METHOD AND SYSTEM FOR IMPORTING HARD COPY ASSESSMENTS INTO AN AUTOMATIC EDUCATIONAL SYSTEM ASSESSMENT

Abstract

This disclosure provides a method and system to create an educational assessment using an image processing system. According to an exemplary method, a preexisting printed assessment is scanned to produce an image file and the image processing system generates and executes a search query based on a user selected preexisting question. The executed search queries a Data Warehouse/Repository (DW/R) based on the search query to retrieve one or more predefined questions and associated metadata. The retrieved question and metadata are used to create the educational assessment.

Description

CROSS REFERENCE TO RELATED PATENTS AND APPLICATIONS

U.S. patent application Ser. No. 14/609,820, filed Jan. 30, 2015, by Clar et al., entitled “METHOD AND SYSTEM TO ATTRIBUTE METADATA TO PREEXISTING DOCUMENTS” is incorporated herein by reference in its entirety.

BACKGROUND

This disclosure relates to document processing methods and systems. According to an exemplary embodiment of this disclosure, a document processing method and system is provided to create an educational assessment using an image processing system, such as a multifunction printer (MFP), the created educational assessment including a plurality of questions administered to one or more students for completion.

Moreover, the present disclosure relates to the process of assessing the attributes of a student or group of students at selected times during their learning process and particularly relates to the assessment and evaluation of student attributes or progress in a structured classroom where a teacher is required to educate the students to a level of proficiency in various subject matters and at particular grade levels. Typically, in a grade level classroom, the teacher periodically gives the students printed form assessments or tests, as they have previously been referred to, in order to obtain an indication of the student(s) level(s) of proficiency in the subject matter of immediate interest. U.S. Patent Publication No. 2010/0075290, published Mar. 25, 2010, by DeYoung et al., and entitled “AUTOMATIC EDUCATIONAL ASSESSMENT SERVICE” describes a system for automatically evaluating assessments of the type given by a teacher/educator for determining the state of learning or progress of students during the course of instructions; and, the system is applicable particularly in a classroom setting where the teacher is responsible for educating a relatively large group of students. The system and technique of the present disclosure enables the teacher/educator to select from the digital user interface (DUI) of a Multifunction Device (MFD) any of multiple predetermined stored assessment forms in a Data Warehouse/Repository of such assessment forms for administration to a teacher/educator selected group of one or more students.

The teacher then requests the system to create an Assessment Batch and to print out personalized versions of the assessment form, where each version is automatically bar coded for the individual student. The student's name is also printed on the form for the purpose of delivering each assessment to the appropriate student. If desired, the student's name may be printed on the reverse side of the form such as, for example in large print, such that the person administering the test can verify from a distance that each student has the correct form, and so that forms can be handed out individually without disclosing the content of the assessment.

Once the students have completed the assessment, or alternatively where the teacher/educator marks the assessment for students' oral response, the marked assessment forms are then scanned into the system at the MFD.

Based on the information bar coded on the scanned forms, the system then identifies the student and Assessment Batch. The system then employs the appropriate image analysis of the markings, and performs an evaluation of each item on each of the assessments based upon a pre-programmed rubric. The system then automatically stores a preliminary evaluation in the Data Warehouse/Repository for each student. The teacher/educator may then view the assessments at a remote terminal and validate/annotate them. The system then automatically updates the validated/annotated assessment records in the Data Warehouse/Repository (DW/R) for later retrieval in various report views, which may be retrieved at the MFD or remotely by the teacher or other authorized educator.

This disclosure and the exemplary embodiments provided herein address concerns of users of an Automatic Educational Assessment System as disclosed in U.S. Patent Publication No. 2010/0075290, published Mar. 25, 2010, by DeYoung et al., and entitled “AUTOMATIC EDUCATIONAL ASSESSMENT SERVICE”, which include the desire to use preexisting assessments and curriculum.

INCORPORATION BY REFERENCE

IMS Global Learning Consortium, IMS Question & Test Interoperability Overview, http://www.imsglobal.org/question/qtiv2p1/imsqti_oviewv2p1.html, 31 Aug. 2012;

U.S. Pat. No. 8,831,504, issued Sep. 9, 2014, by German et al., and entitled “SYSTEM AND METHOD FOR GENERATING INDIVIDUALIZED EDUCATIONAL PRACTICE WORKSHEETS”;

U.S. Pat. No. 8,768,241, issued Jul. 1, 2014, by Venable, and entitled “SYSTEM AND METHOD FOR REPRESENTING DIGITAL ASSESSMENTS”;

U.S. Pat. No. 8,725,059, issued May 13, 2014, by Lofthus et al, and entitled “SYSTEM AND METHOD FOR RECOMMENDING EDUCATIONAL RESOURCES”;

U.S. Pat. No. 8,718,534, issued May 6, 2014, by Srinivas Sharath, and entitled “SYSTEM FOR CO-CLUSTERING OF STUDENT ASSESSMENT DATA”;

U.S. Pat. No. 8,699,939, issued Apr. 15, 2014, by German et al., and entitled “SYSTEM AND METHOD FOR RECOMMENDING EDUCATIONAL RESOURCES”;

U.S. Pat. No. 8,521,077, issued Aug. 27, 2013, by Venable, and entitled “SYSTEM AND METHOD FOR DETECTING UNAUTHORIZED COLLABORATION ON EDUCATIONAL ASSESSMENTS”;

U.S. Pat. No. 8,457,544, issued Jun. 4, 2013, by German et al., and entitled “SYSTEM AND METHOD FOR RECOMMENDING EDUCATIONAL RESOURCES”;

U.S. Pat. No. 7,965,891, issued Jun. 21, 2011, by Handley et al., and entitled “SYSTEM AND METHOD FOR IDENTIFYING AND LABELING FIELDS OF TEXT ASSOCIATED WITH SCANNED BUSINESS DOCUMENTS”;

U.S. Pat. No. 7,756,332, issued Jul. 13, 2010, by Jager, and entitled “METADATA EXTRACTION FROM DESIGNATED DOCUMENT AREAS”;

U.S. Pat. No. 7,689,037, issued Mar. 30, 2010, by Handley et al., and entitled “SYSTEM AND METHOD FOR IDENTIFYING AND LABELING FIELDS OF TEXT ASSOCIATED WITH SCANNED BUSINESS DOCUMENTS”;

U.S. Pat. No. 7,058,567, issued Jun. 6, 2006, by Ait-Mokhtar et al., and entitled “NATURAL LANGUAGE PARSER”;

U.S. Pat. No. 6,178,308, issued Jan. 23, 2001, by Bobrow et al., and entitled “PAPER-BASED INTERMEDIUM FOR PROVIDING INTERACTIVE EDUCATIONAL SERVICES”;

U.S. Patent Publication No. 2014/0234822, published Aug. 21, 2014, by Srinivas et al., and entitled “SYSTEM FOR CO-CLUSTERING OF STUDENT ASSESSMENT DATA”;

U.S. Patent Publication No. 2014/0093858, published Apr. 3, 2014, by Caruthers, Jr. et al., and entitled “METHOD AND SYSTEM FOR EVALUATING ELECTRONIC DOCUMENT”;

U.S. Patent Publication No. 2014/0065594, published Mar. 6, 2014, by Venable, and entitled “CREATING ASSESSMENT MODEL FOR EDUCATIONAL ASSESSMENT SYSTEM”;

U.S. Patent Publication No. 2014/0064622, published Mar. 6, 2014, by Newell et al., and entitled “METHOD AND SYSTEM FOR EVALUATING HANDWRITTEN DOCUMENTS”;

U.S. Patent Publication No. 2012/0189999, published Jul. 26, 2012, by Uthman et al., and entitled “SYSTEM AND METHOD FOR USING OPTICAL CHARACTER RECOGNITION TO EVALUATE STUDENT WORKSHEETS”;

U.S. Patent Publication No. 2011/0195389, published Aug. 11, 2011, by DeYoung et al., and entitled “SYSTEM AND METHOD FOR TRACKING PROGRESSION THROUGH AN EDUCATIONAL CURRICULUM”;

U.S. Patent Publication No. 2011/0151423, published Jun. 23, 2011, by Venable, and entitled “SYSTEM AND METHOD FOR REPRESENTING DIGITAL ASSESSMENTS”;

U.S. Patent Publication No. 2011/0123967, published May 26, 2011, by Perronnin et al., and entitled “DIALOG SYSTEM FOR COMPREHENSION EVALUATION”;

U.S. Patent Publication No. 2010/0157345, published Jun. 24, 2010, by Lofthus et al., and entitled “SYSTEM FOR AUTHORING EDUCATIONAL ASSESSMENTS”;

U.S. Patent Publication No. 2010/0075292, published Mar. 25, 2010, by DeYoung et al., and entitled “AUTOMATIC EDUCATION ASSESSMENT SERVICE”;

U.S. Patent Publication No. 2010/0075291, published Mar. 25, 2010, by DeYoung et al., and entitled “AUTOMATIC EDUCATIONAL ASSESSMENT SERVICE”;

U.S. Patent Publication No. 2010/0075290, published Mar. 25, 2010, by DeYoung et al., and entitled “AUTOMATIC EDUCATIONAL ASSESSMENT SERVICE”;

U.S. Patent Publication No. 2009/0035733, published Feb. 5, 2009, by Meitar et al., and entitled “DEVICE, SYSTEM, AND METHOD OF ADAPTIVE TEACHING AND LEARNING”;

U.S. Patent Publication No. 2005/0041860, published Feb. 24, 2005, by Jager, and entitled “METADATA EXTRACTION FROM DESIGNATED DOCUMENT AREAS”; and

Misra et al., “A SYSTEM FOR AUTOMATED EXTRACTION OF METADATA FROM SCANNED DOCUMENTS USING LAYOUT RECOGNITION AND STRING PATTERN SEARCH MODELS”, Archiving, 2009, 1509STP: 107-112, 17 pages, are incorporated herein by reference in their entirety.

BRIEF DESCRIPTION

In one embodiment of this disclosure, described is a method of creating an educational assessment using an image processing system, the created educational assessment including a plurality of questions associated with one or more predefined formats including metadata associated with each of the plurality of questions, and the created educational assessment administered to one or more students for completion, the method comprising: a) a user of the image processing system performing one or more of scanning a preexisting educational assessment into the image processing system generating a digital representation of the preexisting educational assessment which does not conform to the one or more predefined formats and does not include the associated metadata, and loading into the image processing system the digital representation of the preexisting educational assessment which does not conform to the one or more predefined formats and does not include the associated metadata; b) the image processing system displaying the preexisting educational assessment on a display operatively associated with the image processing system; c) the user selectably capturing an image of a single question associated with the displayed preexisting educational assessment; d) the image processing system generating a search query including one or more items included within the captured image of the single question; e) the image processing system executing a search of a Data Warehouse/Repository (DW/R) based on the search query to retrieve one or more predefined questions matching one or more search criteria associated with the search query, the one or more predefined questions associated with the one or more predefined formats including metadata associated with each of the one or more predefined questions; f) the image processing system displaying the one or more matching predefined questions on the display; g) the user selecting one or more of the displayed matching predefined questions including the metadata associated with each of the one or more predefined questions; and h) the image processing system creating a digital representation of an educational assessment including the user selected one or more displayed matching predefined questions including the metadata associated with each of the one or more predefined questions.

In another embodiment of this disclosure, described is an image processing system for creating an educational assessment, the created educational assessment including a plurality of questions associated with one or more predefined formats including metadata associated with each of the plurality of questions, and the created educational assessment administered to one or more students for completion, the image processing system comprising: a preexisting educational assessment processing module configured to perform one or more of receiving a digital representation of a preexisting educational assessment into the image processing system generated using an operatively associated scanner, and loading into the image processing system the digital representation of the preexisting educational assessment, the digital representation of the preexisting educational assessment not conforming to the one or more predefined formats and not including the associated metadata and the preexisting educational assessment processing module configured to display the preexisting educational assessment on a display operatively associated with the image processing system; an image capture module configured to capture an image of a single question associated with the displayed preexisting educational assessment; a search query module configured to generate a search query including one or more items included within a captured image of a single question associated with the displayed preexisting educational assessment, and execute a search of a Data Warehouse/Repository (DW/R) based on the search query to retrieve one or more predefined questions matching one or more search criteria associated with the search query, the one or more predefined questions associated with the one or more predefined formats including metadata associated with each of the one or more predefined questions; and an educational assessment creation module configured to display one or more matching predefined questions, receive one or more of the displayed matching predefined questions selected by the user, and creating a digital representation of an educational assessment including the user selected one or more displayed matching predefined questions including the metadata associated with each of the one or more predefined questions.

In still another embodiment of this disclosure, described is a method of creating an educational assessment using an image processing system, the created educational assessment including a plurality of questions including metadata associated with each of the plurality of questions, and the created educational assessment administered to one or more students for completion, the method comprising: a) a user of the image processing system creating and entering a question using a User Interface (UI) operatively associated with the image processing system; b) the image processing system generating a search query including one or more items included in the user created question; c) the image processing system executing a search of a Data Warehouse/Repository (DW/R) based on the search query to retrieve one or more predefined questions matching one or more search criteria associated with the search query, the one or more predefined questions associated with the one or more predefined formats including metadata associated with each of the one or more predefined questions; d) the image processing system displaying the one or more matching predefined questions and associated metadata on the UI; e) the user selecting one of the displayed matching predefined questions and/or selecting the metadata associated with one of the displayed matching predefined questions; and f) the image processing system creating a digital representation of an educational assessment including the user created question including metadata associated with the user selected matching predefined question and/or user selected metadata.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a pictorial diagram of a method to process preexisting assessments according to an exemplary embodiment of this disclosure;

FIG. 2 is a diagram of a system to process preexisting assessments according to an exemplary embodiment of this disclosure;

FIGS. 3A and 3B is a flow chart of a method to generate a printed assessment for manual marking by a student according to an exemplary embodiment of this disclosure;

FIG. 4 is a pictorial diagram of a workflow method to create an educational assessment based on a preexisting educational assessment not including metadata using an image processing system according to an exemplary embodiment of this disclosure, the created educational assessment including a plurality of questions and associated metadata retrieved from a question item bank;

FIG. 5 is an example of a preexisting educational assessment question according to an exemplary embodiment of this disclosure;

FIG. 6 is an example of an original preexisting teacher created educational assessment which does not include any associated metadata, the original preexisting educational assessment subsequently processed according to an exemplary embodiment of this disclosure;

FIG. 7 illustrates the display of the example preexisting teacher created educational assessment after it is scanned into the image processing system according to an exemplary embodiment of this disclosure;

FIG. 8 illustrates the image processing system displayed preexisting educational assessment in FIG. 7 including a teacher selected question according to an exemplary embodiment of this disclosure;

FIG. 9 is a detailed view of the teacher selected question shown in FIG. 8;

FIG. 10 illustrates a Question Selected Tool including question query results for selection by a teacher and features to further refine the query according to an exemplary embodiment of this disclosure;

FIG. 11 is a pictorial diagram of another workflow method to create an educational assessment based on a teacher created question not including metadata using an image processing system according to an exemplary embodiment of this disclosure, the created educational assessment including a plurality of questions and associated metadata retrieved from a question item bank; and

FIG. 12 is a detailed view of the teacher created question shown in FIG. 11.

DETAILED DESCRIPTION

This disclosure provides a method and system that can take digital content that has been converted from paper and with the aid of the content owner, such as a teacher, search for similar and relevant content from published items. The teacher can then use their content and associate it with the published items or replace their content with the published item(s). The method and system provides an ease of use interface that enables teachers to create their own digital content based on exiting and previously used paper based content. In addition, the disclosed method and system allows for the elimination or reduction in the amount of professional services, i.e., specially trained technicians, required for the conversion of teacher content. See U.S. patent application Ser. No. 14/609,820, filed Jan. 30, 2015, by Clar et al., entitled “METHOD AND SYSTEM TO ATTRIBUTE METADATA TO PREEXISTING DOCUMENTS”.

Referring to FIG. 1, an overview of the functional operation of an assessment creation/evaluation system is illustrated wherein at station 1 the multifunctional device (MFD) is provided for the teacher/educator to input the information required regarding the assessment form and student or number of students desired to create an Assessment Batch; and, once the Assessment Batch has been created in the system by teacher/educator input at the DUI (digital user interface) of the MFD, the assessments may be also printed at the MFD or any remote printer connected thereto. In the present practice, an Assessment Batch includes the teacher's name and a student list which includes the names of the students to be included in the batch, the particular assessment form to be administered to the students in the student list and the creation date of the Assessment Batch.

At station 2 of the system indicated generally at 10 in FIG. 1, the teacher/educator administers the assessments which are marked. Depending on type of the assessment, the printed sheets may be marked by the teacher/educator or the students according to the nature of the assessment.

At station 3, the teacher/educator or their designated representative, scans the marked assessments into the system at the MFD. At station 4, the system automatically evaluates the assessments employing image analysis according to the established rubrics associated with the assessment form associated with the Assessment Batch and enables the teacher to access the evaluations at station 5 which is illustrated as a remote station such as a teacher's personal computer (PC). The teacher/educator validates/annotates the assessments and upon receipt of the validation, the system generates reports at station 6 which may be accessed and viewed at either the MFD or the teacher's personal computer terminal remote from the MFD.

Referring to FIG. 2, the overall architecture of the system employed with the presently disclosed method is illustrated pictorially with the MFD 12 connected through an application server 14 along line 16 to a network 18 which may be either a local or wide area network and may include connections to the internet. A remote terminal or PC 20 such as a teacher/educator access terminal is connected along line 22 to the network 18. A system server 24 is also connected to the network 18 and provides the functions of database access, serves as a workflow engine, mail handler, web server and functions of image processing/scoring.

A Data Warehouse/Repository 26 is also connected to the network and contains such items as assessment forms and associated rubrics, workflow definitions, Assessment Batch records, reports and teacher/student/class data and is operable to receive updates and to provide for access to data stored therein remotely therefrom over network 18.

As mentioned hereinabove, the system and method of the present disclosure function to assist a teacher/educator by providing automatic evaluation of assessments administered to students based upon established rubrics programmed into the system and employing image analysis. The system and method of the present disclosure have the capability to evaluate assessments which are marked with images other than by marking within a box or bubble with respect to multiple choice answers. The system has the ability to scan the marked assessment and lift the manually made marks made during the administering of the assessment from the preprinted markings on the assessment sheet. The system and method then employ image analysis to identify and evaluate the lifted marks. The method and system are capable of handling numerous types of assessment items employed by teachers/educators examples of which are illustrated in the present disclosure in FIGS. 8-22.

Various types of assessments may be administered to the students and may include summative, formative, diagnostic, interest, preference and benchmark assessments.

Referring to FIGS. 3A and 3B, the operation of the method of the present disclosure presented in block diagram in which, at step 30 the teacher/educator selects the education assessment service (EAS) print service from the DUI (Digital User Display) of the MFD 12 and proceeds to require the teacher to provide authentication or personal identification information at step 32. At step 34 the system then proceeds to display on the MFD DUI all the pre-defined assessment forms currently associated with the teacher's identification entered in at step 32.

The teacher then chooses at step 36 an assessment form and initiates the formation of an assessment “Batch” associated with that teacher and the selected assessment form. It will be understood, that once initiated, the “Assessment Batch” comprises the basic evaluation unit or cell that the teacher has requested. The teacher then proceeds at step 38 to input a class to assess such as, for example, a seventh grade class, a seventh grade math class, a fifth grade English writing class, or a fourth grade reading class, etc. The system then proceeds to step 40 and enquires as to whether the teacher/educator wishes to select the entire class; and, if the enquiry in step 40 is answered in the affirmative, the system then proceeds to step 42 and includes all students in the class on the Assessment Batch Student List. However, if the query at step 40 is answered in the negative, the system proceeds to step 44 and the class list is displayed on the MFD DUI and the teacher selects specific students to be included on the Assessment Batch Student List.

From step 42 or step 44 the system then proceeds to step 46 and the teacher is prompted to select print from the MFD DUI. The system then proceeds to step 48 and automatically creates a new Assessment Batch record in the Data Warehouse/Repository to store the teacher's identification, the particular assessment form, the Student List, the status data, the date created, and other data which may be required by the particular school administrator/system.

The system then proceeds to step 50 and automatically formats a personalized assessment layout for each student on the Student List, which layout includes the student name to insure each student receives the correct assessment and an identification bar code to encode the Assessment Batch and the student. The assessment item order/layout for each student may be varied for each student to discourage students from looking at neighboring students' assessments for hints. The system then proceeds to step 52, prints the personalized page(s) for each student on the Student List for the Assessment Batch. The system then confirms that all page(s) are printed and updates the Data Warehouse/Repository.

At step 54, the teacher/educator takes the personalized printed assessment page(s) and administers the assessment to each designated student. The teacher/assessor or student, as the case may be, manually marks on the printed assessment page(s) the appropriate response to the challenge indicated on the particular assessment page. Upon completion of marking of the assessments, the marked assessment pages are collected by the teacher/educator for subsequent evaluation.

For an assessment creator/evaluator system, the use of metadata is crucial for the functions of data tracking, reporting, and the customization of learning for the students as well for assisting teachers in their daily practice. The type of metadata to track ranges from the global level to the question level. For example, items being tracked on a global level may include:

(A)Global Level:

1. Assessment Name

2. Description

3. Level-(Grade)

4. Subject

5. Standards

6. Skills

The metadata being tracked on the question level may include:

(B)Question Level:

1. Question Type—(Multiple Choice, Rubric, Constructed Response, Fill in the Box, N of M, Bubble sheet, and future types (allowing for growth of invention)

2. Question Number

3. Points (worth)

4. Description

5. Standards

6. Skills

This data is stored in the system and aligned with the assessment that was scanned in. The assessment creator/evaluator system assigns additional data for filing and sorting of the assessment such as:

(C) Filing and Sorting Data Assigned

Assessment Name (A1)

Version number (auto generated as 1.0 for first install, successively increases as same assessment is scanned again with same name)

Created By (from user ID)

Grade (A3)

CCSS code (A5)

Description (A2)

Subject (A4).

Educators, over the course of their careers, accumulate a wealth of material that they like to incorporate into their lesson plans. This material includes assessments, often provided by publishers. One of the major challenges in getting educators to adopt automatic educational assessment technology is that educators are not willing to simply replace the content that they have used for years with the content included with the new platform. Simply providing a wealth of material isn't enough; the automatic educational assessment system needs to provide a mechanism for importing this existing material into the system.

Currently, automatic educational assessment systems do not have the capability to scan an arbitrary assessment and deconstruct it into separate questions, including question types, correct answers, etc. Existing content must be imported into the system and modified into a format that the assessment system is capable of interpreting. A current mechanism for doing this is a manually intensive process that requires scanning existing assessments and manually indicating the location of “hot spots” on the page, i.e., locations into which students will record the answers to the questions on the assessment, as well as the correct answers to each question. Some disadvantages associated with this stop-gap measure include (1) the use of a manual process requiring a trained professional services team to scan, markup the assessments (identifying “hot spots,” etc.), and to identify question types and correct answers; (2) the resulting assessments are one off aberrations that require a separate flow through an automatic educational assessment system; (3) detailed metadata about the questions, including the content of the question, is lost; and (4) assessments created in this manner cannot be used for newly created workflows based on automatically generated assessments, e.g., online assessments or tablet-based assessments.

Many publishers of educational material provide assessment content in structured, digital formats such as the IMS Question and Test Interoperability (QTI) standard. Standards like QTI provide a very structured representation of assessment questions, also referred to as “items”, including complete question content, question type, grade level, unit, correct answers, associated artifacts (e.g., images, charts, etc.) as well as a plethora of additional detailed metadata.

Typically, when a school district purchases materials from the publisher, the school district is also granted the right to use the structured, digital versions of the assessment content that is included with the material. For a fee, third party vendors will act as a go-between aggregating the content to which a specific school district has access across multiple publishers, and providing it to the school district, usually as something similar to a large set of flat files in QTI XML format. It is then possible to parse the content and store it in a searchable database referred to as an Item Bank. Once stored, the items may be retrieved in a number of ways, including database queries. For example, something like the following query can be used to find items that contain the words “quick,” “brown,” and “fox”, assuming the item body content is stored column ‘ItemBody’ of table ‘items’:

SELECT * FROM items WHERE CONTAINS(ItemBody, ‘quick’) AND
CONTAINS(ItemBody, ‘brown’) AND CONTAINS(ItemBody,
‘fox’);

Other, more sophisticated queries can test for specific word order or co-location of terms, e.g. return only questions that contain the words “quick,” “brown,” “fox,” “lazy,” and “dog” in that order:

SELECT * FROM items WHERE CONTAINS(ItemBody,
‘NEAR((quick, brown, fox, lazy, dog), 3)’);

Note the number “3” near the end of the query; this is the maximum distance parameter to the NEAR condition of the CONTAINS statement. This is used to specify the maximum number of non-matching terms that may appear between the terms specified in the query. Accordingly, for this example, the following item body is considered a match because none of the search terms are separated by more than 3 words.

• • The quick brown fox jumped over the lazy dog.

However, the following item body is not considered a match because the phrase “jumped over the very” separates the terms “fox” and “lazy” by more than 3 words.

• • The quick brown fox jumped over the very lazy dog.

The automatic educational assessment method and system disclosed herein leverages access to item banks to retrieve the structured, digital version of assessment items.

Initially, the teacher scans the existing content into the teacher-facing UI S61 and the existing assessment content is displayed 70 by the UI.

Next, the teacher draws a bounding box 71 around the body of an individual item, e.g., the text content of the question not including the answers in a multiple choice question S62.

Next, the bounding box is used to crop the image and Optical Character Recognition (OCR) is used to extract the text content 72 from the cropped image S63.

Next, the text is converted into an SQL (Structured Query Language) query 74 S64 and the query is executed by accessing an item bank 76. Step S65 executes some simple techniques to prevent the generation of long, complex queries and/or to improve results, such as:

Dropping stop words, such as “or,” “and,” “the,” etc.

Using only the longest words.

Splitting a query into some number N queries, e.g., one per line of extracted text. If many questions are returned by each query, results may be narrowed by only considering questions that are returned by M out of N queries S65.

Next, the teacher is presented with a list of the results 78 and chooses the correct or desired item S66.

If there are no satisfactory results returned because the corresponding item isn't available in the Item Bank, an assessment creation system can be used to recreate the item content as disclosed in U.S. patent application Ser. No. 14/609,820, filed Jan. 30, 2015, by Clar et al.

At this point the teacher may choose to alter the item content. While content publishers generally don't encourage this, it is not uncommon for teachers to use modified versions of publisher content.

Steps S61-S66 are repeated for each remaining question on the assessment.

The automatic educational assessment system generates and stores a new assessment with the content from the selected items and the assessment may now be administered to students along with any other assessment using a workflow as described with reference to FIGS. 1-3 associated with the automatic assessment system.

For those items that exist in the Item Bank to which the teacher has access, some potential benefits associated with the disclosed automatic educational assessment system include:

• • A teacher's existing content is quickly and easily imported into the automatic educational assessment system and used to create assessments compatible with the main, paper-based workflow, overcoming a significant barrier to adoption of an automatic assessment system by teachers.
  • Items imported may be relatively easily mixed-and-matched with other items to create custom assessments.
  • Assessments translated from paper to digital format may also be used in additional workflows, e.g., tablet or online based assessments.
  • All relevant metadata for each item is preserved without the need to extract metadata from the content on the page.

FIG. 5 is an example of a preexisting educational assessment question according to an exemplary embodiment of this disclosure.

FIG. 6 is an example of an original preexisting teacher created educational assessment which does not include any associated metadata, the original preexisting educational assessment subsequently processed according to an exemplary embodiment of this disclosure.

FIG. 7 illustrates the display of the example preexisting teacher created educational assessment after it is scanned into the image processing system according to an exemplary embodiment of this disclosure.

FIG. 8 illustrates the image processing system displayed preexisting educational assessment in FIG. 7 including a teacher selected question according to an exemplary embodiment of this disclosure.

FIG. 9 is a detailed view of the teacher selected question shown in FIG. 8.

FIG. 10 illustrates a Question Selected Tool including question query results for selection by a teacher and features to further refine the query according to an exemplary embodiment of this disclosure.

In many cases educators like to create their own questions or alter the content of existing questions, and the assessment creation toolkit provided herein includes this capability using an alternative workflow. The alternative workflow provides the teacher with the flexibility to tailor and tune assessments precisely as they see fit for their students, without the drawback of other systems which lose the metadata that publisher created content contains. Item formats such as QTI contain significant and detailed metadata that provides detailed information about individual questions, well above and beyond the item body and possible answers. Information such as grade level, subject, Common Core compliance and much more is contained within this metadata. For example, as shown in FIG. 10, each of the assessment questions is associated with a Common Core Standard (CCS) metadata field, here CCS: 3.MD.A.1.

Using a slightly altered version of the main workflow previously described with reference to FIG. 4, educators can construct their own questions and use the content as a query to find similar questions in an item bank. If a similar enough question is returned as a result of the query, the returned question metadata can be copied from the existing returned question into the newly teacher created question and modified as needed, thus avoiding the manual metadata entry that would otherwise be needed.

With reference to FIG. 11, shown is a pictorial diagram of the slightly altered version of the main workflow previously described, the altered version creating an educational assessment based on a teacher created question not including metadata using an image processing system according to an exemplary embodiment of this disclosure, the created educational assessment including a plurality of questions and associated metadata retrieved from a question item bank. Initially, at step S81 the teacher creates a new question 90 using the assessment creator. FIG. 12 is a detailed view of the teacher created question shown in FIG. 11.

Next, at step S82 the text of the question 91 is converted into an SQL query S83. The educator may pick and choose which terms are significant, e.g. “yards” and “divide” to find questions about division involving measurement in yards; other terms like “Jackie” or “rope” may constrain the question too much and reduce or eliminate good matches.

Next, at step S83 the question text is used to construct one or more search queries for the item bank 76.

Next, as S84, a matching algorithm expands or narrows the query to fine tune the results before returning the resulting items 92 to the teacher.

Next, at step S85 the teacher is presented with a list of the results 93 and chooses an item that most closely matches what she is looking for, and copies the metadata for that question.

a. If no results are returned, the teacher may alter the query, e.g., to search for “feet” instead of “yards.”

Next, the teacher pastes the metadata from the matching question into her new question, and modifies the fields as needed, and saves the item to her item bank.

Next, the teacher repeats steps S81-S85 for each question in the assessment.

Finally, the automatic educational assessment system generates and stores a new assessment with the content from the selected items and the assessment may now be given along with any other assessment using the workflow previously described with reference to FIGS. 1-3.

After executing this workflow, the teacher has a complete assessment populated with custom content and with all of the appropriate metadata intact.

Various aspects of the method and system are now described in further detail.

Given the example question in FIG. 5, there are several possible ways that a query or queries may be constructed to attempt to retrieve the corresponding question from an item bank. Provided are a few exemplary algorithms. It is to be understood, the variations may be used alone, or in combination if too many or too few results are returned. Further, the queries may be altered, e.g., using “OR” instead of “AND” clauses, to find similar but not exactly matching questions.

It is also important to note that the queries described herein are constructed solely using the content of the question body, as opposed to the entire question, e.g. the multiple choice options. The content of the entire question may be used in combination with another cropping and parsing technique to create queries that will produce different and sometimes better results by allowing for interrogation of other parts of the item model, e.g., the responses in a multiple choice question and/or the answer in addition to the item body.

OCR is not a perfect technology, and so it is desirable to avoid relying on a perfect and complete extraction of the content of the entire question. In order to improve results, and increase the possibility of receiving at least one matching item from the item bank, one exemplary technique breaks the question into significant parts, potentially using a confidence metric produced by the OCR engine to focus only on the words with a highest confidence, and build queries from those parts. Variations on this technique are used in the example algorithms below. To facilitate this, some simple natural language processing is used to remove stop words, e.g., and, or, the, etc., from the item content. For example, the item text, after stop words are removed could read something similar to the example shown in FIG. 4 as reference character 72. Additionally, for the examples described below, it is assumed that the text content of the item is stored as a string in the ‘ItemBody’ column of the ‘items’ table within the Item Bank.

In every case it is assumed that at least one item will be returned, and that the result set will contain the correct item. Alternatively, if no acceptable items are returned after trying several different techniques, a manual technique may be used to extract some of the question content directly from the scanned image instead.

A Single Simple Query

In this example, the entire content of the question is used as a single query. It's worth noting that some databases limit the number of search terms to some maximum, e.g., 64, so for a very long question this alternative may not be an option.

Step 1), calculate the maximum distance parameter for the NEAR condition for the entire body of text; this is a count of the stop words between search terms. In this example, the longest stop word phrase is 3 words long, “Which of the”.

Step 2), create a query containing all of the terms in the body of text (see example query below).

Step 3), execute the query against the item bank and return the result set.

The example query below contains every search term in the entire question:

SELECT * FROM items WHERE CONTAINS (ItemBody,
‘NEAR(Jackie, 20, yards, rope, needs, divide, between, 5,
people, following, shows, correct, units, answer), 3)’;

Querying Using Only Long Words

Alternatively, the query may be simplified by using only words longer than some arbitrary threshold.

Step 1), calculate the maximum distance parameter for the NEAR condition counting not only skipped stop words, but words containing fewer than some number of characters, e.g., 6. In this example, the longest phrase containing terms not included in the search is 8 words long, e.g., “has 20 yards of rope. She needs to”.

Step 2), create a query containing all of the words that contain at least the required number of characters and the calculated distance parameter (see example query below).

Step 3), execute the query against the item bank and return the result set.

In the example below, only words that are longer than 5 characters are used:

SELECT * FROM items WHERE CONTAINS(ItemBody,
‘NEAR(Jackie, divide, between, people, following,
correct, answer), 8)’;

One Query Per Line

Alternatively, the query may be broken up into several queries, each of which returns a separate result set.

Step 1), calculate the maximum distance parameter for the NEAR condition only for the first line of text. In this example there is at most one word separating each of the terms.

Step 2), create a query containing only terms from the first line of text using the calculated maximum distance (see example queries below).

Step 3), execute the query against the item bank and save the result set.

Repeat steps 1)-3) for each line of text in the question that contains two or more search terms.

If a line contains fewer than 2 search terms, e.g. line 4, which contains only the single term “answer”, it may be omitted or concatenated onto another query.

Step 4), iterate over the result sets and record the number of times each unique item appears.

Step 5), build a new result set by comparing the count for each unique item to a threshold and including only those items that meet or exceed the threshold, e.g., items that appear in 2 out of 3 of the result sets.

The example queries for lines 1 and 2 contain only search terms corresponding to words found on those lines of text:

SELECT * FROM items WHERE CONTAINS (ItemBody,
‘NEAR(Jackie, 20, yards, rope, needs), 2)’;
SELECT * FROM items WHERE CONTAINS (ItemBody,
‘NEAR(divide, between, 5, people), 2)’;

In order to avoid a query that contains only a single word which would therefore return a large set of results, the final query concatenates the single word ‘answer’ from line 4 of the text onto the end of the query for line 3:

SELECT * FROM items WHERE CONTAINS (ItemBody,
‘NEAR(following, shows, correct, units, answer),
2);

Some portions of the detailed description herein are presented in terms of algorithms and symbolic representations of operations on data bits performed by conventional computer components, including a central processing unit (CPU), memory storage devices for the CPU, and connected display devices. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is generally perceived as a self-consistent sequence of steps leading to a desired result. The steps are those requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like.

It should be understood, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated otherwise, as apparent from the discussion herein, it is appreciated that throughout the description, discussions utilizing terms such as “processing” or “computing” or “calculating” or “determining” or “displaying” or the like, refer to the action and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices.

The exemplary embodiment also relates to an apparatus for performing the operations discussed herein. This apparatus may be specially constructed for the required purposes, or it may comprise a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer. Such a computer program may be stored in a computer readable storage medium, such as, but is not limited to, any type of disk including floppy disks, optical disks, CD-ROMs, and magnetic-optical disks, read-only memories (ROMs), random access memories (RAMs), EPROMs, EEPROMs, magnetic or optical cards, or any type of media suitable for storing electronic instructions, and each coupled to a computer system bus.

The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose systems may be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform the methods described herein. The structure for a variety of these systems is apparent from the description above. In addition, the exemplary embodiment is not described with reference to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the exemplary embodiment as described herein.

A machine-readable medium includes any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer). For instance, a machine-readable medium includes read only memory (“ROM”); random access memory (“RAM”); magnetic disk storage media; optical storage media; flash memory devices; and electrical, optical, acoustical or other form of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.), just to mention a few examples.

The methods illustrated throughout the specification, may be implemented in a computer program product that may be executed on a computer. The computer program product may comprise a non-transitory computer-readable recording medium on which a control program is recorded, such as a disk, hard drive, or the like. Common forms of non-transitory computer-readable media include, for example, floppy disks, flexible disks, hard disks, magnetic tape, or any other magnetic storage medium, CD-ROM, DVD, or any other optical medium, a RAM, a PROM, an EPROM, a FLASH-EPROM, or other memory chip or cartridge, or any other tangible medium from which a computer can read and use.

Alternatively, the method may be implemented in transitory media, such as a transmittable carrier wave in which the control program is embodied as a data signal using transmission media, such as acoustic or light waves, such as those generated during radio wave and infrared data communications, and the like.

It will be appreciated that variants of the above-disclosed and other features and functions, or alternatives thereof, may be combined into many other different systems or applications. Various presently unforeseen or unanticipated alternatives, modifications, variations or improvements therein may be subsequently made by those skilled in the art which are also intended to be encompassed by the following claims.

Claims

1. A method of creating an educational assessment using an image processing system, the created educational assessment including a plurality of questions associated with one or more predefined formats including metadata associated with each of the plurality of questions, and the created educational assessment administered to one or more students for completion, the method comprising:

a) a user of the image processing system performing one or more of scanning a preexisting educational assessment into the image processing system generating a digital representation of the preexisting educational assessment which does not conform to the one or more predefined formats and does not include the associated metadata, and loading into the image processing system the digital representation of the preexisting educational assessment which does not conform to the one or more predefined formats and does not include the associated metadata;

b) the image processing system displaying the preexisting educational assessment on a display operatively associated with the image processing system;

c) the user selectably capturing an image of a single question associated with the displayed preexisting educational assessment;

d) the image processing system generating a search query including one or more items included within the captured image of the single question;

e) the image processing system executing a search of a Data Warehouse/Repository (DW/R) based on the search query to retrieve one or more predefined questions matching one or more search criteria associated with the search query, the one or more predefined questions associated with the one or more predefined formats including metadata associated with each of the one or more predefined questions;

f) the image processing system displaying the one or more matching predefined questions on the display;

g) the user selecting one or more of the displayed matching predefined questions including the metadata associated with each of the one or more predefined questions; and

h) the image processing system creating a digital representation of an educational assessment including the user selected one or more displayed matching predefined questions including the metadata associated with each of the one or more predefined questions.

2. The method of executing an educational assessment according to claim 1, wherein steps c)-h) are repeated for a second user selected single question.

3. The method of creating an educational assessment according to claim 1, wherein the user selectably captures the image of the single question using a bounding box.

4. The method of creating an educational assessment according to claim 1, wherein step d) includes the image processing system performing Optical Character Recognition (OCR) to extract text content from the captured image.

5. The method of creating an educational assessment according to claim 4, wherein the extracted text is processed by the image processing system to generate the search query.

6. The method of creating an educational assessment according to claim 5, wherein the search query is a SQL (Structured Query Language) query.

7. The method of creating an educational assessment according to claim 6, wherein step e) narrows the search query if more than a predetermined number of matching predefined questions are retrieved from the DW/R.

8. The method of creating an educational assessment according to claim 1, wherein step d) comprises:

d1) performing OCR to extract text content from the captured image; and

d2) generating a SQL search query, the SQL search query generated using one or more of: dropping predefined stop words; using only longest extracted words; and splitting the query into a plurality of queries.

9. The method of creating an educational assessment according to claim 1, wherein the associated metadata includes one or more of question content, question type, grade level, unit, correct answer, and associated one or more artifacts.

10. The method of creating an educational assessment according to claim 1, wherein step c) includes the user selecting one or more items included in the captured image of the single question to be used to generate the search query.

11. An image processing system comprising memory storing instructions for performing the method of creating an educational assessment according to claim 1.

12. An image processing system for creating an educational assessment, the created educational assessment including a plurality of questions associated with one or more predefined formats including metadata associated with each of the plurality of questions, and the created educational assessment administered to one or more students for completion, the image processing system comprising:

a preexisting educational assessment processing module configured to perform one or more of receiving a digital representation of a preexisting educational assessment into the image processing system generated using an operatively associated scanner, and loading into the image processing system the digital representation of the preexisting educational assessment, the digital representation of the preexisting educational assessment not conforming to the one or more predefined formats and not including the associated metadata and the preexisting educational assessment processing module configured to display the preexisting educational assessment on a display operatively associated with the image processing system;

an image capture module configured to capture an image of a single question associated with the displayed preexisting educational assessment;

a search query module configured to generate a search query including one or more items included within a captured image of a single question associated with the displayed preexisting educational assessment, and execute a search of a Data Warehouse/Repository (DW/R) based on the search query to retrieve one or more predefined questions matching one or more search criteria associated with the search query, the one or more predefined questions associated with the one or more predefined formats including metadata associated with each of the one or more predefined questions; and

an educational assessment creation module configured to display one or more matching predefined questions, receive one or more of the displayed matching predefined questions selected by the user, and creating a digital representation of an educational assessment including the user selected one or more displayed matching predefined questions including the metadata associated with each of the one or more predefined questions.

13. The image processing system according to claim 12, wherein the image capture module is configured to selectably capture the image of the single question using a bounding box.

14. The image processing system according to claim 12, wherein the search query module is configured to perform Optical Character Recognition (OCR) to extract content from the captured image and the extracted text is processed to generate a SQL (Structured Query Language) query.

15. The image processing system according to claim 12, wherein the associated metadata includes one or more of question content, question type, grade level, unit, correct answer, and associated one or more artifacts.

16. The image processing system according to claim 12, wherein the search query module is configured to generate the search query using one or more user selected items included in the captured image of the single question.

17. A method of creating an educational assessment using an image processing system, the created educational assessment including a plurality of questions including metadata associated with each of the plurality of questions, and the created educational assessment administered to one or more students for completion, the method comprising:

a) a user of the image processing system creating and entering a question using a User Interface (UI) operatively associated with the image processing system;

b) the image processing system generating a search query including one or more items included in the user created question;

c) the image processing system executing a search of a Data Warehouse/Repository (DW/R) based on the search query to retrieve one or more predefined questions matching one or more search criteria associated with the search query, the one or more predefined questions associated with the one or more predefined formats including metadata associated with each of the one or more predefined questions;

d) the image processing system displaying the one or more matching predefined questions and associated metadata on the UI;

e) the user selecting one of the displayed matching predefined questions and/or selecting the metadata associated with one of the displayed matching predefined questions; and

f) the image processing system creating a digital representation of an educational assessment including the user created question including metadata associated with the user selected matching predefined question and/or user selected metadata.

18. The method of creating an educational assessment according to claim 17, wherein step b) includes the image processing system performing Optical Character Recognition (OCR) to extract text content from the user created question, and the extracted text is processed by the image processing system to generate the search query.

19. The method of creating an educational assessment according to claim 17, wherein the associated metadata includes one or more of question content, question type, grade level, unit, correct answer, and associated one or more artifacts.

20. An image processing system comprising memory storing instructions for performing the method of creating an educational assessment according to claim 17.