various embodiments, the evaluation engine may be arranged to eliminate one or more descriptions based on filtering out one or more evaluation models based on rules, conditions, etc. For example, in some embodiments, the evaluation engine may be configured to automatically exclude descriptions associated with confidence scores below a defined threshold.

[0153] Furthermore, in one or more of the various embodiments, other metrics or characteristics of one or more of the descriptions, visualization models, data sources, data, users, organizations, etc., can be incorporated into conditions, rules, etc., which can be executed to filter out one or more assessments or descriptions. For example, in some embodiments, a filter can include conditions associated with one or more user roles. Thus, for example, a filter can be configured to be more inclusive for some user roles or less inclusive for others. Thus, in this example, the number of descriptions included in the assessment report can be increased for data scientists and decreased for general users.

[0154] In some embodiments, other metrics or characteristics used for filtering can be based on various sources, including organizational preferences, user preferences, location, user input, other configuration information, and the like.

[0155] Similarly, in one or more of the various embodiments, the evaluation engine can be arranged to rank one or more descriptions based on various conditions, rules, metrics, or characteristics. For example, in some embodiments, the descriptions can be ranked based on confidence scores, etc. Furthermore, in some embodiments, for example, one or more descriptions can be ranked based on user preferences, organizational preferences, etc.

[0156] Similar to filters, in some embodiments, the various conditions, rules, metrics, or characteristics used for ranking instructions can be based on various sources, including organizational preferences, user preferences, localization, user input, other configuration information, etc.

[0157] In one or more of the various embodiments, the evaluation engine can be arranged to generate an evaluation report at block 910. In one or more of the various embodiments, the evaluation report can include various information, including a ranked list of descriptions, a description of one or more characteristics of the evaluated markers of interest, a visualization showing the markers of interest in different contexts or views, and the like.

[0158] Next, in one or more of the various embodiments, control may be returned to the calling process.

[0159] Figure 10 A flow chart of a process 1000 for adapting filtering or ranking of an evaluation model based on monitoring user interactions is shown, according to one or more of various embodiments. Following a start block, in block 1002, in one or more of various embodiments, an evaluation engine can be arranged to generate an evaluation report based on an automatic evaluation of one or more markers of interest. As described above, the evaluation engine can be arranged to provide information for generating an interactive report, including one or more user interface features that enable a user to interact with the instructions.

[0160] Additionally, in one or more of the various embodiments, the interactive evaluation report can include one or more user interface components that enable a user to provide feedback to rate the instructions. For example, in some embodiments, the interactive evaluation report can enable a user to rate an instruction or visualization using various rating systems, such as helpful / unhelpful, a rating scale (e.g., 1-100, stars, letter grades, etc.), a natural language narrative, etc.

[0161] In box 1004, in one or more of various embodiments, the assessment engine can be arranged to monitor one or more user interactions or user feedback that can be associated with the assessment report.As mentioned above, the interactive assessment report can be arranged to include components or features for directly collecting user feedback.For example, in some embodiments, the user can be made to grade the usefulness or correctness of one or more explanations.Therefore, in one or more of various embodiments, the assessment engine can monitor or record the feedback that is associated with the various parts of the assessment report.In some embodiments, the assessment engine can be arranged to enable the user to provide overall grade for whole assessment report.

[0162] In addition, in one or more of the various embodiments, the evaluation engine may be arranged to passively monitor how one or more users interact with the evaluation report. In some embodiments, monitoring various user interaction metrics can provide additional insights into the performance or quality of the evaluations that can be provided by various evaluation models. For example, in some embodiments, if the monitored interactions show that the user is doing things like ignoring one or more instructions, reclassifying the instruction list, spending a lot of time reviewing lower-ranked instructions, clicking on help screens, running several tag evaluations in a short period of time, etc., it may be an indication that the instruction narrative or evaluation model may not be satisfactorily explaining the tag. In contrast, for example, monitored information indicating that the user accepted the instructions without performing additional confirmation actions or reviews may indicate that the evaluation report may be satisfactory.

[0163] In one or more of the various embodiments, the evaluation engine may be arranged to provide a modified confidence score based on the monitored interactions or feedback at block 1006. In one or more of the various embodiments, the evaluation engine may be arranged to execute one or more formulas to generate a confidence score indicating how well the evaluation model performs.

[0164] Thus, in one or more of the various embodiments, the evaluation engine can be arranged to increase or decrease the evaluation model confidence score based on user feedback or observed user activity. In some embodiments, the impact of various types of feedback or observed activity can vary depending on the type of feedback or observed activity.

[0165] In one or more of the various embodiments, the assessment engine may be arranged to provide or modify the confidence score based on one or more rules or actions that may be defined in the configuration information.

[0166] At decision block 1008 , in one or more of the various embodiments, if the confidence score of the one or more evaluation models is below a defined threshold, control may pass to block 1010 ; otherwise, control may flow to block 1012 .

[0167] At block 1010, in one or more of various embodiments, the evaluation engine may be arranged to discard or retrain one or more low-scoring evaluation models. In some embodiments, the evaluation engine may be arranged to exclude one or more low-scoring evaluation models from use in a particular organization. Furthermore, in some embodiments, the evaluation engine may be arranged to globally exclude one or more evaluation models from use in some or all other organizations based on confidence scores that may be associated with the one or more evaluation models.

[0168] In one or more of the various embodiments, rather than discarding the differential evaluation models, the evaluation engine can be arranged to indicate that one or more differential evaluation models may require retraining or recertification before being used for evaluation labeling. Thus, in some embodiments, the evaluation engine can be arranged to generate a notification or include retraining or recertification information in the evaluation report.

[0169] At block 1012, in one or more of the various embodiments, the assessment engine may be arranged to use the confidence scores to filter or sort subsequently generated tagged assessments or descriptions. In one or more of the various embodiments, the assessment engine may be arranged to enable an organization or user to define thresholds for including or excluding assessment models or assessment model results from the assessment report. Next, in one or more of the various embodiments, control may be returned to the calling process.

[0170] Figure 11 A flow chart of a process 1100 for generating an expected value distribution for an evaluation model is shown, according to one or more of various embodiments. Following a start block, in block 1102, in one or more of various embodiments, the evaluation model and the marker of interest can be provided to an evaluation engine. As described above, the evaluation engine can be arranged to evaluate a set of two or more evaluation models to determine which one can account for the performance of the marker of interest. Thus, in some embodiments, the evaluation engine can be arranged to evaluate each evaluation model in the set of models to rank them based on the degree to which they can account for the marker of interest.

[0171] At block 1104, in one or more of various embodiments, some or all of the data that can be directly displayed in a visualization can be incrementally provided to the evaluation engine. In some embodiments, the visualization that can be displayed to the user can include one or more portions of the data source. For example, in some embodiments, the visualization can be generated based on a portion of the columns or fields available in the data source. Thus, in some embodiments, the columns or fields that can be directly included in the visualization can be determined.

[0172] In one or more of the various embodiments, the evaluation engine can be arranged to incrementally add data included in the visualization to the evaluation data set. For example, in some embodiments, if the displayed visualization can be based on five columns from the data source, the evaluation engine can be arranged to evaluate the evaluation model based on two visualization columns, then based on three visualization columns, and so on.

[0173] In some embodiments, the evaluation engine may be arranged to provide data portions (e.g., columns or fields) in various sequences, such as the order in which they appear in the visualization, the order in which they appear in the data source, a random order, one or more sorted orders, etc. Thus, in some embodiments, the evaluation engine may be arranged to determine the order in which data portions may be added to the data set based on rules included in configuration information, etc.

[0174] At block 1106, in one or more of various embodiments, the evaluation engine may be arranged to use one or more evaluation models and the current dataset to provide a probability distribution for the marker of interest. Thus, in some embodiments, the evaluation model may use data fields or columns in the current dataset to attempt to predict a value for the marker of interest based on the current dataset.

[0175] Thus, in one or more of the various embodiments, a model may be used to generate a probability distribution that can predict the value of a marker of interest each time additional data can be added to the evaluation dataset.

[0176] At decision block 1108, in one or more of the various embodiments, if the displayed data can be arranged to be exhausted, control can proceed to block 1110; otherwise, control can loop back to block 1104. For example, if the visualization associated with the marker of interest includes five columns, after each evaluation model in the ensemble has generated a distribution of predicted values ​​for the marker of interest for each combination of data portions associated with the visualization. Note that the evaluation engine can be arranged to use configuration information to determine the number, order, or type of combinations of data portions used to predict the value of the marker of interest. Furthermore, in some embodiments, while most of the examples described herein relate to evaluation models that produce probability distributions, other types of models or predictors are contemplated, including models that produce single values ​​and error ranges. Furthermore, in one or more of the various embodiments, it is generally contemplated that the evaluation engine can be arranged to employ a variety of prediction models so long as they can predict the value of the marker of interest for a given data set selected from a data source.

[0177] At block 1110, in one or more of various embodiments, the evaluation engine can be arranged to incrementally modify the model dataset to include data not included in the visualization. In some embodiments, the data source can include additional data (e.g., columns or fields) not included in the visualization. In some cases, information in the additional columns or fields may account for the appearance of the marker in the visualization. Thus, similar to the description of block 1104, these data portions can be incrementally added to the evaluation dataset.

[0178] At block 1112, in one or more of the various embodiments, the evaluation engine can be arranged to generate one or more probability distributions using the evaluation model based on the incrementally modified dataset. Thus, similar to what was described with respect to block 1106, the evaluation engine can be arranged to use the evaluation dataset and the evaluation model to predict the value of the marker of interest.

[0179] At decision block 1114, in one or more of various embodiments, if the remainder of the data portion associated with the tag of interest has been exhausted, control may be returned to the calling process; otherwise, control may loop back to block 1110. See the description of decision block 1108 for additional details.

[0180] Figure 12 A flow diagram of a process 1200 for comparing results of evaluation models is shown, according to one or more of various embodiments. Following a start block, in block 1202, in one or more of various embodiments, an evaluation engine may be arranged to generate various expected value distributions as described above.

[0181] In box 1204, in one or more of the various embodiments, the evaluation engine may be arranged to generate a model performance score based on the amount of information provided by the best prediction of a given model. In some embodiments, the amount of information provided by different models can be compared by calculating the inherent randomness (e.g., entropy) of the probability distribution generated by a given model. Therefore, in one or more of the various embodiments, the evaluation engine may be arranged to use entropy to compare different models. In some embodiments, the specific mechanism for calculating the entropy of a given model and its results may vary depending on the model type. However, it will be appreciated by those skilled in the art that the evaluation engine may be arranged to perform one or more conventional or well-known information theory calculations to estimate the entropy measurement to generate a given probability distribution. In some embodiments, the evaluation engine may be arranged to use one or more rules, instructions, etc. defined in the configuration information to determine the entropy value of a given probability distribution or evaluation model. Therefore, in some embodiments, the evaluation engine may be arranged to use one or more unconventional or customized methods to calculate entropy.

[0182] In some embodiments, the amount of information provided by the evaluation model predictions can be expressed or measured using conventional or well-known information theory units, such as bits, nats, dits, etc., which enable the quantitative information included in the predictions to be expressed. Therefore, in some embodiments, the amount of information provided by different models or distributions can be compared.

[0183] At block 1206, in one or more of various embodiments, the evaluation engine may be arranged to generate a model complexity score for each evaluation model based on the complexity associated with the provided prediction. Information theory provides various mechanisms for measuring the complexity of a prediction model, which can be used to fairly compare evaluation models. In some embodiments, complexity can be considered a measure of how difficult it is for a model to produce a given result. Thus, in some embodiments, complexity can be measured based on various factors, including the number of inputs, the number of parameters, etc.

[0184] Furthermore, in one or more of the various embodiments, the complexity score can reflect how complex the suggested description of the tag of interest is. For example, in some embodiments, a suggestion that a tag of interest is strongly dependent on one other data portion (e.g., a column) can be considered less complex than a suggestion that is dependent on two or more other data portions.

[0185] In one or more of the various embodiments, the evaluation engine may be arranged to calculate a complexity metric for the evaluation model using rules, instructions, etc., which may be provided by configuration information. Typically, in some embodiments, these may include well-known or conventional information theoretic methods as well as custom or proprietary methods.

[0186] In block 1208, in one or more of the various embodiments, the assessment engine may be arranged to provide an overall model score for each assessment model based on the associated information score and complexity score. In one or more of the various embodiments, the total score may be arranged to select the assessment model that provides the most information with the least complexity. For example, in some embodiments, the information score (see, block 1204) and the complexity score (see, block 1206) may be normalized or mapped to a 0-100 scale and summed to provide an overall score for the assessment model. However, in some embodiments, the assessment engine may be arranged to use rules, instructions, etc. provided via configuration information to calculate an overall score based on the information score or the complexity score.

[0187] In box 1210, in one or more of the various embodiments, the evaluation engine may be arranged to modify one or more overall model scores based on one or more defined weights, heuristics, user preferences, etc. For example, as described above, user feedback may be used to weight the overall score of one or more evaluation models. Likewise, in one or more of the various embodiments, it may be observed that one or more evaluation models produce incorrect results under some conditions, overfit in sparse data applications, etc. In one or more of the various embodiments, the evaluation engine may be arranged to modify the overall scores of certain evaluation models under specific circumstances. Thus, in one or more of the various embodiments, the evaluation engine may be arranged to employ one or more rules, instructions, etc. provided via configuration information to determine whether the overall model score should be modified.

[0188] At block 1212 , in one or more of the various embodiments, the evaluation engine may be arranged to rank the evaluation models based on the modified total scores.

[0189] Next, in one or more of the various embodiments, control may be returned to the calling process.

[0190] It will be understood that each frame in each flowchart illustration and the combination of frames in each flowchart illustration can be implemented by computer program instructions. These program instructions can be provided to a processor to produce a machine so that the instructions executed on the processor create a device for implementing the action specified in each flowchart frame. The computer program instructions can be executed by a processor so that the processor performs a series of operating steps to produce a computer-implemented process so that the instructions executed on the processor provide steps for implementing the action specified in each flowchart frame. The computer program instructions can also enable at least some of the operating steps shown in the frame of each flowchart to be performed in parallel. In addition, some of the steps can also be performed across more than one processor, such as may occur in a multi-processor computer system. In addition, without departing from the scope or spirit of the present invention, one or more frames or a combination of frames in each flowchart illustration can also be performed simultaneously with other frames or a combination of frames, or even performed in an order different from the diagram.

[0191] Thus, each block in each flowchart illustration supports a combination of means for performing a specified action, a combination of steps for performing a specified action, and program instruction means for performing a specified action. It will also be understood that each block in each flowchart illustration and the combination of blocks in each flowchart illustration can be implemented by a special purpose hardware-based system or a combination of special purpose hardware and computer instructions that performs the specified action or steps. The foregoing examples should not be construed as limiting or exhaustive, but rather as illustrative use cases to illustrate implementation of at least one of the various embodiments of the present invention.

[0192] In addition, in one or more embodiments (not shown in the figures), an embedded logic hardware device, such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a programmable array logic (PAL), or the like, or a combination thereof, may be used instead of a CPU to execute the logic in the illustrative flow charts. The embedded logic hardware device may directly execute its embedded logic to perform actions. In one or more embodiments, the microcontroller may be arranged to directly execute its own embedded logic to perform actions, and access its own internal memory and its own external input and output interfaces (e.g., hardware pins or wireless transceivers) to perform actions, such as a system on a chip (SOC).

Claims

1. A method for visualizing management data, comprising: providing one or more visualizations based on data from a data source, wherein the one or more visualizations include one or more tags associated with one or more values ​​from the data source; determining a marker of interest from the one or more markers based on the one or more characteristics of the one or more markers and the one or more visualizations; using one or more evaluation models to generate one or more evaluation results for the one or more evaluation models based on the marker of interest and the data from the data source, wherein each evaluation result is associated with one or more scores based on the fit to the data from the data source and the predicted value of the marker of interest; rank-ordering the one or more evaluation results based on the one or more scores; generating an overall model score for each of the one or more evaluation models based on the model performance score and the model complexity score, wherein the overall model score is modified based on one or more of weights, heuristics, or preferences; updating the rank ranking of the one or more evaluation models and updating the one or more evaluation results of the one or more evaluation models using the modified overall model score; and A report is provided that includes a ranked list of the one or more evaluation results.

2. The method of claim 1 , wherein generating the one or more evaluation results comprises: Based on the evaluation of the token of interest and one or more narrative templates, one or more natural language narratives are generated that describe one or more characteristics of the token of interest.

3. The method of claim 1 , wherein providing the report comprises: One or more other visualizations associated with one or more of the one or more evaluation models, the one or more evaluation results, or the markers of interest are generated.

4. The method according to claim 1, further comprising: monitoring feedback information associated with the report; providing one or more other scores based on the feedback information; and The one or more other scores are used to determine one or more modifications to the one or more evaluation results.

5. The method according to claim 1, further comprising: Based on the one or more scores, the one or more assessment results are filtered, wherein each assessment result associated with a score less than a defined threshold is excluded from the report.

6. The method of claim 1 , wherein determining the marker of interest comprises: A statistical analysis is performed on a data distribution of the one or more values ​​associated with the one or more markers included in the data visualization, wherein based on the statistical analysis, the marker of interest is identified as a statistical outlier compared to other markers of the one or more markers included in the data visualization.

7. The method according to claim 1, further comprising: evaluating data associated with the marker of interest included in the data source and omitted from the visualization; and Based on the evaluation, a portion of the one or more evaluation results is generated.

8. A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions that, when executed by a computer, cause the computer to: providing one or more visualizations based on data from a data source, wherein the one or more visualizations include one or more tags associated with one or more values ​​from the data source; determining a marker of interest from the one or more markers based on the one or more characteristics of the one or more markers and the one or more visualizations; using one or more evaluation models to generate one or more evaluation results for the one or more evaluation models based on the marker of interest and the data from the data source, wherein each evaluation result is associated with one or more scores based on the fit to the data from the data source and the predicted value of the marker of interest; rank-ordering the one or more evaluation results based on the one or more scores; generating an overall model score for each of the one or more evaluation models based on the model performance score and the model complexity score, wherein the overall model score is modified based on one or more of weights, heuristics, or preferences; updating the rank ranking of the one or more evaluation models and updating the one or more evaluation results of the one or more evaluation models using the modified overall model score; and A report is provided that includes a ranked list of the one or more evaluation results.

9. The computer-readable storage medium of claim 8, wherein generating the one or more evaluation results comprises: Based on the evaluation of the token of interest and one or more narrative templates, one or more natural language narratives are generated that describe one or more characteristics of the token of interest.

10. The computer-readable storage medium of claim 8, wherein providing the report comprises: One or more other visualizations associated with one or more of the one or more evaluation models, the one or more evaluation results, or the markers of interest are generated.

11. The computer-readable storage medium of claim 8, further comprising: monitoring feedback information associated with the report; providing one or more other scores based on the feedback information; and The one or more other scores are used to determine one or more modifications to the one or more evaluation results.

12. The computer-readable storage medium of claim 8, further comprising: Based on the one or more scores, the one or more assessment results are filtered, wherein each assessment result associated with a score less than a defined threshold is excluded from the report.

13. The computer-readable storage medium of claim 8, wherein determining the marker of interest further comprises: A statistical analysis is performed on a data distribution of the one or more values ​​associated with the one or more markers included in the data visualization, wherein based on the statistical analysis, the marker of interest is identified as a statistical outlier compared to other markers of the one or more markers included in the data visualization.

14. The computer-readable storage medium of claim 8, further comprising: evaluating data associated with the marker of interest included in the data source and omitted from the visualization; and Based on the evaluation, a portion of the one or more evaluation results is generated.

15. A computer system comprising: one or more processors; Memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for: Based on data from a data source, one or more visualizations are provided, wherein The one or more visualizations include one or more tags associated with one or more values ​​from the data source; determining a marker of interest from the one or more markers based on the one or more characteristics of the one or more markers and the one or more visualizations; using one or more evaluation models to generate one or more evaluation results for the one or more evaluation models based on the marker of interest and the data from the data source, wherein each evaluation result is associated with one or more scores based on the fit to the data from the data source and the predicted value of the marker of interest; rank-ordering the one or more evaluation results based on the one or more scores; generating an overall model score for each of the one or more evaluation models based on the model performance score and the model complexity score, wherein the overall model score is modified based on one or more of weights, heuristics, or preferences; updating the rank order of the one or more evaluation models and updating one or more evaluation results of the one or more evaluation models using the modified overall model score; and A report is provided that includes a ranked list of the one or more evaluation results.

16. The computer system of claim 15, wherein generating the one or more evaluation results comprises: Based on the evaluation of the token of interest and one or more narrative templates, one or more natural language narratives are generated that describe one or more characteristics of the token of interest.

17. The computer system of claim 15, wherein providing the report comprises: One or more other visualizations associated with one or more of the one or more evaluation models, the one or more evaluation results, or the markers of interest are generated.

18. The computer system of claim 15, wherein the one or more programs include instructions for: monitoring feedback information associated with the report; providing one or more other scores based on the feedback information; and The one or more other scores are used to determine one or more modifications to the one or more evaluation results.

19. The computer system of claim 15, wherein the one or more programs include instructions for: Based on the one or more scores, the one or more assessment results are filtered, wherein each assessment result associated with a score less than a defined threshold is excluded from the report.

20. The computer system of claim 15, wherein determining the indicia of interest comprises: A statistical analysis is performed on a data distribution of the one or more values ​​associated with the one or more markers included in the data visualization, wherein based on the statistical analysis, the marker of interest is identified as a statistical outlier compared to other markers of the one or more markers included in the data visualization.

21. The computer system of claim 15, wherein the one or more programs include instructions for: evaluating data associated with the marker of interest included in the data source and omitted from the visualization; and Based on the evaluation, a portion of the one or more evaluation results is generated.

Images