JP6200032B2 - Method and system for dynamically generating a data model for data prediction - Google Patents

Description

  The present subject matter relates generally to, but not limited to, data prediction, and more particularly to a method and system for dynamically generating a data model for event data prediction.

  In general, predictive data for products and / or services is a very important concern for many organizations. By predicting, future demand for products and / or services is expected based on historical data and decision data in various ways. Demand forecasting is a key parameter for various business activities, specifically inventory adjustment and replenishment, and / or effective management of services, and thus contributes significantly to the productivity and profits of the organization To do. However, there is an error in predicting natural / human phenomena, because it cannot thoroughly consider all the factors that affect the phenomenon or event, and the sensor is prone to failure, or the interface is in error Due to that. The conventional prediction method collects error data in the past, generates a probability distribution thereof, corrects the error, and corrects the predicted value based on the error. However, the errors that can be suppressed by these conventional methods are negligible.

  Therefore, there is a need for a method and system for dynamically generating data models for error-predicting prediction and overcoming the disadvantages and limitations of existing prediction systems.

  Through this disclosure, one or more of the weaknesses of the prior art are overcome and additional advantages are provided. Additional features and advantages are recognized through the techniques of this disclosure. Other embodiments and aspects of the disclosure are described in detail herein and are considered a part of the claimed disclosure.

  Accordingly, the present disclosure relates to a method for dynamically generating a data model for data prediction regarding events. The method includes receiving a plurality of past data sets from a historical data (HD) database, wherein the data set includes one or more first and second variables associated with data prediction. As well as determining statistical reference aggregate values for a plurality of past data sets. The method dynamically classifies a plurality of past data sets into a plurality of data sets based on one or more second variables, and a statistical value for each of the classified plurality of data sets. The method further includes the step of determining a specific aggregate value. Simultaneously with the determination, a data model of the plurality of classified data sets is generated based on a comparison between the statistical reference aggregation value and the statistical specific aggregation value.

  Furthermore, the present disclosure relates to a system for dynamically generating a data model for data prediction regarding events. Past data coupled to a processor and configured to store a plurality of past data sets including data corresponding to one or more first and second variables associated with data prediction (HD) database. The system further comprises a processor and a memory communicatively coupled to the processor, the memory storing processor executable instructions that, when executed, send the processor a plurality of past data from the HD database. Have the set received. The processor is further configured to determine a statistical reference aggregate value for the plurality of past data sets. The processor further dynamically classifies the plurality of past data sets into a plurality of data set groups based on the one or more second variables, and determines a statistical value for each of the classified plurality of data set groups. Determine a specific summary value. Simultaneously with the dynamic classification of multiple historical datasets, the processor generates a data model for the group of multiple classified datasets based on the comparison of the statistical reference aggregate value with the statistical specific aggregate value .

  Furthermore, the present disclosure relates to a non-transitory computer readable medium including instructions stored thereon, which instructions are processed by at least one processor from a historical data (HD) database. An act of receiving a plurality of past data sets is performed, the data sets including data corresponding to one or more first and second variables associated with the data prediction. Further, the instructions cause the processor to determine statistical reference aggregate values for a plurality of past data sets.

  Further, the instructions cause the processor to dynamically classify a plurality of past data sets into a plurality of data sets based on one or more second variables, and Each statistical specific summary value is determined. At the same time as the dynamic classification of multiple historical datasets, the instruction tells the processor a data model for the group of multiple classified datasets based on the comparison of the statistical reference aggregate value with the statistical specific aggregate value. Is generated.

  The foregoing summary is merely exemplary and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

  The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles. In the figure, the leftmost digit of a reference number identifies the figure in which that reference number first appears. The same numbers are used throughout the figures to reference like features and components. Several embodiments of systems and / or methods according to embodiments of the present subject matter will now be described, by way of example only, with reference to the accompanying figures.

FIG. 2 is an architectural diagram of an example system for dynamically generating a data model for data prediction on events according to some embodiments of the present disclosure. FIG. 2 is an exemplary block diagram of the data modeling system of FIG. 1 according to some embodiments of the present disclosure. 4 is a flow diagram of an example method for dynamically generating a data model for data prediction regarding events according to some embodiments of the present disclosure. FIG. 6 is a block diagram of an exemplary computer system for implementing an embodiment in accordance with the present disclosure.

  Those skilled in the art should appreciate that any block diagram herein represents a conceptual diagram of an exemplary system that embodies the principles of the present subject matter. Similarly, any flow charts, flow diagrams, state transition diagrams, pseudocode, etc. may be substantially represented in computer-readable media, with such computers or processors being explicitly indicated by computers or processors. It will be appreciated that it represents various processes that can be performed, whether or not.

  In this document, the word “exemplary” is used herein to mean “serving as an example, instance, or illustration”. . Any embodiment or implementation of the present subject matter described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

  While this disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will be described in detail below. However, it is not intended to limit the disclosure to the specific forms disclosed, but rather, the disclosure should cover all modifications, equivalents, and alternatives falling within the scope of the disclosure. Please understand that.

  The term “comprises”, “comprising”, or any other variation thereof is intended to cover non-exclusive inclusions, and thus a setting comprising a list of components or steps, A device or method does not include only those components or steps, but other components or steps not explicitly listed, or other such settings or devices or methods specific to the method. It may also include components or steps. In other words, one or more elements in a system or device processed by “comprises… a” are not further constrained and may be other elements or additional elements of the system or device. Do not exclude existence.

  The present disclosure relates to methods and systems for dynamically generating a data model for event prediction of events. In one embodiment, the method receives a past data set stored in a past data database and determines a statistical reference aggregate value for the past data set. The method further classifies past data sets into a plurality of data set groups, and determines a statistically specific aggregate value of the plurality of data set groups. Further, the method generates a data model of the plurality of classified data sets based on the statistical reference aggregation value and the statistical specific aggregation value. The data model thus generated allows future predicted data values to be determined while suppressing errors. Thus, the proposed data model minimizes errors in predicting data, thereby improving the economic status and operational efficiency of the organization.

  In the following detailed description of embodiments of the present disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, other embodiments may be utilized, and modifications may depart from the scope of the disclosure. It should be understood that it may be done without. Thus, the following description should not be construed in a limiting sense.

  FIG. 1 shows an architectural diagram of an exemplary system for dynamically generating a data model for data prediction on events according to some embodiments of the present disclosure.

  As shown in FIG. 1, exemplary system 100 comprises one or more components configured to dynamically generate a data model for data prediction regarding events. In one embodiment, exemplary system 100 includes a data modeling system 102, a plurality of sensors 104-1, 104-2,..., 104-N (collectively referred to as sensors 104), a communication network. And a past data (HD) database 106 connected via the network 108. Data modeling system 102 dynamically generates a data model based on data captured by sensor 104 and stored in HD database 106. In one embodiment, sensor 104 and HD database 106 can be integrated within data modeling system 102. In another embodiment, sensor 104 and HD database 106 can be implemented separately from data modeling system 102.

  The sensor 104 can be, for example, a data sensor configured to receive data regarding events. The data can include data related to multiple variables related to past events. The data can be stored in the HD database, and is hereinafter referred to as a plurality of past data in this specification. A plurality of past data is processed by the data modeling system 102 to dynamically generate a data model in real time.

  In one embodiment, the data modeling system 102 includes a central processing unit (“CPU” or “processor”) 110, a memory 112, and a statistical summary value analyzer (SSVA) 114. And a data set classifier 116 and a data model generator 118. Data modeling system 102 may be a typical data modeling system illustrated in FIG. The data modeling system 102 includes a processor 110, a memory 112, and an I / O interface 202. I / O interface 202 is coupled to processor 110 and I / O devices. The I / O device is configured to receive input via the I / O interface 202 and send output for display on the I / O device via the I / O interface 202.

  The data modeling system 102 further comprises data 204 and a module 206. In one implementation, data 204 and module 206 may be stored in memory 112. In one example, the data 204 can include a historical data set 208, a statistical reference summary value 210, a statistical specific summary value 212, a significance matrix 214, a plurality of significance intervals 216, and other data 218. . In one embodiment, the data 204 can be stored in the memory 112 in the form of various data structures. In addition, the aforementioned data can be organized using a data model such as a relational data model or a hierarchical data model. Other data 218 may also be referred to as a reference repository for storing recommended implementation techniques as reference data. Other data 218 may also store data including time data and time files generated by module 206 for performing various functions of system 102.

  The module 206 includes, for example, a statistical total value analyzer 114, a data set classifier 116, a data model generator 118, a data update module 222, and a future predictive value determination (FFVD) module. 220. Module 206 may also include other modules 224 that perform various diverse functions of data modeling system 102. It will be appreciated that such a module described above may be represented as a single module or a combination of various modules. Module 206 can be implemented in the form of software, hardware, and / or firmware.

  The data modeling system 102 receives a plurality of past data sets 208 from the HD database 106. The plurality of historical data sets 208 includes one or more data corresponding to one or more response variables or dependent variables (hereinafter referred to as first variables) and one or more Data associated with a suspicious predictor variable or independent variable (hereinafter referred to as the second variable herein). SSVA 114 determines a statistical reference aggregate value 210 for a plurality of past data sets 208 using known techniques. In one example, SSVA 114 determines a reference average value for a plurality of past data sets based on data relating to one or more first variables. Simultaneously with the determination of the statistical reference summary value 210, a plurality of data sets are generated using a classification technique.

  In one embodiment, the data set classifier 116 dynamically classifies a plurality of past data sets 208 based on data relating to one or more second variables. The data set classifier 116 selects one or more second variables and determines boundary values for the one or more selected second variables. Based on the boundary value, the data set classifier 116 repeats determining a plurality of discrete interval values and a step size corresponding to the plurality of discrete interval values. In another embodiment, the user can manually provide boundary values, multiple discrete interval values, and corresponding step sizes. Simultaneously with the determination, the data set classifier 116 generates a plurality of data sets of one or more second variables based on the plurality of discrete interval values and step sizes. For each of the plurality of categorized data sets, SSVA 114 determines a statistical specific summary value 212 using known techniques. In one example, SSVA 114 determines a specific average value for each of a plurality of grouped data sets based on data relating to one or more second variables. Concurrently with the determination of the statistical specific summary value 212, a data model is generated based on the statistical reference summary value 210 and the statistical specific summary value 212.

  In one embodiment, the data model generator 118 compares the statistical reference summary value 210 and the statistical specific summary value 212 and determines a statistical significance factor (k) based on the comparison. The significance coefficient (k) indicates whether there is a substantial difference between the statistical reference aggregate value 210 and the statistical specific aggregate value 212. The value of k can be between 0 and 1, for example. If the data model generator 118 determines that a substantial difference exists, the significance factor (k) is set equal to 1 and the statistical specific summary value 212 is the predicted statistical summary value. As determined. On the other hand, if the data model generator 118 determines that there is no substantial difference, the significance factor (k) is set equal to 0 and the statistical reference summary value 210 is the predicted statistical Determined as an aggregate value. Based on the predicted statistical aggregate value thus determined, the data model generator 118 generates a significance matrix of one or more second variables.

  In one embodiment, the data model generator 118 generates a significance matrix based on the determined significance coefficient (k). The significance matrix may be a matrix of significance coefficients (k) that are mapped against a plurality of discrete intervals (also referred to as significance intervals) of one or more second variables. Based on the significance matrix, the data model generator 118 determines the data model by mapping the corresponding predicted statistical aggregate value of the one or more second variables. Simultaneously with the generation of the data model, future predicted data values are determined.

  In one embodiment, FFVD module 220 determines future predicted data values based on previously determined predicted data values stored in HD database 106 and the data model thus generated. To do. The data update module 222 dynamically updates future predicted data values, generated data models, and actual values corresponding to the predictions in the HD database 106 for further data prediction.

  Accordingly, the present disclosure dynamically generates a data model for data prediction for events that suppresses errors that occur during prediction by considering all coefficients or variables and improves the efficiency of data prediction.

  FIG. 3 illustrates a flowchart of an exemplary method for dynamically generating a data model for data prediction regarding events according to some embodiments of the present disclosure.

  As illustrated in FIG. 3, the method 300 includes one or more blocks implemented by the processor 110 for dynamically generating a data model for data prediction regarding events. Method 300 may be described in the general context of computer-executable instructions. In general, computer-executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions that perform particular functions or implement particular abstract data types.

  The order in which method 300 is described is not intended to be construed as limiting, and any number of the described method blocks can be combined in any order that implements method 300. In addition, individual blocks may be deleted from method 300 without departing from the spirit and scope of the subject matter described herein. Moreover, method 300 can be implemented in any suitable hardware, software, firmware, or combination thereof.

  At block 302, a past data set is received. In one embodiment, the data modeling system 102 receives multiple historical data sets 208 from the HD database 106. The plurality of past data sets 208 includes one or more data corresponding to the one or more first variables and data associated with the one or more second variables.

  Consider an example scenario where the data modeling system 102 receives a historical data set of error data relating to, for example, prediction of power consumption data acquired at a particular location at a particular time. The data modeling system 102 is predicting power consumption data to monitor power consumption at various locations and at various time periods to reduce unused energy, thereby improving the efficiency of grid operation. It aims at error modeling to suppress the errors thus obtained. The actual data regarding energy consumption captured during the previous time at various locations is stored in the HD database 106. Furthermore, the corresponding predicted data and the error data acquired by the difference between the predicted data and the actual data are stored in the HD database 106. Accordingly, the plurality of past data sets include error data as data of one or more first variables (y) and time as data of one or more second variables (a, b). And spatial / geographic data. In one example, the HD database 106 may include data from a power company, ie, 24-hour error data from April 1, 2014 to April 3, 2014, and the data modeling system 102 However, consider that the load at location 1 at 2 am on April 8, 2014 can be predicted.

  At block 304, a statistical reference summary value is determined. In one embodiment, SSVA 114 determines a statistical reference aggregate value 210 for multiple historical data sets 208. In one example, SSVA 114 determines a reference average value (μr) for a plurality of past data sets based on data relating to one or more first variables. In one aspect, the probability distribution of error data is determined graphically over time. As illustrated, a reference average value μr of past error data, ie, μr = 389 MW, is determined.

  At block 306, past data sets are classified into data sets. In one embodiment, the data set classifier 116 dynamically classifies a plurality of past data sets 208 based on data relating to one or more second variables. The data set classifier 116 selects one or more second variables and determines boundary values for the one or more selected second variables. Based on the boundary value, the data set classifier 116 repeats determining a plurality of discrete interval values and a step size corresponding to the plurality of discrete interval values. As illustrated, the data set classifier 116 generates error data at a plurality of data sets, ie, location 1 at 2 am for 3 days.

  At block 308, a statistically specific aggregate value for each data set group is determined. For each of the plurality of categorized data sets, SSVA 114 determines a statistical specific summary value 212 using known techniques. In one example, the SSVA 114 determines a specific average value (μ1) for each of a plurality of grouped data sets based on data relating to one or more second variables. As illustrated, SSVA 114 determines a specific average value μ1, ie μ1 = 292 MW, based on error data at location 1 at 2 am for 3 days.

  At block 310, a data model is generated. In one embodiment, the data model generator 118 compares the statistical reference summary value 210 and the statistical specific summary value 212 and determines a statistical significance factor (k) based on the comparison. The significance coefficient (k) indicates whether there is a substantial difference between the statistical reference aggregate value 210 and the statistical specific aggregate value 212. The value of k can be between 0 and 1, for example. If the data model generator 118 determines that a substantial difference exists, the significance factor (k) is set equal to 1 and the statistical specific summary value 212 is the predicted statistical summary value. As determined. On the other hand, if the data model generator 118 determines that there is no substantial difference, the significance factor (k) is set equal to 0 and the statistical reference summary value 210 is the predicted statistical Determined as an aggregate value. As illustrated, the data model generator 118 determines a significant difference between μr and μ1, so the value of the significance coefficient k is set to 1. Based on the predicted statistical aggregate value thus determined, the data model generator 118 generates a significance matrix of one or more second variables.

  In one embodiment, the data model generator 118 generates a significance matrix based on the determined significance coefficient (k). The significance matrix may be a matrix of significance coefficients (k) that are mapped against a plurality of discrete intervals (also referred to as significance intervals) of one or more second variables. For example, the second variable “a” may be a temporal variable, eg, time of day, so to say 1 or 2 am, and “b” is a spatial variable, eg, geographic. Can be location 1 and geographic location 2.

  It can be noted that the temporal variable at 2 am at location 1 is highly significant in the data model thus generated.

Based on the significance matrix, the data model generator 118 maps the data model by mapping corresponding predicted statistical aggregate values of one or more second variables exemplified below in equation (1). To decide.
y1 = μr * (1−k) + μ1 * k (1)

  Simultaneously with the generation of the data model, future predicted data values are determined. In one embodiment, the FFVD module 220 may determine future predicted data values based on previously determined predicted data values stored in the HD database 106 and the error data model thus generated. To decide.

  An illustration of a comparison of the results of the conventional data model with the results of the proposed data model is given below.

  The data update module 222 then dynamically updates future predicted data values and generated data models in the HD database 106 for further data prediction.

  FIG. 4 is a block diagram of an exemplary computer system for implementing embodiments in accordance with the present disclosure.

  Variations of computer system 401 may be used to implement any computing system that can be utilized to implement the features of the present disclosure. The computer system 401 can include a central processing unit (“CPU”, “processor”) 402. The processor 402 may comprise at least one data processor for executing program components for executing user-generated or system-generated requests. The processor may include a dedicated processing device such as an integrated system (bus) controller, a memory management controller, a floating point arithmetic unit, a graphics processing unit, a digital signal processing unit. Processor 402 may include a microprocessor, such as an AMD Athlon, Duron or Opteron, ARM application, embedded or secure processor, IBM PowerPC, Intel Core, Itanium, Xeon, Celeron, or other family of processors. it can. The processor 402 can be implemented using a mainframe, distributed processor, multi-core, parallel, grid, or other architecture. Some examples include application-specific integrated circuits (ASICs), digital signal processors (DSPs), field programmable gate arrays (FPGAs, etc.). Such embedded technology can be used.

  The processor 402 can be placed in communication with one or more input / output (I / O) devices via an I / O interface 403. The I / O interface 403 includes, but is not limited to, audio, analog, digital, monaural, RCA, stereo, IEEE-1394, serial bus, universal serial bus (USB: universal serial bus), infrared, PS / 2 , BNC, coaxial, component, composite, digital visual interface (DVI), high definition multimedia interface (HDMI (registered trademark): high-definition multimedia interface), RF antenna, S- Video, VGA, IEEE802. n / b / g / n / x, Bluetooth (registered trademark), cellular (for example, code-division multiple access (DCMA), high-speed packet access (HSPA +), global system) Communication protocols / methods such as Four Mobile Communications (GSM (registered trademark): global system for communications), Long Term Evolution (LTE), WiMax, etc. can be adopted.

  Using the I / O interface 403, the computer system 401 can communicate with one or more I / O devices. For example, the input device 404 includes an antenna, keyboard, mouse, joystick, (infrared) remote control unit, camera, card reader, fax machine, dongle, biometric reader, microphone, touch screen, touch pad, trackball, sensor (Eg, accelerometer, light sensor, GPS, gyroscope, or proximity sensor), stylus, scanner, storage device, transceiver, video device / source, visor, etc. The output device 405 includes a printer, a fax machine, a video display (for example, a cathode ray tube (CRT), a liquid crystal display (LCD), a light-emitting diode (LED), or a plasma. ), Audio speakers and the like. In some embodiments, the transceiver 406 can be placed in connection with the processor 402. The transceiver can facilitate various types of wireless transmission or reception. For example, the transmitter / receiver provides IEEE802.11a / b / g / n, Bluetooth (registered trademark), FM, global positioning system (GPS), 2G / 3G HSDPA / HSUPA communication, etc. May include an antenna operably connected to the instrument chip (e.g., Texas Instruments WiLink WL1283, Broadcom BCM4750IUB8, or Infineon Technologies X-Gold 618-PMB9800).

  In some embodiments, the processor 402 can be placed in communication with the communication network 408 via the network interface 407. The network interface 407 can communicate with the communication network 408. The network interface 407 includes a direct connection, Ethernet (registered trademark) (for example, twisted pair 10/40 / 400Base-T), transmission control protocol / Internet protocol (TCP / IP), token A connection protocol including, but not limited to, ring, IEEE 802.11a / b / g / n / x, etc. may be employed. The communication network 408 may include, but is not limited to, using direct interconnection, a local area network (LAN), a wide area network (WAN), a wireless network (eg, Wireless Application Protocol). ), Internet, and the like. Using network interface 407 and communication network 408, computer system 401 can communicate with devices 409, 410, and 411. These devices include various mobile devices such as personal computers, servers, fax machines, printers, scanners, cellular phones, smartphones (eg Apple iPhone (registered trademark), Blackberry, Android phones, etc.), tablets, and the like. A computer, an eBook reader (such as Amazon Kindle, Nook), a laptop computer, a notebook, or a gaming console (Microsoft Xbox, Nintendo DS, Sony PlayStation, etc.) may be included without limitation. In some embodiments, the computer system 401 may itself implement one or more of these devices.

  In some embodiments, processor 402 may be placed in communication with one or more memory devices (eg, RAM 413, ROM 414, etc.) via storage interface 412. The storage interface includes serial advanced technology attachment (SATA), integrated drive electronics (IDE), IEEE-1394, universal serial bus (USB), fiber channel, small size It can be connected to memory devices including, but not limited to, memory drives, removable disk drives, etc. that employ connection protocols such as a computer system interface (SCSI: small computer systems interface). Memory drives include drums, magnetic disk drives, magneto-optical drives, optical drives, redundant array of independent disks (RAID), solid-state memory devices, solid-state drives, etc. Further can be included.

  Memory 415 includes operating system 416, user interface application 417, web browser 418, mail server 419, mail client 420, user / application data 421 (eg, any data variable discussed in this disclosure). Or a set of database components including but not limited to data records). The operating system 416 can facilitate resource management and operation of the computer system 401. Examples of operating systems include system distributions such as Apple Macintosh OS X, UNIX (registered trademark), Unix (registered trademark) (for example, Berkeley Software Distribution (BSD), FreeBSD, NetBSD, OpenBSD registered, LBSD, etc.) Trademark) distribution (for example, Red Hat, Ubuntu, Kubuntu, etc.), IBM OS / 2, Microsoft Windows (registered trademark) (XP, Vista / 7/8, etc.), Apple iOS, Google Android, etc. are limited to BlackberryOS. It is mentioned without. User interface 417 may facilitate display, execution, interaction, manipulation, or operation of program components through text or graphic functions. For example, the user interface provides computer interaction interface elements in a display system operatively connected to the computer system 401, such as a cursor, icon, check box, menu, scroller, window, widget, etc. Can do. A graphical user interface (GUI) is available for the Apple Macintosh operating system Aqua, IBM OS / 2, Microsoft Windows (registered trademark) (for example, Aero, Metro, etc.), Unix (registered trademark) ow X-W (Registered trademark), or a web interface library (for example, ActiveX, Java (registered trademark), Java (registered trademark) Script, AJAX, HTML, Adobe Flash, etc.) may be employed without limitation.

  In some embodiments, the deployment computer system 401 can implement a web browser 418 that stores program components. The web browser can be a hypertext viewing application such as Microsoft Internet Explorer, Google Chrome, Mozilla Firefox, Apple Safari, etc.

  Secure web browsing can be provided using HTTPS (Secure Hypertext Transport Protocol), Secure Sockets Layer (SSL), Transport Layer Security (TLS), and the like. The web browser can use functions such as AJAX, DHTML, Adobe Flash, Java (registered trademark) Script, Java (registered trademark), and an application programming interface (API). In some embodiments, the computer system 401 may implement a mail server 419 that stores program components. The mail server can be an Internet mail server such as Microsoft Exchange. The mail server is ASP, ActiveX, ANSI C ++ / C #, Microsoft. Functions such as NET, CGI script, Java (registered trademark), Java (registered trademark) Script, PERL, PHP, Python, and WebObjects can be used. The mail server includes an Internet message access protocol (IMAP), a messaging application programming interface (MAPI), a Microsoft Exchange, and a post office p protocol (PO). communication protocol such as simple mail transfer protocol (SMTP) or simple mail transfer protocol (SMTP). In some embodiments, the computer system 401 may implement a mail client 420 that stores program components. The mail client can be a mail viewing application such as Apple Mail, Microsoft Entourage, Microsoft Outlook, Mozilla Thunderbird.

  In some embodiments, the computer system 401 may store user / application data 421, such as data, variables, records, etc., as described in this disclosure. Such a database can be implemented as a fault-tolerant, relational, scalable, secure database such as Oracle or Sybase. Alternatively, such a database may use standardized data structures such as arrays, hashes, linked lists, structures, structured text files (eg, XML), tables, or as an object-oriented database. (E.g., using ObjectStore, Poet, Zope, etc.). Such databases may sometimes be integrated or sometimes distributed among the various computer systems described above in this disclosure. It should be understood that the structure and operation of any computer or database component may be combined, integrated or distributed in any operational combination.

  As described above, module 206 includes routines, programs, objects, components, and data structures that perform particular tasks or implement particular abstract data types, among others. Module 206 may also be implemented as a signal processor, state machine, logic circuit, and / or some other device or component that manipulates signals based on operational instructions. Further, module 206 can be implemented by one or more hardware components, by computer readable instructions executed by a processing device, or a combination thereof.

  The illustrated steps are presented to illustrate the illustrated exemplary embodiment, and expect that ongoing technical development will change the way in which specific functions are performed. Should. These examples are presented herein for purposes of illustration and not limitation. Furthermore, the boundaries of functional building blocks are arbitrarily defined herein for convenience of explanation. Alternative boundaries can be defined as long as a particular function and its relationships are performed appropriately. Alternatives (including equivalents, extensions, variations, deviations, etc. of those described herein) will be apparent to those skilled in the art based on the teachings contained herein. . Such alternatives fall within the scope and spirit of the disclosed embodiments. Also, the words “comprising”, “having”, “containing” and “including”, as well as other similar forms, An item or items following any one of them means an exhaustive listing of such items or items, ie limiting to only the listed item or items Are equivalent in the sense that they are not, and are intended to be open-ended. Also, as used herein and in the appended claims, the singular forms “a”, “an”, and “the” have the plural references unless the context clearly dictates otherwise. It must also be noted that symbols are included.

  Further, one or more computer readable storage media may be utilized in implementing embodiments in accordance with the present disclosure. Computer-readable storage media refers to any type of physical memory that can store information or data readable by a processor. Accordingly, a computer readable storage medium may store instructions for execution by one or more processors, including instructions for causing a processor to perform steps or stages according to embodiments described herein. it can. The term “computer-readable medium” should be understood to include tangible items and not to include carrier waves and transient signals, ie, non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, non-volatile memory, hard drive, CD ROM, DVD, flash memory, Discs, and any other known physical storage media.

  It is intended that the present disclosure and examples be considered as exemplary only, with the true scope and spirit of the disclosed embodiments being indicated by the appended claims.

DESCRIPTION OF SYMBOLS 100 System 102 Data modeling system 104, 104-1, 104-2, ..., 104-N sensor 106 HD database 108 Communication network 110 Central processing unit, CPU, processor 112 Memory 114 Statistical total value analyzer (SSVA)
116 Data Set Classifier 118 Data Model Generator 202 I / O Interface 204 Data 206 Module 208 Historical Data Set 210 Statistical Reference Aggregation Value 212 Statistical Specific Aggregation Value 214 Significant Matrix 216 Significant Interval 218 Other Data 220 Future Data Predictive Value Determination (FFVD) Module 222 Data Update Module 224 Other Module 401 Computer System 402 Central Processing Unit, CPU, Processor 403 I / O Interface 404 Input Device 405 Output Device 406 Transceiver 407 Network Interface 408 Communication Network 409 Device 410 device 411 device 412 storage interface 413 RAM
414 ROM
415 Memory 416 Operating System 417 User Interface 418 Web Browser 419 Mail Server 420 Mail Client 421 User / Application Data

Claims (12)

A method for dynamically generating a data model for predicting data about an event, comprising:
Receiving a plurality of past data sets from a historical data (HD) database by a processor of the data modeling system, wherein the plurality of past data sets are associated with data prediction; Or comprising data corresponding to a plurality of first and second variables,
Determining a statistical reference aggregate value of the plurality of past data sets;
Selecting the one or more second variables of the plurality of past data sets and determining a boundary value of the one or more second variables based on the selection;
Repetitively determining a plurality of discrete interval values of the one or more second variables and a step size corresponding to the plurality of discrete interval values based on the boundary value;
Generating the plurality of data sets of the one or more second variables based on the plurality of discrete interval values and a step size;
Determining respective statistical particular aggregate values of a plurality of data set groups the generated, and based on the comparison of the statistical particular aggregate value and the statistical reference aggregate value, the plurality of data the generated steps including how to generate a data model of the set group. Generating the data model comprises:
Comparing the statistical reference aggregate value of the plurality of past data sets with the statistical specific aggregate value of the generated plurality of data sets;
Determining whether a difference between the statistical reference summary value and the statistical specific summary value is substantial;
Estimating one of the statistical reference aggregate value and the statistical specific aggregate value as a predicted statistical aggregate value based on the determination;
Determining a significance matrix of the one or more second variables based on the predicted statistical aggregate value thus estimated, and based on the significance matrix determined in this way, the data model The method of claim 1, comprising generating.   The method of claim 1, further comprising determining a future predicted data value based on the generated data model stored in the HD database and a previously determined predicted data value. .   The method of claim 1, further comprising dynamically updating future predicted data values in the HD database, the generated data model, for further data prediction. A system for dynamically generating a data model for data prediction about events,
Processor,
Past data (HD) that is coupled to the processor and configured to store a plurality of past data sets including data corresponding to one or more first and second variables related to data prediction. data) a database, as well as a memory arranged in communication with the processor and storing processor executable instructions, wherein the instructions are:
Receiving a plurality of past data sets from the HD database;
Determining a statistical reference aggregate value of the plurality of historical data sets;
Selecting the one or more second variables of the plurality of past data sets and determining a boundary value of the one or more second variables based on the selection;
Repetitively determining a plurality of discrete interval values of the one or more second variables and a step size corresponding to the plurality of discrete interval values based on the boundary value;
Generating the plurality of data sets of the one or more second variables based on the plurality of discrete interval values and step sizes;
Determining each statistically specific aggregate value of the plurality of data sets generated;
A system comprising a memory, including instructions for generating a data model of the plurality of generated data sets based on a comparison between the statistical reference aggregate value and the statistical specific aggregate value. The processor is
Comparing the statistical reference aggregate value of the plurality of past data sets with the statistical specific aggregate value of the generated plurality of data sets;
Determining whether a difference between the statistical reference summary value and the statistical specific summary value is substantial;
Estimating one of the statistical reference aggregate value and the statistical specific aggregate value as a predicted statistical aggregate value based on the determination;
Determining a significance matrix of the one or more second variables based on the predicted statistical aggregate value thus estimated, and based on the significance matrix determined in this way, the data model The system of claim 5 , wherein the system is configured to generate the data model by generating. The processor is further configured to determine a future predicted data value based on the generated data model and a previously determined predicted data value stored in the HD database. Item 6. The system according to Item 5 . 6. The system of claim 5 , wherein the processor is further configured to dynamically update future predicted data values in the HD database, the generated data model, for further data prediction. Instruction is a non-transitory computer readable medium having stored, which instructions, at least one processor,
An act of receiving a plurality of past data sets from a historical data (HD) database, wherein the data sets correspond to one or more first and second variables associated with data prediction. Actions, including data,
Determining a statistical reference aggregate value of the plurality of past data sets;
Selecting the one or more second variables of the plurality of past data sets and determining a boundary value of the one or more second variables based on the selection;
An act of repeatedly determining a plurality of discrete interval values of the one or more second variables and a step size corresponding to the plurality of discrete interval values based on the boundary value;
Generating the plurality of data sets of the one or more second variables based on the plurality of discrete interval values and step sizes;
Act of determining respective statistical particular aggregate values of a plurality of data set groups the generated, and based on the comparison of the statistical particular aggregate value and the statistical reference aggregate value, the plurality of data the generated The act of generating a data model for the set ,
To do ,
Non-transitory computer readable medium. The instructions to the at least one processor to the al,
Comparing the statistical reference aggregate value of the plurality of past data sets with the statistical specific aggregate value of the generated plurality of data sets;
Determining whether a difference between the statistical reference summary value and the statistical specific summary value is substantial;
Estimating one of the statistical reference aggregate value and the statistical specific aggregate value as a predicted statistical aggregate value based on the determination;
Determining a significance matrix of the one or more second variables based on the predicted statistical aggregate value thus estimated, and based on the significance matrix determined in this way, the data model The medium of claim 9 , wherein the generating step causes the data model to be generated. The instructions are in the at least one processor al, based on the prediction Data value determined on the HD database on the generated Data models stored and past, determining the future prediction Data value The medium according to claim 9 . The instructions to the at least one processor to the al, for further data predicting the HD future predicted Data values in the database, to dynamically update the already generated data model, according to claim 9 Medium.