JP5905690B2 - Answer processing device, answer processing method, program, and seal - Google Patents

Description

  The present invention relates to an apparatus for processing an answer written on an answer sheet by a student.

  2. Description of the Related Art Conventionally, as an answer processing system, an answer processing system provided with an input means and a display means, (a) a first storage in which answer data in which an unprocessed answer of a test is converted into image data is stored. Means, (b) second storage means for storing answer data in which the answer that has been processed is converted into image data, and (c) explanatory data relating to the question being questioned in the test is stored in advance. A database, and (d) in response to a display instruction of a specific answer input from the input means, read out answer data corresponding to the specific answer from the first storage means and display on the display means, In addition to adding the processing data of the answer based on a predetermined standard inputted from the input means in response to the displayed answer data to the displayed answer data, the answer data is included in the answer Answer processing means for reading explanation data relating to a subject from the database and adding the answer data to the answer data, and storing answer data to which the processing data and the explanation data are added in a second storage means, There has been known an answer processing system characterized by the fact (see, for example, Patent Document 1).

JP 2006-227317 A (first page, FIG. 1 etc.)

  However, in the past, there has been a problem that an answer written by a student cannot be appropriately processed.

  For example, as described above, it is possible to manage the answer by the student as image data. In this case, in order to manage the answer in association with the student, when the answer is converted into image data, etc. The student's identification information (for example, name, etc.) must be manually input, which is very time-consuming and cannot be processed easily.

  Further, when the student's answer is used for statistical processing or the like, it is necessary to take out the contents entered by the student in the image data of the answer and perform character recognition by so-called OCR to acquire character information. However, there is a problem that characters other than the contents entered by the student, such as characters originally printed on the answer sheet, are recognized by the OCR, and unnecessary information is generated. As a result, for example, there has been a problem that statistical processing using the contents entered by students cannot be performed properly.

  The answer processing apparatus according to the present invention is an answer sheet in which one or more students have entered an answer, and is an image information associated with student identification information that is identification information of each student who has entered the answer. Information indicating an answer reading information storage unit for storing answer reading information, which is information obtained by reading an answer sheet on which an image is arranged, and an answer sheet from which answer reading information is read before the answer is written An answer sheet information storage unit for storing answer sheet information, and a difference acquisition unit for acquiring difference related information that is information related to a difference of answer sheet information of the answer reading information stored in the answer reading information storage unit; The difference acquisition unit detects an identification image of the answer reading information from which the difference is acquired, and has a student identification information acquisition unit that acquires student identification information associated with the identification image, difference related information, and student identification information. Answer information storage section for storing answer information, answer information storage section storing answer information including difference related information acquired by the difference acquisition section and student identification information acquired by the student identification information acquisition section An answer processing apparatus including an accumulation unit.

  With this configuration, since the answer written by the student and the student identification information can be easily acquired from the answer reading information and stored as answer information, the answer written by the student can be appropriately processed.

  The answer processing apparatus according to the present invention includes a statistical analysis unit that performs statistical analysis on the answer information for each student using the student identification information included in the answer information stored in the answer information storage unit. The answer processing apparatus includes an output unit that outputs a statistical analysis result of the statistical analysis unit.

  With this configuration, appropriate statistical analysis can be performed using the answer information.

  In the answer processing apparatus according to the present invention, in the answer processing apparatus, the answer information further includes date information which is information indicating a date corresponding to the answer information, and the statistical analysis unit has the answer information. This is an answer processing apparatus that performs statistical analysis on answer information for each period specified in advance using date information.

  With this configuration, it is possible to easily obtain a statistical analysis result for each predetermined period.

  The answer processing apparatus of the present invention further includes a character recognition unit that performs character recognition processing on the difference related information acquired by the difference acquisition unit in the answer processing device, and the statistical analysis unit performs statistical analysis on the answer information. As a statistical analysis on the characters described in the difference related information included in the answer information, using information indicating the result of the character recognition processing performed by the character recognition unit on the difference related information included in the answer information It is an answer processing apparatus to be performed.

  With this configuration, it is possible to easily obtain a statistical analysis result regarding characters in the student's answer.

  In the answer processing apparatus according to the present invention, in the answer processing apparatus, the statistical analysis related to the characters described in the difference related information is an answer regarding the amount of characters recognized for the difference related information by the character recognition unit. It is a processing device.

  With this configuration, for example, it is possible to easily obtain a statistical analysis result relating to the amount of characters written in a student's answer.

  In the answer processing apparatus of the present invention, in the answer processing apparatus, the statistical analysis related to the characters described in the difference related information is a statistical analysis related to the diversity of characters recognized for the difference related information by the character recognition unit. This is an answer processing apparatus.

  With this configuration, for example, it is possible to easily obtain a statistical analysis result on knowledge about characters, character strings, words, and the like of each student.

  The answer processing apparatus according to the present invention is an answer processing apparatus in which, in the answer processing apparatus, the statistical analysis related to the characters described in the difference-related information is statistical analysis related to the attributes of the characters described.

  With this configuration, it is possible to easily obtain a statistical analysis result regarding the character attributes in the student's answer.

  The answer processing apparatus of the present invention is an answer processing apparatus in which, in the answer processing apparatus, the statistical analysis relating to the character attribute is a statistical analysis relating to the character recognition result performed by the character recognition unit on the difference related information. .

  With this configuration, for example, it is possible to easily obtain a statistical analysis result regarding the cleanliness of characters in the student's answer.

  In the answer processing apparatus according to the present invention, in the answer processing apparatus, the statistical analysis related to the character attribute is a statistics related to a recognized character size indicated by a character recognition result performed by the character recognition unit on the difference related information. It is an answer processing apparatus that is an analysis.

  With this configuration, for example, it is possible to easily obtain a statistical analysis result regarding the cleanliness of characters in the student's answer.

  The answer processing apparatus according to the present invention further includes a character recognition unit that performs character recognition processing on the difference related information acquired by the difference acquisition unit in the answer processing apparatus, and relates to the characters described in the difference related information. Statistical analysis is an answer processing apparatus that is statistical analysis on the accuracy of a sentence indicated by characters recognized by a character recognition unit.

  With this configuration, for example, it is possible to easily obtain a statistical analysis result regarding whether or not a student can create an accurate sentence.

  The answer processing apparatus according to the present invention further includes a character recognition unit that performs character recognition processing on the difference related information acquired by the difference acquisition unit in the answer processing apparatus, and relates to the characters described in the difference related information. The statistical analysis is an answer processing apparatus that is a statistical analysis regarding the number of characters per unit area of the written characters.

  With such a configuration, for example, it is possible to easily obtain a statistical analysis result regarding the degree of the amount that a student enters characters in an answer.

  The seal of the present invention is a seal in which an identification image associated with student identification information, which is student identification information, is arranged on the surface.

  With this configuration, it is possible to easily arrange student identification information on an answer sheet simply by attaching a sticker, and it is possible to easily arrange student identification information corresponding to each student on a student's answer.

  The seal of the present invention is a seal in which a character string indicating student identification information corresponding to the identification image is arranged around the identification image in the seal.

  With this configuration, each student can easily confirm which student's identification image is arranged.

  According to the answer processing apparatus and the like according to the present invention, the answer written by the student can be appropriately processed.

The block diagram of the answer processing apparatus in embodiment of this invention The figure which shows the figure which shows an example of the seal A flowchart for explaining the operation of the answer processing apparatus A flowchart for explaining the operation of the answer processing apparatus FIG. 5A shows an example of answer sheet information of the answer processing apparatus (FIG. 5A), and FIG. 5B shows an example of answer reading information (FIG. 5B). The figure which shows the answer sheet information management table of the answer processing apparatus The figure which shows the answer reading information management table | surface of the answer processing apparatus The figure which shows the difference relevant information of the answer processing apparatus A figure showing text information acquired by the answer processing apparatus (FIG. 9A) and a figure showing a recognition management table (FIG. 9B) The figure which shows the answer information management table | surface of the answer processing apparatus The figure which shows the acquisition information classified by year of the same answer processing device The figure which shows the annual analysis result management table of the same answer processing device The figure which shows the annual analysis result management table of the same answer processing device The figure which shows an example of the external appearance of the computer system in embodiment of the same invention The figure which shows an example of a structure of the computer system

  Hereinafter, embodiments of an answer processing apparatus and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.

(Embodiment)
FIG. 1 is a block diagram of an answer processing apparatus 1 according to the present embodiment.

  The answer processing apparatus 1 includes an answer reading information storage unit 11, an answer sheet information storage unit 12, a difference acquisition unit 13, a student identification information acquisition unit 14, a character recognition unit 15, an answer information storage unit 16, an answer information storage unit 17, a statistics An analysis unit 18 and an output unit 19 are provided.

  The answer reading information storage unit 11 stores one or more answer reading information. The answer reading information is an answer sheet in which one or more students have filled in the answer, and is information obtained by reading an answer sheet in which an identification image associated with the student identification information of each student who has entered the answer is arranged. is there. The answer reading information is usually information obtained by reading an answer sheet with a scanner or the like. However, it may be information read (photographed) by a digital still camera or the like. The answer reading information is, for example, image information of the reading surface of the answer sheet. The answer reading information is, for example, a raster image in JPEG format, PNG format, or TIFF format. However, it may be an image obtained by vectorizing a raster image by automatic tracing or the like. The color depth of the answer reading information does not matter. Usually, in the answer, there are many cases where color information is not necessary, so a binary image such as black and white or a gray scale image may be used. A color image may also be used. The color depth may be changed after reading the answer sheet. A higher resolution of the answer reading information is preferable in that the characters written by the student can be read accurately. However, since the amount of data such as the answer reading information increases, for example, a resolution of about 200 ppi to 600 ppi is used. Often.

  The answer sheet is a sheet on which an answer to a question is entered. The material of the answer sheet does not matter. In the answer sheet, usually, an entry field for entering an answer, and problem identification information such as a problem number used for associating the entry field with a problem are arranged (for example, printed). The answer sheet on which the answer is written is an answer sheet in which characters indicating the answer written by the student using a writing tool or the like are arranged. In addition, answers other than letters may be entered. The students here are students of schools, cram schools, prep schools and the like. The answer sheet may contain questions. The answer sheet may include a date entry field, an answer sheet, and information for identifying a problem corresponding to the answer sheet.

  The student identification information is identification information of each student. For example, the student identification information includes a student name, a student ID number, a resident code, an e-mail address, and the like.

  The identification image is information of an image associated with identification information (here, particularly student identification information). The identification image is an image that represents a character string (specifically, a code) with a figure. This character string may be a number or the like. The identification image is, for example, a barcode. A bar code represents a character by, for example, a plurality of rectangles having various thicknesses and lengths, and their arrangement and intervals. The barcode may be, for example, a one-dimensional barcode in which a plurality of lines having various thicknesses are arranged in one direction and characters are expressed by the arrangement and interval of the lines. The barcode is, for example, a plurality of rectangles having various thicknesses and lengths arranged in the vertical direction and the horizontal direction, and the characters are expressed by the arrangement (positional relationship) of the rectangles and the intervals thereof. It may be a two-dimensional barcode (hereinafter referred to as a two-dimensional barcode). A two-dimensional barcode is also called a two-dimensional code. The two-dimensional barcode is, for example, a QR code or PDF417. In the present embodiment, for convenience of explanation, a case where the identification image is a two-dimensional barcode will be described as an example.

  The identification image associated with the student identification information is information (character string) read from the identification image (for example, a two-dimensional barcode), the identification image being student identification information, or information (character string) read out. Is an identification image associated with the student identification information. Reading of a character string or the like from the identification image is performed by a device that reads the identification image and converts it into a corresponding character string, such as a so-called bar code reader (not shown). For example, in a QR code or the like which is one of two-dimensional barcodes, it is possible to acquire student identification information such as a student name by performing a process of reading the QR code with a dedicated barcode reader. The identification image may be arranged in any manner on the answer sheet. For example, the identification image may be printed on the answer sheet from the beginning, or a two-dimensional barcode is placed on the surface (for example, printed). However, it may be affixed to the answer sheet.

  Since the 2D barcode placed on the answer sheet needs to be associated with the student identification information of the student who fills in the answer, each answer sheet has a student who fills in the answer. It is preferable to affix a sticker on which a two-dimensional barcode associated with the student identification information is placed.

  FIG. 2 is a diagram illustrating an example of a sticker on which an identification image associated with student identification information is arranged.

  An identification image is arranged on the surface of the seal 20. Here, a case where a two-dimensional barcode is used as an identification image is shown as an example. However, other identification images may be used. For example, an adhesive or a pressure-sensitive adhesive is provided on the back surface of the seal 20. In the seal 20 of the identification image 21, as shown in FIG. 2, a character string 22 (here, Yamada A male) indicating student identification information associated with the identification image is arranged in the vicinity of the identification image. It is preferable to be (for example, printed). The character string 22 here is a concept including numbers and the like. In this way, it is possible to easily determine which student the identification image associated with the student identification information is the seal 20 on which the identification image is arranged without reading the identification image. Note that the student identification information arranged in the vicinity of the identification image only needs to be associated with the student identification information associated with the identification image (for example, student identification information read from the identification image). , They are not necessarily the same. For example, the student identification information arranged in the vicinity of the identification image may be the student's name, and the student identification information associated with the identification image may be the student's student ID number. By sticking such a sticker 20 to an answer sheet in which each student has written an answer or an answer sheet in which each student intends to fill in an answer, an identification image associated with the student identification information of each student is obtained. It can be easily placed on the answer sheet.

  In addition, the position where the sticker 20 is pasted or the range in which the sticker 20 can be pasted on the answer sheet may be specified on the answer sheet using a frame line or the like.

  The answer reading information may be associated with information related to the date of the answer sheet on which the student has written the answer. The information on the date of the answer sheet on which the student has written the answer may be information on the date on which the student has written the answer, or information on the date on which the answer sheet was read. The information related to the date is usually date information. The information regarding the date may include time information.

  The answer reading information storage unit 11 is preferably a nonvolatile recording medium, but can also be realized by a volatile recording medium. The same applies to other storage units and the like.

  The answer sheet information storage unit 12 stores answer sheet information, which is information indicating a state before an answer is written, of an answer sheet from which answer reading information is read. The answer sheet information is, for example, image information of an answer sheet obtained by reading, using a scanner or the like, an answer sheet before a student enters an answer, or an unfilled answer sheet that is the same as an answer sheet on which a student has entered an answer. is there. Further, it may be data for creating an answer sheet, for example, data for a word processor or DTP software, or information obtained by rasterizing these data. The answer sheet information may be information that can acquire a raster image of the answer sheet, for example. Note that the resolution of the answer sheet information and the resolution of the answer reading information are preferably the same. The answer reading information and answer sheet information corresponding to one answer sheet are managed in association with each other, for example. For example, each answer reading information is managed in association with the identification information of the corresponding answer sheet information. It should be noted that by identifying the answer sheet identification information in advance on the answer sheet, the identification information obtained by reading the answer sheet identification information can be used as both the answer reading information and the answer sheet information. You may make it match | combine. For example, in this case, an identification image (for example, a barcode) associated with the identification information of the answer sheet is placed on the answer sheet, and the answer reading information and the answer sheet information The identification information obtained by reading the identification image may be associated with both the answer reading information and the answer sheet information.

  The difference acquisition unit 13 acquires difference related information, which is information related to a difference between the answer reading information stored in the answer reading information storage unit 11 and the answer sheet information stored in the answer sheet information storage unit 12. The difference here is, for example, difference image information. The difference between the answer reading information and the answer sheet information is a concept including the difference of the answer sheet information with respect to the answer reading information. The difference-related information may be the difference information itself, information obtained by performing processing specified in advance on the difference, for example, information obtained by binarizing the difference information, so-called contour correction, or the like It may be information that has been performed. The difference-related information is, for example, image information indicating a difference between answer reading information and answer sheet information, or image information obtained by performing a predesignated process on the image information. The difference acquisition unit 13 reads, for example, one or more answer reading information that is the acquisition target of difference related information and answer sheet information corresponding to each answer reading information, and for each answer reading information, a corresponding answer, respectively. The difference related information is acquired by acquiring the difference with respect to the sheet information. Or processing etc. are performed to the acquired difference and difference related information is acquired. When the answer sheet information is a vector image or the like, the difference is obtained by appropriately rasterizing. The difference acquisition unit 13 deletes the pixel when the pixel values match between the pixels of the answer reading information that overlap the answer sheet information (for example, the pixels with the same coordinates), thereby obtaining the difference. Get related information. Alternatively, when the pixel values match, the color value of the pixel may be changed to a color value such as white that is designated in advance. Alternatively, the pixel may be invisible. Thereby, the difference related information indicating the difference image can be acquired. In order to make a pixel invisible, for example, a channel (so-called alpha channel) that specifies the transparency of each pixel may be provided in the difference-related information. In the difference related information, a minimum rectangle including a portion where a difference exists may be detected, and a portion other than the rectangle may be deleted.

  The student identification information acquisition unit 14 detects the identification image of the answer reading information from which the difference acquisition unit 13 has acquired the difference, and acquires the student identification information associated with the identification image. The student identification information acquisition unit 14 detects an image of an identification image in the answer reading information and uses the detected identification image by a device that reads identification information associated with the identification image such as a so-called barcode reader. For example, student identification information that is identification information corresponding to an identification image is acquired by processing with an algorithm similar to the algorithm. As a result, the student identification information acquisition unit 14 has acquired the student identification information. When the identification image is detected from the answer reading information, for example, a pre-designated dot pattern or contour line provided at a corner or the like of the identification image is searched and detected from the answer reading information. It is determined that the identification image is arranged in a region surrounded by a corner or the like. In addition, for example, when the place where the identification image is arranged is determined in advance by coordinates or the like, the image of the predetermined place of the answer reading information is read as the image of the identification image, or this place is the same as described above. The identification image is searched for. In addition, since the process etc. which detect the position of an identification image within an image are well-known as a barcode reader technique etc., detailed description is abbreviate | omitted here. In addition, since processing for obtaining corresponding identification information from an identification image such as a two-dimensional barcode is well known as a technology of an apparatus for reading an identification image such as a barcode reader, detailed description thereof is omitted here.

  The character recognition unit 15 performs a character recognition process on the difference related information acquired by the difference acquisition unit 13. As character recognition processing, for example, OCR (Optical Character Recognition) is used. As a result of character recognition, for example, text information composed of characters recognized for difference-related information is acquired. This text information may include information on a format such as a character size. Since the OCR technique is a known technique, a detailed description thereof will be omitted, but an example of the OCR process will be briefly described below.

  For example, the character recognition unit 15 performs binarization processing or the like on the difference-related information to detect the boundary between character pixels, or detects the change point of the color density of the portion other than the character and the character. The boundary of the character pixel is detected, each character written by the student is recognized as one continuous chunk, and a rectangular area surrounding each character chunk is obtained. As a result, an image that individually includes each character included in the difference-related information is detected. Then, for the characters included in each obtained rectangular area, for example, vectorization or the like is performed to obtain values indicating character features such as intersection position information and end point position information, and these values are prepared in advance. The similarity score between the characters included in the dictionary and the characters in each rectangular area is obtained by comparing the values with the same characteristics stored in the dictionary in association with a plurality of characters. To do. Then, the character having the best score is acquired from the dictionary as the recognized character. Note that the process until individual characters included in the difference-related information are individually detected may be considered as a character recognition process.

  The result of the character recognition process acquired by the character recognition unit 15 may be, for example, text information composed of characters recognized for the difference related information as described above, or is a character in the difference related image. The number of images determined as (for example, the number of rectangular areas described above) may be used. Or the score showing the similarity etc. computed in the case of character recognition as mentioned above may be sufficient. For example, the result of the character recognition process is a score indicating the degree of similarity or the like of the character included in the dictionary for character recognition processing determined to have the highest degree of similarity with respect to each character image to be character-recognized. There may be.

  The difference-related information to be subjected to character recognition processing by the character recognition unit 15 may be difference-related information before being accumulated in the answer information storage unit 16 described later as part of the answer information, or the answer information storage unit 16 described later. The difference related information included in the answer information stored in. For example, the character recognition unit 15 may perform character recognition processing on the difference related information immediately after the difference acquisition unit 13 acquires one difference related information, or the answer stored in the answer information storage unit 16. Character recognition processing may be sequentially performed on the difference related information included in the information.

  The answer information storage unit 16 stores answer information having difference related information and student identification information. The difference related information and student identification information included in one answer information are, for example, difference related information and student identification information acquired by the difference acquisition unit 13 and the student identification information acquisition unit 14 for one answer reading information, respectively. The answer information may further include text information acquired as a result of the character recognition unit 15 performing a character recognition process on the difference related information included in the answer information. The answer information may further include information indicating a date corresponding to the answer information (hereinafter, date information). The date information (information indicating the date corresponding to the answer information) may be date information associated with the answer reading information as described above, or the answer information is accumulated in the answer information storage unit 16. Date information may also be used. The storage here is a concept including temporary storage.

  The answer information accumulating unit 17 accumulates answer information having difference-related information acquired by the difference acquiring unit 13 and student identification information acquired by the student identification information acquiring unit 14 in the answer information storage unit 16. One answer information accumulated by the answer information accumulating unit 17 is answer information having difference-related information and student identification information acquired for one answer reading information. Further, the answer information storage unit 17 stores answer information further including text information acquired as a result of the character recognition processing performed by the character recognition unit 15 on the difference related information included in the answer information in the answer information storage unit 16. May be. Further, the answer information storage unit 17 may store answer information further including date information indicating a date corresponding to the answer information as described above in the answer information storage unit 16.

  For example, the statistical analysis unit 18 performs statistical analysis on the answer information for each student using the student identification information included in the answer information stored in the answer information storage unit 16. Performing statistical analysis for each student is, for example, performing statistical analysis for each student identification information. For example, statistical analysis is performed using answer information having the same student identification information.

  Moreover, you may make it the statistical analysis part 18 perform the statistical analysis regarding answer information for every period designated beforehand using the date information which answer information has. For example, the statistical analysis unit 18 uses the answer information stored in the answer information storage unit 16 to answer information having date information indicating dates included in the period for each period (for example, year) specified in advance. And the statistical analysis is performed using the answer information for each detected period. In addition, you may make it perform the answer analysis for every student mentioned above for every period.

  Note that the statistical analysis described here may be any statistical analysis, and what kind of statistical analysis is performed is set in accordance with, for example, the purpose and application of the statistical analysis. For example, in the statistical analysis here, the information that satisfies the pre-specified conditions among the information to be statistically analyzed is aggregated for each condition, or the ratio of the aggregated results to the entire information to be statistically analyzed, etc. Is to get. In addition, for example, for information that has a value that satisfies a pre-specified condition among pieces of information subject to statistical analysis, the average value, variance, standard deviation, maximum value, minimum value, median value, etc. of the value May be obtained. The statistical analysis may be multivariate analysis such as cluster analysis. In statistical analysis, the value of information used for statistical analysis, the number of information, the result of statistical analysis, and the like may be normalized as appropriate. This also applies to the following.

  The statistical analysis unit 18 performs, for example, statistical analysis on characters described in difference-related information included in the answer information as statistical analysis on the answer information. For example, the statistical analysis unit 18 performs statistical analysis on characters using information indicating the result of the character recognition processing performed by the character recognition unit 15 on the difference related information included in the answer information. The result of the character recognition processing described here may be text information composed of characters recognized for each difference-related information as described above, or is determined to be one character in the difference-related image. The number of images that have been recognized (that is, the number of rectangular areas described above), the number of images that have been character-recognized, the number of images that have not been character-recognized, etc. Alternatively, each difference-related information may be a score representing similarity or the like for characters included in a dictionary or the like obtained in character recognition processing for each image determined to be a character.

  The statistical analysis regarding the characters described in the difference related information performed by the statistical analysis unit 18 is, for example, a statistical analysis regarding the amount of characters recognized for the difference related information in the character recognition processing by the character recognition unit 15. The amount of characters described here is, for example, the number of characters. The amount of characters may be considered as the number of words included in the text information obtained as a result of the character recognition process. Words included in the text information can be detected, for example, by performing morphological analysis. Since morphological analysis is a known technique, detailed description thereof is omitted here.

  The statistical analysis related to the amount of characters includes, for example, totaling characters that satisfy (or do not satisfy) a predetermined condition, and calculating a ratio of the total number to the total. The condition designated in advance is, for example, a condition for designating a character type. Examples of character types include kanji, hiragana, and alphabet. The predesignated condition may be a condition of all characters recognized in the character recognition process. Moreover, the average of the total number of characters that satisfy (or do not satisfy) a predetermined condition included in the plurality of answer reading information may be used. For example, the number of characters of all the characters included in the text information obtained by the character recognition processing performed for each of the plurality of difference related information corresponding to one user is totaled for each difference related information. And the average value of the total result is acquired as a statistical analysis result.

  The statistical analysis on the characters described in the difference related information performed by the statistical analysis unit 18 refers to the characters recognized by the character recognition unit 15 about the difference related information (specifically, the text information obtained as the character recognition result). This is a statistical analysis of the diversity of characters included. Character diversity may be considered as word diversity composed of characters. The diversity here is, for example, the number of unique characters (or words) among characters (or words) recognized by character recognition. For example, it is the total number obtained by counting characters and words by excluding duplicates (for example, duplicates are counted only once). Alternatively, it is the number of unique characters or words whose character type is a character type (kanji, hiragana, etc.) designated in advance among characters (or words) recognized by character recognition. The word diversity may be information indicating the number or ratio of words used in a specific group. The specific group is, for example, a group of words classified by the vocabulary difficulty level. For example, the process of acquiring what difficulty level vocabulary is included in the text information or the like can be realized by using a technique such as the following non-patent document. (Non-patent literature: Yoshiko Kawamura, "Analysis of Japanese textbooks using vocabulary checker", [online], [searched September 8, 1999], Internet <URL: http://language.tiu.ac. jp / castel99.pdf>).

  The statistical analysis regarding the characters described in the difference related information performed by the statistical analysis unit 18 is, for example, statistical analysis regarding the attributes of the characters described. Character attributes include character size and ease of character recognition.

  For example, the statistical analysis regarding the attribute of the character performed by the statistical analysis unit 18 is a statistical analysis regarding the result of the character recognition performed by the character recognition unit 15 on the difference related information. Statistical analysis related to the result of character recognition is, for example, a score indicating the degree of similarity between each character recognized in the character recognition process and an image including each character in the difference-related information that is a recognition target of these characters. It is also possible to acquire an average value, variance, etc. for one or more difference related information. Since a character with a high score is considered to be a character that can be easily recognized by character recognition, for example, a beautiful character, such a statistical analysis result indicates the cleanliness of the character. Note that obtaining the ratio of the number of characters whose score is equal to or less than a threshold value prepared in advance and the number of all recognized characters may be considered as a statistical analysis regarding the character recognition result.

  Moreover, the statistical analysis regarding the attribute of the character which the statistical analysis part 18 performs is a statistical analysis regarding the size of the recognized character which the character recognition result performed by the character recognition part 15 performed with respect to difference related information. The recognized character size may be, for example, the character size (for example, the number of points) recognized in the character recognition process. Further, in the course of the character recognition process, the vertical or horizontal length of the rectangular area set for the image including one character may be used. In the statistical analysis unit 18, for example, the statistical analysis unit 18 acquires a value obtained by counting the number of recognized characters by size, a ratio of the total value to the total number of characters, and the like as a statistical analysis result. Further, it is also possible to determine the variation in the character size by acquiring the character size variance or the like as the statistical analysis result. For example, in general, it can be determined that a character with less variation in character size is a beautiful character.

  The statistical analysis regarding the characters described in the difference-related information performed by the statistical analysis unit 18 is, for example, statistical analysis regarding the accuracy of the sentence indicated by the characters recognized by the character recognition unit 15. The character recognized by the character recognition unit 15 here is, for example, a character included in text information output as a character recognition result. Statistical analysis on sentence accuracy is, for example, typographical omission or kanji mistake in a sentence that is output as a character recognition result, that is, a sentence composed of specific characters judged from a character image of difference-related information. This is a statistical analysis of the number of occurrences of items such as mistakes in combination of particles, use of words not in the dictionary, errors in homophones, errors in syllabary, errors in punctuation, errors in idioms, etc. These statistical analyzes may be statistical analysis for each item or statistical analysis in which a plurality of items are collected. Note that the processing for detecting the location of the item as described above from the text is a well-known technique in document proofing support software, a word processor, or the like, and therefore detailed description thereof is omitted here. For example, an example is disclosed in the following non-patent documents. (Non-patent literature: "Reduced burden on proofreaders with detailed checks | Sentence proofreading tool Just Right! 4 Pro CE", [online], [searched September 8, 1999], Internet <URL: http http://www.justsystems.com/jp/products/justright/feature1.html>). Note that the statistical analysis of the sentence accuracy may be any statistical analysis that can determine the situation and tendency of the sentence accuracy. As a result, the statistical analysis of the sentence inaccuracy is also accurate. It can be considered as a form of statistical analysis of the degree.

  Moreover, the statistical analysis regarding the characters described in the difference-related information performed by the statistical analysis unit 18 is a statistical analysis regarding the number of characters per unit area of the described characters. The number of characters per unit area is, for example, the ratio of the number of characters recognized in the difference related information to the area of one difference related information (for example, the read area). The number of recognized characters may be the number of characters recognized by the character recognition unit 15 (for example, the number of characters included in the text information obtained as a result of character recognition), or in the process of character recognition by the character recognition unit 15. It may be the number of rectangular areas including one character detected in the difference related information. The number of characters here may be the number of characters having a specific attribute as described above. The number of characters per unit area is, for example, information indicating the degree to which characters are entered on the answer sheet.

  The output unit 19 outputs the statistical analysis result of the statistical analysis unit 18. The output described here means display on a display, projection using a projector, printing on a printer, transmission to an external device, storage on a recording medium, processing result to other processing devices or other programs, etc. It is a concept that includes delivery. For example, the output unit 19 may output the statistical analysis result using a graph or the like.

  The output unit 19 may be considered as including or not including an output device such as a display. The output unit 19 can be realized by driver software for an output device or driver software for an output device and an output device.

Next, operation | movement of the answer processing apparatus 1 is demonstrated using the flowchart of FIG.
It is assumed that the answer sheet information obtained for the same answer sheet and the answer reading information are associated in advance with the same answer sheet identification information (hereinafter referred to as answer sheet identification information). Also, it is assumed that the answer sheet information and the answer reading information are associated with information on the date on which the answer was written by the student.

  (Step S <b> 101) The difference acquisition unit 13 determines whether or not the answer reading information that has not been processed for acquiring the difference related information is accumulated in the answer reading information storage unit 11. If so, the process proceeds to step S102. If not, the process proceeds to step S111. For example, for the answer reading information from which the difference acquisition unit 13 has acquired the difference related information, a flag indicating that the answer has been processed is given, and the presence or absence of the unprocessed answer reading information is determined based on the presence or absence of this flag. be able to. Alternatively, the processed answer reading information may be deleted.

  (Step S102) The difference acquisition unit 13 assigns 1 to the counter m.

  (Step S <b> 103) The difference acquisition unit 13 determines whether or not there is m-th answer reading information in the answer reading information that has not been acquired for the difference related information. If there is, the process proceeds to step S104, and if not, the process proceeds to step S111.

  (Step S104) The difference acquisition unit 13 acquires answer sheet information corresponding to the mth answer reading information from the answer sheet information storage unit 12. For example, answer sheet information associated with the same answer sheet identification information as the answer sheet identification information associated with the mth answer reading information is acquired.

  (Step S105) The difference acquisition unit 13 acquires difference-related information that is a difference of the mth answer reading information with respect to the answer sheet information. In addition, you may acquire what performed processes, such as a sharpness process, with respect to a difference as difference relevant information. Further, when obtaining the difference related information, the vicinity of the region where the identification image information is arranged may be excluded in advance from the target region from which the difference is obtained. Note that a flag indicating that the process of acquiring the difference related information has been processed is added to the mth answer reading information.

  (Step S106) The character recognition part 14 performs a character recognition process with respect to the difference relevant information acquired in step S105. Then, for example, text information composed of a character string specified by character recognition is acquired as information indicating a character recognition result. Here, for example, information indicating a score for each character when the character is recognized is acquired. It is assumed that the text information includes character size information and the like.

  (Step S107) The student identification information acquisition unit 14 detects an identification image from the mth answer reading information.

  (Step S108) The student identification information acquisition unit 14 reads the identification image information detected in step S107, and acquires student identification information.

  (Step S109) The answer information storage unit 17 obtains the difference-related information acquired in Step S105, the student identification information acquired in Step S108, and the character recognition result acquired in Step S106 (here, the text information and the score for each character). ) And date information that is date information associated with the m-th answer reading information is stored in the answer information storage unit 16.

  (Step S110) The difference acquisition unit 13 increments the value of the counter m by 1. Then, the process returns to step S103.

  (Step S111) The statistical analysis unit 18 determines whether or not to perform statistical analysis. For example, when an instruction to perform statistical analysis is received by a user or the like via a reception unit (not shown), it is determined that statistical analysis is to be performed. When performing statistical analysis, it progresses to step S112, and when not receiving, it returns to step S101.

  (Step S112) The statistical analysis unit 18 determines whether information specifying one or more periods to be analyzed has been received from the user via a reception unit (not shown) or the like. The period here is, for example, a year or a fiscal year. If accepted, the process proceeds to step S113. If not accepted, the process returns to step S112.

  (Step S113) The statistical analysis unit 18 substitutes 1 for the counter n.

  (Step S114) The statistical analysis unit 18 determines whether or not the answer information stored in the answer information storage unit 16 includes the nth student identification information. If there is, the process proceeds to step S115, and if not, the process proceeds to step S120.

  (Step S115) The statistical analysis unit 18 substitutes 1 for the counter k.

  (Step S116) The statistical analysis unit 18 determines whether or not the kth period is specified in the period specified in step S112. If yes, the process proceeds to step S117. If not, the process proceeds to step S119.

  (Step S117) The statistical analysis unit 18 performs statistical processing. Details of this processing will be described later.

  (Step S118) The statistical analysis unit 18 increments the value of the counter k by 1. Then, the process returns to step S116.

  (Step S119) The statistical analysis unit 18 increments the value of the counter n by 1. Then, the process returns to step S114.

  (Step S120) The output unit 19 outputs the result of statistical processing acquired by the statistical analysis unit 18. Then, the process ends.

  Note that the statistical analysis unit 18 may accept student identification information to be statistically analyzed before and after step S112. Then, the statistical analysis unit 18 may perform the process of step S114 on the received student identification information.

  Next, the detailed operation of the statistical processing by the answer processing apparatus 1 will be described with reference to the flowchart of FIG. This process is an example of the detailed operation of step S117 described above.

  (Step S201) The statistical analysis unit 18 increments the value of the counter p by 1.

  (Step S202) The statistical analysis unit 18 determines whether there is p-th answer information having n-th student identification information and date information indicating a date included in the k-th period. If there is, the process proceeds to step S203; otherwise, the process proceeds to step S210.

  (Step S203) The statistical analysis unit 18 acquires information indicating the amount of characters using information (for example, text information) indicating a character recognition processing result included in the p-th answer information. For example, the number of recognized characters is acquired. The acquired information is stored, for example, in a storage medium (not shown) in association with the p-th answer information.

  (Step S204) The statistical analysis unit 18 acquires information indicating character diversity using information indicating the character recognition processing result included in the p-th answer information. For example, the number of unique words included in the character recognition processing result is acquired. The number of unique words is the number of words when duplicate words are counted as one word. The acquired information is stored, for example, in a storage medium (not shown) in association with the p-th answer information.

  (Step S205) The statistical analysis unit 18 acquires information related to the result of the character recognition process included in the p-th answer information. For example, the statistical analysis unit 18 uses the score of each character when character recognition is performed to obtain the average value of the score of the character recognized. The acquired information is stored, for example, in a storage medium (not shown) in association with the p-th answer information.

  (Step S206) The statistical analysis unit 18 uses the information indicating the character recognition processing result included in the p-th answer information to obtain a value related to the character size. For example, the average value of the character sizes is acquired using the character size values of a plurality of characters included in the character recognition processing result. The acquired information is stored, for example, in a storage medium (not shown) in association with the p-th answer information.

  (Step S207) The statistical analysis unit 18 acquires a value related to the accuracy of the character by using information indicating the character recognition processing result included in the p-th answer information. For example, the number of typographical errors is acquired using a plurality of characters included in the character recognition processing result. The acquired information is stored, for example, in a storage medium (not shown) in association with the p-th answer information.

  (Step S208) The statistical analysis unit 18 acquires the number of characters per unit area using information indicating the character recognition processing result included in the p-th answer information. For example, the number of characters indicated by the character recognition processing result is divided by the size (area) of the answer reading information corresponding to the p-th answer information or the size of the difference-related information included in the p-th answer information. Get the number of characters. The acquired information is stored, for example, in a storage medium (not shown) in association with the p-th answer information.

  (Step S209) The statistical analysis unit 18 increments the value of the counter p by 1. Then, the process returns to step S202.

  (Step S210) The statistical analysis unit 18 uses the information acquired in steps S203 to S208 for p pieces of answer information, and acquires an average value for each value acquired in each step as a statistical analysis result. Instead of obtaining the average value, values relating to other statistical processes, such as variance and standard deviation, may be obtained.

  (Step S211) The statistical analysis unit 18 stores the statistical analysis result acquired in Step S210 in a storage medium or the like (not shown) in association with the nth student identification information and the information indicating the kth period. Then, the process returns to the upper process.

  Hereinafter, a specific operation of the answer processing apparatus 1 in the present embodiment will be described.

  For example, each student at a school is provided with a sticker 20 with an identification image 21 associated with the student identification information of each student, as shown in FIG. 2, and each student takes a test. At this time, it is assumed that this sticker is affixed to a predetermined area of the answer sheet. Here, the student identification information is assumed to be a student name as an example. The identification image 21 is assumed to be a QR code, which is one of two-dimensional barcodes, as an example here. As shown in FIG. 2, it is assumed that characters indicating the student identification information 22 are written near the lower side of the identification image 21.

  Here, for example, every time a test is performed on a student, the answer sheet used for the test and the answer sheet on which the student wrote the answer in the test are collected, and these answer sheets are collected by a teacher or the like. It is assumed that the image information is converted into image information using a scanner or the like (not shown) and accumulated in the answer sheet information storage unit 12 and the answer reading information storage unit 11. Also, here, as an example, when storing the answer reading information, information on the date on which the test was performed is stored in association with the answer sheet information obtained for the answer sheet used in the one test. And the answer reading information are stored in association with the above-mentioned answer sheet identification information (hereinafter referred to as answer sheet identification information) input by a teacher or the like via a reception unit (not shown). And

  FIG. 5 is a diagram (FIG. 5 (a)) showing answer sheet information 51 obtained by reading the entry surface of the answer sheet used in the above-described test that the student receives with a scanner or the like (not shown). The figure which shows an example of the answer reading information 52 which read the answer side of the answer sheet which each student wrote the answer with the scanner etc. (not shown) with respect to the same answer sheet as this answer sheet (FIG.5 (b)). It is. The answer sheet corresponding to the answer sheet information 51 in FIG. 5A is an answer sheet in which no answer is entered. This answer sheet may be considered as a sample or original of the answer sheet. In addition, on the answer sheet on which the student corresponding to the answer reading information 52 in FIG. 5B has entered the answer, the student's seal 20 on which the answer is written is placed in a frame 501 which is a predesignated area by the student. It shall be affixed.

  FIG. 6 is an answer sheet information management table for managing answer sheet information stored in the answer sheet information storage unit 12. The answer sheet information management table has items of “answer sheet information” and “answer sheet ID”. “Answer sheet information” indicates the file name of the answer sheet information. “Answer sheet ID” is answer sheet identification information associated with the answer sheet information. The “answer sheet ID” associated with the answer sheet information shown in FIG. 5A is assumed to be “K2011-101”. Note that the “answer sheet information” and the “answer sheet ID” may be set as one item by using the file name of the answer sheet information as the answer sheet identification information.

  FIG. 7 is a diagram showing an answer reading information management table for managing answer reading information stored in the answer reading information storage unit 11. The answer reading information management table has items of “answer reading information”, “answer sheet ID”, “date”, and “processed”. “Answer reading information” indicates a file name of answer reading information. The “answer sheet ID” is answer sheet identification information associated with the answer reading information, and corresponds to the “answer sheet ID” in FIG. “Date” is the date on which the test corresponding to the answer reading information was performed. “Processed” is flag information indicating whether or not the answer reading information has been processed to acquire the difference related information. The value “0” is unprocessed and the value “1” is processed. It shows that.

  Next, if a user such as a teacher activates the answer processing apparatus 1 to perform statistical analysis on the test, the difference acquisition unit 13 performs a process of acquiring difference related information in the answer reading information storage unit 11. It is determined whether there is unprocessed answer reading information. Here, it is determined whether or not the answer reading information shown in FIG. 7 has a “processed” value of “0”. Here, it is assumed that there is a record whose “processed” value is “0”. However, the trigger and timing of the start of judgment are not questioned.

  Since there is unprocessed answer reading information, the difference acquisition unit 13 sequentially reads the unprocessed answer reading information and acquires the difference related information. For example, first, the answer reading information whose file name is “01000125.tif” is read out from the first record (row) of the answer reading information management table shown in FIG. That is, the answer reading information shown in FIG. Also, answer sheet identification information corresponding to this answer reading information, specifically, “K2011-001”, which is the value of “answer sheet ID” of the same record, is read out from the answer sheet information management table shown in FIG. , Answer sheet information in which “answer sheet ID” is associated with “K2011-001”, specifically, answer sheet information with the file name “100545.tif” is acquired. That is, the answer sheet information shown in FIG.

  The difference acquisition unit 13 acquires an image of the difference between the answer reading information with the file name “01000125.tif” read out above and the answer sheet information with the file name “100545.tif”. That is, an image of the difference between the answer reading information shown in FIG. 5B and the answer sheet information shown in FIG. 5A is acquired. For example, the pixels having the same color information (or gradation information) among the pixels at the overlapping coordinates are deleted. However, here, it may be considered that there is a difference in color information within a range specified in advance. Further, instead of deleting a pixel, it may be changed to a pixel of a color designated in advance (for example, white). Here, as an example, for the area in the frame 501 for applying the seal 20 as described above, the coordinates indicating the area are indicated in advance, and the difference image is acquired. The image within this frame 501 is deleted from the difference image so that it is not included. Then, the difference-related information is obtained by appropriately performing sharpness processing, level correction processing, and the like on the difference image. Thereby, the difference related information which is an image showing only the answer written by the student is obtained. Note that the difference image may be acquired as the difference related information as it is. Further, the difference acquisition unit 13 acquires “2011/5/25”, which is date information associated with the answer reading information “01000125.tif”, as date information. Further, the difference acquisition unit 13 changes the value of “acquired” of the record including the answer reading information “01000125.tif” that acquired the difference related information to “1” in the answer reading information management table.

  FIG. 8 is a diagram illustrating an example of the difference related information acquired by the difference acquisition unit 13. For example, a file name or the like is given to the acquired difference related information according to a rule or the like designated in advance, and is temporarily stored in a storage medium (not shown) or the like. Here, it is assumed that the file name “500001.tif” is given.

  Next, the student identification information acquisition unit 14 detects the identification image 21 in the frame 501 of the answer sheet information whose file name is “100545.tif”. The identification image 21 can usually be detected by detecting an image having a specific shape provided at a corner or the like of the identification image 21 by pattern matching or the like. Here, the QR code which is the identification image 21 on the seal 20 is detected. Then, the identification image 21 is read out, and student identification information associated with the read out identification image 21 is acquired. Here, for example, it is assumed that the student identification information “Yamada A male” is acquired.

  Next, the character recognition part 15 performs a character recognition process with respect to the difference relevant information shown in FIG. Specifically, OCR processing is performed. For example, in the difference-related information shown in FIG. 8, a block of pixels considered as one character is sequentially detected, and a rectangular area surrounding each block is set.

  Next, information indicating the characteristics of the character image included in each rectangular area is acquired, and a character image included in each rectangular area and a character dictionary for character recognition processing (not shown) prepared in advance. The score indicating the degree of similarity with each character included in each rectangular area is acquired for each rectangular area, and the character having the highest score in each rectangular area is acquired as the recognized character for the rectangular area. . And the text information which has arrange | positioned the recognized character in the vicinity of the recognized position etc. is acquired as a character recognition result. The file name of the text information is given by, for example, a rule designated in advance. Here, for example, it is assumed that the file name “500001.rtf” is given. In addition, here, the recognition management table, which is information obtained by associating the score obtained during the character recognition processing of the recognized character and the information on the size of the recognized character for each recognized character, is also used as the character recognition result. get. The file name of the recognition management table is given by, for example, a rule designated in advance. Here, for example, it is assumed that a file name “500001.csv” is given.

  FIG. 9 is a diagram showing text information acquired as a result of character recognition by the character recognition unit 15 (FIG. 9A), each recognized character, a score at the time of character recognition processing, and a character size. It is a figure (FIG.9 (b)) which shows the recognition management table which matches and manages this information. The recognition management table includes items of “recognized character” indicating the recognized character, “score” that is the score of the recognized character, and “size” that is the size of the recognized character. Here, for example, the recognition management table is created for each difference related information. However, one recognition management table may be prepared for a plurality of pieces of difference related information, and identification information of the difference related information may be associated with a record corresponding to each difference related information.

  The answer information storage unit 17 includes difference-related information whose file name acquired by the difference acquisition unit 13 is “500001.tif”, student identification information “Yamada A male” acquired by the student identification information acquisition unit 14, and an answer sheet The identification information “K2011-001”, the text information “500001.rtf” obtained as a result of the character recognition process, the recognition management table “50,0001.csv” obtained as a result of the character recognition process, and the difference acquisition unit 13 The answer information having the date information “2011/5/25” acquired by is stored in the answer information storage unit 16.

  In the same manner, the answer information is accumulated (added) by repeating the same process for answer reading information whose difference related information has not been processed. When accumulating, it is determined whether or not answer information whose student identification information value matches the answer sheet identification information value is already accumulated. Since the same student's answer information for will be double-registered, a warning that double-registration is done, a warning that there is a possibility of some fraud, etc. should be output to the user etc. Anyway.

  FIG. 10 is a diagram showing an answer information management table for managing answer information stored in the answer information storage unit 16. The answer information management table includes “answer ID”, “difference related information”, “student ID”, “answer sheet ID”, “recognition text”, “recognition management table”, and “date information”. Have items. The “answer ID” is identification information of answer information. Here, as an example, the “answer ID” is obtained by removing the extension from the file name of the difference related information included in the answer information. However, it does not matter according to what rule the “answer ID” is given. “Difference related information” is the file name of the difference related information. “Student ID” is student identification information. “Answer sheet ID” is answer sheet identification information and corresponds to the “answer sheet ID” in FIGS. 6 and 7. “Recognized text” is text information obtained by character recognition processing. The “recognition management table” is a recognition management table obtained by character recognition processing. “Date information” is date information acquired by the difference acquisition unit 13. The answer information acquired above for the answer reading information “01000125.tif” is a record whose “difference related information” is “500001.tif”.

  Next, if a user such as a teacher gives an instruction to perform statistical analysis on the answer information acquired above to the answer processing apparatus 1 via a reception unit (not shown), the answer processing apparatus 1 performs statistical analysis. An interface screen (not shown) for accepting an instruction for designating a target period is displayed on a monitor or the like (not shown). Then, it is assumed that the user gives an instruction to the answer processing apparatus 1 to perform statistical analysis for each year in the period from 2008 to 2011 by operating this interface screen.

  Upon receipt of this instruction, the statistical analysis unit 18 first sequentially reads out the value of “student ID” from each record of the answer information management table of FIG. 10 and temporarily accumulates (adds to) a storage medium (not shown). To go. At this time, if the same “student ID” has already been accumulated, duplicate accumulation is not performed. In this way, a list of unique student identification information about the student who submitted the answer sheet is obtained.

Next, the statistical analysis unit 18 acquires one piece of student identification information from the acquired list of student identification information. Here, for example, it is assumed that the student identification information “Yamada A male” is acquired. In addition, the statistical analysis unit 18 acquires information indicating one year within the period specified above, for example, “2011”. In the answer information management table shown in FIG. 10, the “student ID” is “Yamada A male” and the value of “date information” is changed from “2011/1/1” to “2011/12/31”. Search for one of the records (answer information) that matches any of the date values up to. Here, for example, it is assumed that a record whose “answer ID” is “500001” is detected.
In addition, when the information indicating the above year is handled as the information of the year and "2011" is acquired as the information indicating the year, the start date and end date of the year such as an elementary school or a junior high school are considered, The statistical analysis unit 18 records that the value of “date information” matches the value of any date from “2011/4/1” to “2012/3/31” in the range indicating the 2011 fiscal year (answer) Information) may be searched. That is, the beginning of the year may be “April 1” of the designated year, and the last of the year may be “March 31” of the year following the designated year.

  First, the statistical analysis unit 18 acquires the number of characters as the amount of “recognized text” characters managed in the retrieved record. For example, here, the number of characters is counted for the recognized text “50001.rtf”. Assume that the count result is “124”, for example. The statistical analysis unit 18 accumulates this value in, for example, a storage medium (not shown) in association with the answer ID “500001”.

  Next, the statistical analysis unit 18 acquires a value indicating character diversity for the recognized text “50001.rtf” managed by the record searched above. Here, as an example, the number of unique words is acquired as a value indicating character diversity. For example, morphological analysis is performed on the text information of the recognized text “50001.rtf” shown in FIG. 9A, and the text information is divided into words. Then, the number of unique words is obtained by counting the divided words so that duplicated words are counted only once. It is assumed that the number of unique words acquired here is “53”. The statistical analysis unit 18 accumulates this value in, for example, a storage medium (not shown) in association with the answer ID “500001”.

  Next, the statistical analysis unit 18 uses the recognition management table “500001.csv” managed by the record searched above to acquire a value related to the result of the character recognition process. Here, as an example, the score acquired in the character recognition process is acquired for each character that has been character-recognized, and the average value of these is acquired. For example, by adding the “score” values of all the records in the recognition management table “500001.csv” shown in FIG. 9B and dividing the added value by the total number of records, the average score value is obtained. get. It is assumed that the acquired average value is “71”, for example. The statistical analysis unit 18 accumulates this value in, for example, a storage medium (not shown) in association with the answer ID “500001”.

  Next, the statistical analysis unit 18 acquires a value relating to the size of the character recognized in the character recognition process, using the recognition management table “500001.csv” managed by the record searched above. Here, for example, the size of each character that has been character-recognized is acquired, and the average value thereof is acquired. For example, the average value of the character size is obtained by adding the values of “size” of all the records in the recognition management table “500001.csv” shown in FIG. 9B and dividing the added value by the total number of records. To get. It is assumed that the acquired average value is “15.8” (points), for example. The statistical analysis unit 18 accumulates this value in, for example, a storage medium (not shown) in association with the answer ID “500001”.

  Next, the statistical analysis unit 18 acquires a value related to the accuracy of the character for the recognized text “50001.rtf” managed by the record searched above. Here, as an example, the number of typographical errors is acquired as a value related to the accuracy of the character. That is, if the number of typographical errors is small, it indicates that the accuracy of the sentence written by the student is high. For example, a process of detecting a typographical error is performed on the text information of the recognized text “50,0001.rtf” shown in FIG. 9A to detect a typographical error. Then, the number of detected typographical errors is counted. Then, normalization is performed by dividing the counted number of typographical errors by the number of characters of the text information acquired above. It is assumed that the number of normalized typographical omissions obtained in this way is “5”. The statistical analysis unit 18 accumulates this value in, for example, a storage medium (not shown) in association with the answer ID “500001”.

  Next, the statistical analysis unit 18 acquires a value indicating the number of characters per unit area for the recognized text “50,0001.rtf” included in the record searched above. For example, the number of characters per unit area is acquired by dividing the number of characters of the recognized text acquired above by the area of the difference related information. For example, if the size of the difference-related information is 7 inches high and 12 inches wide, the number of characters per unit area (here per square inch) is 124 (characters) / 84 = “1.48” characters. It becomes. The statistical analysis unit 18 accumulates this value in, for example, a storage medium (not shown) in association with the answer ID “500001”.

  As a result, the process for the answer information in which the “student ID” is “Yamada A male” and the “answer ID” is “500001” is completed.

  Further, the statistical analysis unit 18 also determines the remaining records (answer information) in which the “student ID” is “Yamada A male” and the first four characters of the “date information” match “2011”. The same processing as above is repeated.

  As a result, the processing for the answer sheet submitted by the student whose “student ID” is “Yamada A male” in “2011” is completed.

  FIG. 11 is a diagram showing yearly acquired information which is the information acquired by the statistical analysis unit 18 in the above-described process for the answer sheet submitted by the student whose “student ID” is “Yamada A male” in “2011”. It is. This information is information accumulated in a storage medium value (not shown) by the above processing. The yearly acquisition information includes items of “answer ID”, “number of characters”, “number of words”, “average score”, “average size”, “number of typographical errors”, and “number of unit characters”. doing. “Number of characters” is the number of characters included in the text information that is the character recognition result, “Number of words” is the number of unique words included in the text information that is the character recognition result, and “Average score” is the number of characters in the character recognition process. The average value of the acquired scores, the average value of the character size recognized in the “average size” character recognition process, the “number of typographical errors” is the normalized number of typographical errors included in the text information that is the character recognition result, “ “Number of unit characters” is the number of characters per unit area in the difference-related information.

  Next, the statistical analysis unit 18 acquires an average value of the values for each item illustrated in FIG. Specifically, the values of the same item in all records are added together, and the added value is divided by the number of records to obtain the average value of each item. This average value is the average value of each item regarding the answer sheet submitted in “2011” by the student whose “student ID” is “Yamada A male”. The student whose “student ID” is “Yamada A male” may be considered as a statistical analysis result of the answer sheet submitted in “2011”. Then, the acquired average value of each item is stored as a statistical analysis result in a storage medium (not shown) in association with the student identification information “Yamada A male” and the value “2011” indicating the year.

  Similarly, the statistical analysis unit 18 performs the same processing for each year from “2010” to “2008”, which are the remaining years.

  FIG. 12 is an annual analysis result management table showing the statistical analysis results of each year acquired and accumulated by the above processing. “Year” indicates the year of statistical analysis. The items of “answer ID”, “number of characters”, “number of words”, “average score”, “average size”, “number of misspelled characters”, and “number of unit characters” are the same names shown in FIG. This is the average value of the items.

  Further, the statistical analysis unit 18 performs the same processing as above for the student identification information other than “Yamada A male” in the list of student identification information acquired above, and the information obtained by the processing is shown in FIG. We will add to the annual analysis results shown in.

  FIG. 13 shows an annual analysis result management table in which statistical analysis results for student identification information other than “Yamada A male” are added.

  Then, the output unit 19 displays the statistical analysis result as shown in FIG. 13 on a monitor or the like (not shown). Needless to say, the whole or part of the statistical analysis result shown in FIG. 13 may be displayed in a graph or the like.

  As described above, according to the present embodiment, the difference-related information regarding the difference between the answer reading information obtained by reading the answer sheet in which the student has entered the answer and the answer sheet information of the answer sheet before the student has entered the answer is acquired. Since the answer information having the difference related information and the student identification information read from the identification image arranged on the answer sheet is accumulated, the answer written by the student can be managed appropriately.

  In addition, various statistical analyzes can be performed using information obtained by character recognition processing of the difference-related information, and the student's answer can be effectively used for various purposes such as evaluation of the student's growth process.

  In each of the above embodiments, each process (each function) may be realized by centralized processing by a single device (system), or by distributed processing by a plurality of devices. May be.

  Further, although cases have been described with the above embodiments where the answer processing apparatus is a stand-alone, the answer processing apparatus may be a stand-alone apparatus or a server apparatus in a server / client system. In the latter case, the output unit or the reception unit receives an input or outputs a screen via a communication line.

  In each of the above embodiments, each component such as the difference acquisition unit 13, the student identification information acquisition unit 14, the character recognition unit 15, the answer information storage unit 17, and the statistical analysis unit 18 is configured by dedicated hardware. Alternatively, it may be configured by software and realized by executing a program. For example, each component can be realized by a program execution unit such as a CPU reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

  The software that realizes the answer processing apparatus in each of the above embodiments is a program as described below. In other words, this program is an answer sheet on which one or more students have written answers, and an identification image that is image information associated with student identification information that is identification information of each student who has entered the answer. This is information indicating a state before answer is written in an answer reading information storage unit for storing answer reading information, which is information obtained by reading an arranged answer sheet, and an answer sheet from which answer reading information is read. A computer that can access the answer sheet information storage unit in which answer sheet information is stored and the answer information storage unit, and information on the difference between the answer reading information stored in the answer reading information storage unit and the answer sheet information. A difference acquisition unit that acquires certain difference related information, and a student that detects the identification image of the answer reading information from which the difference acquisition unit has acquired the difference, and acquires the student identification information associated with the identification image For functioning as an answer information accumulating unit for accumulating in the answer information storage unit answer information having another information acquisition unit, difference-related information acquired by the difference acquisition unit, and student identification information acquired by the student identification information acquisition unit It is a program.

  In the program, the functions realized by the program do not include functions that can be realized only by hardware. For example, a function that can be realized only by hardware such as a modem or an interface card in an acquisition unit that acquires information or an output unit that outputs information is not included in the function realized by the program.

  Further, the computer that executes this program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

  FIG. 14 is a schematic diagram showing an example of the external appearance of a computer that executes the program and realizes the answer processing apparatus according to the embodiment. The above-described embodiment can be realized by computer hardware and a computer program executed on the computer hardware.

  14, a computer system 900 includes a computer 901 including a CD-ROM (Compact Disk Read Only Memory) drive 905 and an FD (Floppy (registered trademark) Disk) drive 906, a keyboard 902, a mouse 903, a monitor 904, and the like. Is provided.

  FIG. 15 is a diagram showing an internal configuration of the computer system 900. In FIG. 15, in addition to the CD-ROM drive 905 and the FD drive 906, a computer 901 is connected to an MPU (Micro Processing Unit) 911, a ROM 912 for storing a program such as a bootup program, and the MPU 911. A RAM (Random Access Memory) 913 that temporarily stores program instructions and provides a temporary storage space, a hard disk 914 that stores application programs, system programs, and data, and an MPU 911 and a ROM 912 are interconnected. And a bus 915. The computer 901 may include a network card (not shown) that provides connection to the LAN.

  A program for causing the computer system 900 to execute the functions of the answer processing apparatus according to the above-described embodiment is stored in the CD-ROM 921 or FD 922, inserted into the CD-ROM drive 905 or FD drive 906, and stored in the hard disk 914. May be forwarded. Instead, the program may be transmitted to the computer 901 via a network (not shown) and stored in the hard disk 914. The program is loaded into the RAM 913 when executed. The program may be loaded directly from the CD-ROM 921, the FD 922, or the network.

  The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 901 to execute the functions of the answer processing apparatus according to the above-described embodiment. The program may include only a part of an instruction that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 900 operates is well known and will not be described in detail.

  The present invention is not limited to the above-described embodiments, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

  As described above, the answer processing apparatus according to the present invention is suitable as an apparatus for processing an answer sheet, and is particularly useful as an apparatus for processing an answer sheet in which a student enters an answer from an answer sheet. .

DESCRIPTION OF SYMBOLS 1 Answer processing apparatus 11 Answer reading information storage part 12 Answer sheet information storage part 13 Difference acquisition part 14 Student identification information acquisition part 15 Character recognition part 16 Answer information storage part 17 Answer information storage part 18 Statistical analysis part 19 Output part 20 Seal 21 Identification image 22 Character string 51 Answer sheet information 52 Answer reading information

Claims (11)

An answer sheet on which one or more students have written an answer, and an answer sheet on which an identification image that is image information associated with student identification information that is identification information of each student who has entered the answer is arranged An answer reading information storage unit in which answer reading information which is read image information is stored;
Answer sheet information that is the image information indicating the state before the answer is written in the answer sheet from which the answer reading information is read, and that stores two or more answer sheet information associated with the answer reading information A storage unit;
For the answer reading information that is image information stored in the answer reading information storage unit, a difference from the answer sheet information stored in the answer sheet information storage unit that is image information corresponding to the answer reading information is acquired. A difference acquisition unit that acquires difference-related information that is difference image information;
A student identification information acquisition unit that detects an identification image of the answer reading information from which the difference has been acquired and acquires student identification information associated with the identification image;
An answer information storage unit in which answer information having the difference-related information and the student identification information is stored;
An answer information accumulating unit for accumulating answer information having difference-related information acquired by the difference acquiring unit and student identification information acquired by the student identification information acquiring unit in the answer information storing unit ;
A character recognition unit that performs character recognition processing on the difference-related information acquired by the difference acquisition unit;
Using the student identification information included in the answer information stored in the answer information storage unit, the answer information includes a statistical analysis on the characters described in the difference related information included in the answer information for each student. A statistical analysis unit that uses information indicating a result of character recognition processing performed by the character recognition unit on the difference-related information; and
An output unit for outputting a statistical analysis result of the statistical analysis unit,
The statistical analysis on the characters described in the difference related information is an answer processing device that is a statistical analysis on the amount of characters of a character type designated in advance among the characters recognized by the character recognition unit for the difference related information. . An answer sheet on which one or more students have written an answer, and an answer sheet on which an identification image that is image information associated with student identification information that is identification information of each student who has entered the answer is arranged An answer reading information storage unit in which answer reading information which is read image information is stored;
Answer sheet information that is the image information indicating the state before the answer is written in the answer sheet from which the answer reading information is read, and that stores two or more answer sheet information associated with the answer reading information A storage unit;
For the answer reading information that is image information stored in the answer reading information storage unit, a difference from the answer sheet information stored in the answer sheet information storage unit that is image information corresponding to the answer reading information is acquired. A difference acquisition unit that acquires difference-related information that is difference image information;
A student identification information acquisition unit that detects an identification image of the answer reading information from which the difference has been acquired and acquires student identification information associated with the identification image;
An answer information storage unit in which answer information having the difference-related information and the student identification information is stored;
An answer information accumulating unit for accumulating answer information having difference-related information acquired by the difference acquiring unit and student identification information acquired by the student identification information acquiring unit in the answer information storing unit;
A character recognition unit that performs character recognition processing on the difference-related information acquired by the difference acquisition unit;
Using the student identification information included in the answer information stored in the answer information storage unit, the answer information includes a statistical analysis on the characters described in the difference related information included in the answer information for each student. A statistical analysis unit that uses information indicating a result of character recognition processing performed by the character recognition unit on the difference-related information; and
An output unit for outputting a statistical analysis result of the statistical analysis unit,
The statistical analysis on the characters described in the difference related information is classified by the number of unique characters or words among the characters recognized by the character recognition unit for the difference related information, or the lexical difficulty level. An answer processing apparatus that is a statistical analysis of the number or ratio of words that belong to a specific group among a group of words. An answer sheet on which one or more students have written an answer, and an answer sheet on which an identification image that is image information associated with student identification information that is identification information of each student who has entered the answer is arranged An answer reading information storage unit in which answer reading information which is read image information is stored;
Answer sheet information that is the image information indicating the state before the answer is written in the answer sheet from which the answer reading information is read, and that stores two or more answer sheet information associated with the answer reading information A storage unit;
For the answer reading information that is image information stored in the answer reading information storage unit, a difference from the answer sheet information stored in the answer sheet information storage unit that is image information corresponding to the answer reading information is acquired. A difference acquisition unit that acquires difference-related information that is difference image information;
A student identification information acquisition unit that detects an identification image of the answer reading information from which the difference has been acquired and acquires student identification information associated with the identification image;
An answer information storage unit in which answer information having the difference-related information and the student identification information is stored;
An answer information accumulating unit for accumulating answer information having difference-related information acquired by the difference acquiring unit and student identification information acquired by the student identification information acquiring unit in the answer information storing unit;
A character recognition unit that performs character recognition processing on the difference-related information acquired by the difference acquisition unit;
Using the student identification information included in the answer information stored in the answer information storage unit, the answer information includes a statistical analysis on the characters described in the difference related information included in the answer information for each student. A statistical analysis unit that uses information indicating a result of character recognition processing performed by the character recognition unit on the difference-related information; and
An output unit for outputting a statistical analysis result of the statistical analysis unit,
The statistical analysis on the characters described in the difference-related information is statistical analysis on the character recognition result performed by the character recognition unit on the difference-related information, and each character recognized in the character recognition process , The average value of the scores indicating the degree of similarity with the image including each character in the difference-related information that is the recognition target of these characters, the variance of the scores indicating the degree of similarity, or the number of characters where the score indicating the degree of similarity is less than or equal to the threshold And an answer processing device that obtains the ratio of the number of all characters recognized. An answer sheet on which one or more students have written an answer, and an answer sheet on which an identification image that is image information associated with student identification information that is identification information of each student who has entered the answer is arranged An answer reading information storage unit in which answer reading information which is read image information is stored;
Answer sheet information that is the image information indicating the state before the answer is written in the answer sheet from which the answer reading information is read, and that stores two or more answer sheet information associated with the answer reading information A storage unit;
For the answer reading information that is image information stored in the answer reading information storage unit, a difference from the answer sheet information stored in the answer sheet information storage unit that is image information corresponding to the answer reading information is acquired. A difference acquisition unit that acquires difference-related information that is difference image information;
A student identification information acquisition unit that detects an identification image of the answer reading information from which the difference has been acquired and acquires student identification information associated with the identification image;
An answer information storage unit in which answer information having the difference-related information and the student identification information is stored;
An answer information accumulating unit for accumulating answer information having difference-related information acquired by the difference acquiring unit and student identification information acquired by the student identification information acquiring unit in the answer information storing unit;
A character recognition unit that performs character recognition processing on the difference-related information acquired by the difference acquisition unit;
Using the student identification information included in the answer information stored in the answer information storage unit, the answer information includes a statistical analysis on the characters described in the difference related information included in the answer information for each student. A statistical analysis unit that uses information indicating a result of character recognition processing performed by the character recognition unit on the difference-related information; and
An output unit for outputting a statistical analysis result of the statistical analysis unit,
The answer processing apparatus, in which the statistical analysis related to the characters described in the difference related information is a statistical analysis related to the size of the recognized character indicated by the character recognition result performed by the character recognition unit on the difference related information. The statistical analysis on the size of the character may include a value obtained by aggregating the number of recognized characters by size, a ratio of a value obtained by aggregating the number of recognized characters by size to the total number of characters, or the recognized character size. The answer processing apparatus according to claim 4, wherein the answer distribution is obtained. An answer sheet on which one or more students have written an answer, and an answer sheet on which an identification image that is image information associated with student identification information that is identification information of each student who has entered the answer is arranged An answer reading information storage unit in which answer reading information which is read image information is stored;
Answer sheet information that is the image information indicating the state before the answer is written in the answer sheet from which the answer reading information is read, and that stores two or more answer sheet information associated with the answer reading information A storage unit;
For the answer reading information that is image information stored in the answer reading information storage unit, a difference from the answer sheet information stored in the answer sheet information storage unit that is image information corresponding to the answer reading information is acquired. A difference acquisition unit that acquires difference-related information that is difference image information;
A student identification information acquisition unit that detects an identification image of the answer reading information from which the difference has been acquired and acquires student identification information associated with the identification image;
An answer information storage unit in which answer information having the difference-related information and the student identification information is stored;
An answer information accumulating unit for accumulating answer information having difference-related information acquired by the difference acquiring unit and student identification information acquired by the student identification information acquiring unit in the answer information storing unit;
A character recognition unit that performs character recognition processing on the difference-related information acquired by the difference acquisition unit;
Using the student identification information included in the answer information stored in the answer information storage unit, the answer information includes a statistical analysis on the characters described in the difference related information included in the answer information for each student. A statistical analysis unit that uses information indicating a result of character recognition processing performed by the character recognition unit on the difference-related information; and
An output unit for outputting a statistical analysis result of the statistical analysis unit,
The answer processing apparatus, wherein the statistical analysis related to the characters described in the difference-related information is a statistical analysis related to the accuracy of a sentence indicated by the characters recognized by the character recognition unit. Statistical analysis on the accuracy of the sentence is that the characters recognized by the character recognition unit are typographical errors, omissions, kanji mistakes, wrong combination of particles, use of words not in the dictionary, homophone errors, and transmission. The answer processing apparatus according to claim 6, wherein the answer processing apparatus is a statistical analysis of the number of occurrences of errors, punctuation errors, or idiomatic expressions. An answer sheet on which one or more students have written an answer, and an answer sheet on which an identification image that is image information associated with student identification information that is identification information of each student who has entered the answer is arranged An answer reading information storage unit in which answer reading information which is read image information is stored;
Answer sheet information that is the image information indicating the state before the answer is written in the answer sheet from which the answer reading information is read, and that stores two or more answer sheet information associated with the answer reading information A storage unit;
For the answer reading information that is image information stored in the answer reading information storage unit, a difference from the answer sheet information stored in the answer sheet information storage unit that is image information corresponding to the answer reading information is acquired. A difference acquisition unit that acquires difference-related information that is difference image information;
A student identification information acquisition unit that detects an identification image of the answer reading information from which the difference has been acquired and acquires student identification information associated with the identification image;
An answer information storage unit in which answer information having the difference-related information and the student identification information is stored;
An answer information accumulating unit for accumulating answer information having difference-related information acquired by the difference acquiring unit and student identification information acquired by the student identification information acquiring unit in the answer information storing unit;
A character recognition unit that performs character recognition processing on the difference-related information acquired by the difference acquisition unit;
Using the student identification information included in the answer information stored in the answer information storage unit, the answer information includes a statistical analysis on the characters described in the difference related information included in the answer information for each student. A statistical analysis unit that uses information indicating a result of character recognition processing performed by the character recognition unit on the difference-related information; and
An output unit for outputting a statistical analysis result of the statistical analysis unit,
The answer processing apparatus, wherein the statistical analysis related to the characters described in the difference-related information is a statistical analysis related to the number of characters per unit area of the described characters. The answer information further includes date information that is information indicating a date corresponding to the answer information.
The answer processing apparatus according to any one of claims 1 to 8 , wherein the statistical analysis unit performs statistical analysis on the answer information for each predetermined period using date information included in the answer information. An answer sheet on which one or more students have written an answer, and an answer sheet on which an identification image that is image information associated with student identification information that is identification information of each student who has entered the answer is arranged Image information indicating a state before answer is written in an answer reading information storage unit for storing answer reading information, which is read image information, and an answer sheet from which the answer reading information is read. An answer sheet information storage unit that stores two or more answer sheet information associated with the read information, a difference acquisition unit, a student identification information acquisition unit, an answer information storage unit that stores answer information , and character recognition Answer processing method that is performed using a part, a statistical analysis part, and an output part ,
The answer sheet stored in the answer sheet information storage unit, which is image information corresponding to the answer reading information, for the answer reading information that is the image information stored in the answer reading information storage unit by the difference acquisition unit A difference acquisition step of acquiring a difference with respect to information and acquiring difference related information that is image information of the difference;
The student identification information acquisition unit detects an identification image of the answer reading information from which the difference is acquired in the difference acquisition step, and acquires student identification information associated with the identification image;
The answer information storage unit, and the difference relevant information acquired by the difference acquisition step, and answer information storage step of storing the answer information and a student identification information acquired by the student identification information acquiring step to the answer information storage unit ,
A character recognition step in which the character recognition unit performs a character recognition process on the difference-related information acquired by the difference acquisition unit;
The statistical analysis unit uses the student identification information included in the answer information stored in the answer information storage unit, and performs statistical analysis on the characters described in the difference related information included in the answer information for each student. A statistical analysis step performed using information indicating a result of the character recognition process performed by the character recognition step with respect to the difference related information included in the answer information;
The output unit includes an output step of outputting a statistical analysis result of the statistical analysis step;
The statistical analysis on the characters described in the difference related information is classified by the number of unique characters or words among the characters recognized for the difference related information by the character recognition step, or the difficulty level of the vocabulary. An answer processing method, which is a statistical analysis on the number or ratio of words used in a specific group among a group of words . An answer sheet on which one or more students have written an answer, and an answer sheet on which an identification image that is image information associated with student identification information that is identification information of each student who has entered the answer is arranged Image information indicating a state before answer is written in an answer reading information storage unit for storing answer reading information, which is read image information, and an answer sheet from which the answer reading information is read. A computer that has access to an answer sheet information storage unit that stores two or more answer sheet information associated with the read information, and an answer information storage unit;
For the answer reading information that is image information stored in the answer reading information storage unit, a difference from the answer sheet information stored in the answer sheet information storage unit that is image information corresponding to the answer reading information is acquired. A difference acquisition unit that acquires difference-related information that is difference image information;
A student identification information acquisition unit that detects an identification image of the answer reading information from which the difference has been acquired and acquires student identification information associated with the identification image;
An answer information accumulating unit for accumulating answer information having difference-related information acquired by the difference acquiring unit and student identification information acquired by the student identification information acquiring unit in the answer information storing unit ;
A character recognition unit that performs character recognition processing on the difference-related information acquired by the difference acquisition unit;
Using the student identification information included in the answer information stored in the answer information storage unit, the answer information includes a statistical analysis on the characters described in the difference related information included in the answer information for each student. A statistical analysis unit that uses information indicating a result of character recognition processing performed by the character recognition unit on the difference-related information; and
Function as an output unit that outputs the statistical analysis result of the statistical analysis unit,
The statistical analysis on the characters described in the difference related information is classified by the number of unique characters or words among the characters recognized by the character recognition unit for the difference related information, or the lexical difficulty level. A program that is a statistical analysis on the number or proportion of words that belong to a particular group of groups of words .

Images