Abstract: An image file representing at least a portion of a printed document is processed to highlight the differences between foreground material (e.g., text or other characters) from background. The method includes selecting a neighborhood of pixels, determining a weighted average of an attribute values (e.g., luminance) for each pixel, and modifying each pixel's value based on the weighted average. Graylevel scaling, error diffusion, and a bit level conversion are also performed each pixel ends up with either a first attribute value level (e.g., luminance of 0) or a second attribute value level (e.g., luminance of 255).

Abstract: A method and a device for predicting a future occurrence of a transportation system incident are disclosed. The method includes receiving transportation incident data comprising information collected during and related to operation of at least one transportation vehicle, the information comprising at least a time stamp, constructing at least one count regression model based upon the transportation incident data, producing a results set based upon the at least one count regression model, predicting at least one future occurrence of an incident based upon the results set, and presenting the at least one predicted future occurrence. The device includes at least a processing device and computer readable medium containing a set of instructions configured to cause the device to perform the method.

Abstract: A method and a device for identifying factors that contribute to schedule deviation in a transportation system are disclosed. The method includes collecting operating information for a vehicle along a transportation route and determining schedule deviation information for the transportation route based upon the operating information. A plurality of models is constructed, each of the plurality of models including at least one combination of factors that contribute to schedule deviation, and the models are ranked. As results sets is produced that includes at least the highest ranked model showing at least one combination of factors that most contributes to schedule deviation, The results set is presented and an operator associated with the transportation system may institute one or more changes to the system. The device includes at least a processing device and computer readable medium containing a set of instructions configured to cause the device to perform the method.

Abstract: Frequency based keyword extraction method and system utilizing a statistical measure is disclosed which generates keywords within a page and/or document that can distinguish the document from an average document. A simple frequency threshold parameter can be utilized to determine a number of common stop words if a word in the document possesses a frequency in a corpus that is more than the threshold parameter. A statistical confidence interval of the frequency in the document can be compared against a frequency confidence interval of the word in the corpus. The extracted keyword possesses a greater intra-document frequency confidence interval than the frequency confidence interval of the word within the corpus. A statistical hypothesis test can also be utilized to determine the keyword by calculating a test statistic and testing whether the test statistic is greater than some threshold.

Abstract: Embodiments herein include a method, service, apparatus, etc., that receives initial user input comprising natural language commands that identify the initial color selection. The method displays the initial color samples or patches corresponding to the initial color selection in a two-dimensional grid and receives additional user input comprising additional natural language commands and a refined axis selection. The embodiments herein revise the initial color selection to a revised color selection based on a color change magnitude, a color change direction, and a color change property. Then, this method matches the revised color selection to the computer program colors to produce refined matching colors. These refined matching colors are displayed as refined color samples or patches in the two-dimensional grid. The axes of the two-dimensional grid can correspond to the refined axis selection and the assigned names can also be displayed on the graphic user interface.

Abstract: An inventory management system for forecasting demand in a print production environment may include a computing device and a computer-readable storage medium in communication with the computing device. The computer-readable storage medium may include programming instructions for updating a predictive model with intervention information comprising an anticipated demand value and a confidence value associated with the anticipated demand value. The predictive model may be associated with a demand distribution of a print-related service.

Abstract: Method and systems of identifying a printing device having an exceptional incident rate among a plurality of printing devices are disclosed. For each of a plurality of printing devices, a processor receiving a printing device model, a print volume, and an incident count that includes a number of incidents occurring within a particular time frame. The processor determines a generalized linear regression model of the incident counts for each printing device model and also determines a predicted incident count for each printing device model using the generalized regression model. The processor determines a residual value for each printing device between the incident count for the printing device and the predicted incident count for the printing device model associated with the printing device. The processor identifies one or more printing devices having a residual value exceeding a threshold value.

Abstract: Methods and systems automatically analyze different types of historical automobile parking violations within a predetermined geographic region to produce parking violation trends. Such methods and systems automatically predict the numbers of parking violations that potentially could be issued during a plurality of predetermined work periods based on the parking violation trends. The methods and systems automatically compare the actual number of parking violations issued during the predetermined work periods to the number of parking violations that potentially could be issued during the predetermined work periods to produce a parking violation issuance variance. The methods and systems also automatically identify ones of the predetermined work periods in which parking violation citations could be increased to produce an opportunity report, and output the opportunity report.

Abstract: Methods and systems of determining a failure copula for a consumable are disclosed. Multiple consumable levels for a consumable and multiple timestamps are received from a device. Each timestamp is associated with one of the consumable levels. The consumable levels are ordered into a time-ordered sequence based on the associated timestamps. For at least one consumable level in the time-ordered sequence, a computing device determines a value associated with the consumable level based on at least one earlier and at least one later consumable level in the time-ordered sequence. The computing device identifies historical consumable replacement(s) based on the values associated with the consumable levels in the time-ordered sequence and determines one or more consumable lifetimes and one or more consumable yields based on the historical consumable replacement(s). The computing device determines a failure copula based on the one or more consumable lifetimes and consumable yields.

Abstract: Providing means for people to input their observations can reduce the need for sensor deployments because humans have excellent sensing abilities. One thing people tend to observe carefully is parking availability. Parking meters and pay stations can request people to enter their observations of parking availability and other environmental factors. The observations, being numerical in nature, can be processed to determine reasonable parking fees, likelihood of violators in an area, and the statistical, observed, or estimated dispersion of available parking with a geographic region.

Abstract: Methods and systems for identifying device models or accounts exhibiting outlying behavior are disclosed. For a method of identifying a device model exhibiting outlying behavior, a processor may receive a color impression count, a monochrome impression count and either a device model for each of a plurality of devices. A proportion of color revenue may be determined for each device based on the color impression count and the monochrome impression count. The processor may determine, for each device model, a distribution of the proportion of color revenue for the one or more devices having the device model and may automatically identify one or more distributions of the proportion of color revenue exhibiting outlying behavior. Each distribution is associated with a device model.

Abstract: Methods and systems for determining print revenue behavior for an account are disclosed. A computing device may determine a print revenue for an account for each of a plurality of time periods. The computing device may select a best fit model from a plurality of models based on the print revenue for the account for the plurality of time periods. The computing device may determine a risk level associated with the account based on a best fit model. The risk level may be based on a difference between the best fit model and the print revenue for the account for each of time period.

Abstract: Methods and systems for determining print capacity are disclosed. A maximum job speed for a document processing device and information pertaining to a plurality of jobs performed by the document processing device may be received. The information may include a job speed and a job size for each job. Sets of first and second jobs may be identified from the plurality of jobs. Each first job may have a job speed greater than a percentage of the maximum job speed. Each second job may have a job speed less than the percentage of the maximum job speed. A job size threshold may be determined based on the job sizes for the first and second jobs. In response to such determination, a linear function based on the one or more second jobs may be obtained. The linear function may be a function of job speed based on job size.

Abstract: A method for analyzing documents is disclosed. The method compares concepts consisting of groups of terms for similarity within a corpus of document, clusters documents that contain certain concept term sets together. It may also rank the documents within each cluster according to the frequency of term co-occurrence within the concepts.

Abstract: A system for detecting suspect meter reads in a print environment may include a computing device and a computer-readable storage medium in communication with the computing device. The computer-readable storage medium may include one or more programming instructions for receiving historical meter read values associated with a print-related service, selecting a model set including one or more of the historical meter read values, using a predictive model to determine an anticipated meter read value and a corresponding forecast error value from the model set, determining an updated forecast error value, determining a threshold value, identifying an actual meter read value, determining an average rate associated with the actual meter read value, and flagging the actual meter read value as suspect based on a comparison of the average rate and the threshold value.

Abstract: Method and systems of identifying a printing device having an exceptional incident rate among a plurality of printing devices are disclosed. For each of a plurality of printing devices, a processor receiving a printing device model, a print volume, and an incident count that includes a number of incidents occurring within a particular time frame. The processor determines a generalized linear regression model of the incident counts for each printing device model and also determines a predicted incident count for each printing device model using the generalized regression model. The processor determines a residual value for each printing device between the incident count for the printing device and the predicted incident count for the printing device model associated with the printing device. The processor identifies one or more printing devices having a residual value exceeding a threshold value.

Abstract: Methods and systems for identifying devices having a specified utilization are disclosed. A selected minimum utilization and maximum utilization defining a utilization band may be received. Device information for each of a plurality of accounts, including a device model and utilization information for each device associated with an account, may also be received. A utilization may be determined for each device based on the utilization information. For each device model in an account, a number of devices in an account having the device model and a utilization in the utilization band may be determined. A plurality of clusters may be identified for device model-account pairs, and at least one device model-account pair may be assigned to a cluster.

Abstract: A systems and methods for providing an image forming machine capable of monitoring the image quality of images that the image forming machine produces and detecting changes in the image quality. The monitoring system using statistical techniques to fit predetermined models to a measured image quality of time sequence of formed images. The predetermined models used to find current and predicted values of image quality and notifying a user or service provider when the image quality has changed.

Abstract: An image file representing at least a portion of a printed document is processed to highlight the differences between foreground material (e.g., text or other characters) from background. The method includes selecting a neighborhood of pixels, determining a weighted average of an attribute values (e.g., luminance) for each pixel, and modifying each pixel's value based on the weighted average. Graylevel scaling, error diffusion, and a bit level conversion are also performed each pixel ends up with either a first attribute value level (e.g., luminance of 0) or a second attribute value level (e.g., luminance of 255).

Abstract: Methods and systems of filtering non-actionable alerts are disclosed. A processing device receives an alert from a printing device and determines a page count for the printing device. The processing device compares the page count with at least one threshold value associated with the alert and the printing device. In response to the page count satisfying the at least one threshold value, the processing device identifies the alert as a valid alert.