JP5484113B2 - Document image related information providing apparatus and document image related information acquisition system - Google Patents

Description

  The present invention relates to a system that allows a user to easily acquire electronic information related to character information included in image data by analyzing image data acquired by photographing a part of a document such as a book. .

  When reading a printed document such as a book or pamphlet, if you want to know more detailed information related to it, or if you can use a computer connected to the Internet, you can obtain the information immediately by searching the Internet. it can.

  Even if you are out of the office and cannot use your computer, if you have a terminal that can be connected to the Internet, you can get information by entering the information you want to know. Due to its complexity, it is not preferred.

  However, if the printed document has a QR code or digital watermark attached, you can use a camera-equipped mobile device that can recognize the QR code and digital watermark without entering characters to link to electronic data on the Internet. Can access and access electronic data.

  In the following Patent Document 1, information input to an image is embedded as a digital watermark, and the image embedded with the digital watermark is printed and distributed, so that the user can simply capture the image and embed it as a watermark. A technique for reading information is described.

  In Non-Patent Document 1, as a method for obtaining a related link after printing, information related to the document is indexed in advance, the document is photographed with a camera-equipped terminal, and an index is searched with words extracted by the character recognition function. A method has been proposed.

JP 2004-357149 A

Information link method between paper documents and digital data using character recognition and word layout analysis, Ryuji Tsuji et al., IEICE Transactions D, Vol. J929D, no. 6, pp. 868-875

  As described above, in order to be able to obtain links to related information from printed documents, QR codes and digital watermarks are assigned to documents in advance, or documents are digitized and linked to link information. It was necessary to keep.

  If the printed document is a pamphlet or poster based on a specific purpose, it is easy to assume that the information that the user wants to know matches the information that the creator wants to provide. It is realistic to associate fixed link information, but it is very enormous that people reading general books, magazines, newspapers, etc. are expected to look up on the Internet. It is not realistic to link the information related to the information to be indexed in advance.

  The present invention has been made in view of the above, and in a situation where a computer connected to the Internet is not available, such as when going out, when there is meaningful information on the Internet among keywords included in printed books, etc. It is an object of the present invention to provide a technique that allows a user to easily use the information from a terminal carried by the user.

In order to solve the above-described problems, the present invention provides a receiving unit that receives image data including an image of a character string from a user terminal connected to a communication network, and a character for the image data received by the receiving unit. A character recognition unit that performs a recognition process and extracts a character string from the image data; a word information extraction unit that analyzes the character string extracted by the character recognition unit and extracts a word group from the character string; A concept dictionary storage means for storing a concept dictionary in which a word group and a field are associated with each other, and a field-specific word dictionary for each field in which a field-specific word dictionary in which a word in the field is associated with an importance is stored for each field storage means, for the word group extracted by said word information extracting means, by referring to the concept dictionary, to determine the areas of the word groups, each of the words in the word group, It obtains the importance of the word by referring to the areas each importance dictionary corresponding to serial the determined field, significance determination means severity determined is a word which satisfies a predetermined condition, is selected as important keywords And related information generating means for generating related information including link information to information related to the important keyword selected by the importance level determining means, and related information generated by the related information generating means, the user terminal A document image related information providing apparatus, comprising: a transmission means for transmitting to the document image.

  The related information generation unit acquires position information of the important keyword in the image data, includes the position information in association with the link information, and receives the related information. When an important keyword corresponding to the position information on the image displayed on the display unit of the user terminal is highlighted, and the highlighted important keyword is selected by the user, it is associated with the position information. The link information may be used to acquire information related to the important keyword and display it on the display unit.

  The document image related information providing apparatus includes an important word dictionary storing unit that stores an important word dictionary that is data in which a word and an importance are associated with each other, and the importance determining unit is extracted by the word information extracting unit. For each word in the word group, the importance may be obtained by referring to the important word dictionary, and a word satisfying a predetermined degree of importance may be selected as the important keyword.

  The document image related information providing apparatus uses a query log storage unit that stores a query log of a search engine, and an appearance frequency of a word included in the query log stored in the query log storage unit as an importance level, so that the important word dictionary is used. You may provide the important word dictionary production | generation means which produces | generates and stores the said important word dictionary in the said important word dictionary storage part.

  The character recognition unit extracts the character string from the image data and acquires position information of each character, and the importance level determination unit extracts the character information using the position information. The position in the image of each word in the set of words may be detected, and the word closer to the center of the image may be determined to be more important.

  Further, the document image related information providing apparatus stores data indicating the condition used by the importance level determination unit and data indicating a generation method condition used when the related information generation unit generates the related information. Condition data storage means for transmitting the screen data for setting the condition data to the user terminal, and condition setting means for storing the condition data received from the user terminal in the condition data storage means Also good.

  According to the present invention, when a person reading a printed document wants to obtain more detailed information about the character string in the document from the Internet, the user captures the document with a user terminal such as a mobile terminal with a camera, By only transmitting to the document image related information providing apparatus, link information relating to an important keyword group can be received, and useful information can be obtained without a complicated operation such as character input of a word to be searched.

  Further, according to the present invention, even when a document is read on a PC terminal, it is possible to quickly obtain information on a keyword that is of interest without complicated operations. In addition, by setting conditions to acquire appropriate link destinations according to word types, users can efficiently collect necessary information without having to explicitly specify search destinations each time. Can do.

1 is an overall configuration diagram of a document image related information acquisition system according to an embodiment of the present invention. It is a flowchart which shows operation | movement of the document image related information acquisition system which concerns on embodiment of this invention. FIG. 6 is a diagram for explaining processing contents of the first embodiment. 10 is a functional configuration diagram of a document image acquisition unit 12 in Embodiment 2. FIG. FIG. 6 is a diagram for explaining processing contents of a second embodiment. It is a function block diagram of the document image relevant-information provision apparatus 2 in Example 3. FIG. It is a figure which shows an example of the important word dictionary data stored in the important word dictionary storage part 26. FIG. It is a figure which shows an example of a search query log. FIG. 10 is a diagram for explaining an importance calculation method according to a fourth embodiment. FIG. 10 is a functional configuration diagram of a document image related information providing apparatus 2 according to a fifth embodiment. 16 is a flowchart for explaining the operation of the document image related information providing apparatus 2 in the fifth embodiment. FIG. 10 is a functional configuration diagram of a document image related information providing apparatus 2 according to a sixth embodiment.

  Embodiments of the present invention will be described below with reference to the drawings.

(Basic configuration of document image related information acquisition system)
FIG. 1 shows the overall configuration of a document image related information acquisition system according to an embodiment of the present invention. As shown in FIG. 1, the document image related information acquisition system according to the present embodiment includes a user terminal 1 and a document image related information providing device 2, which are connected via a communication network 3 such as the Internet. Has been.

  The user terminal 1 includes a communication unit 11, a document image acquisition unit 12, and a related information display unit 13. The communication unit 11 is a functional unit that transmits and receives data to and from other devices via the communication network 3. For example, the document image acquisition unit 12 acquires image data of a document by photographing the document with a camera, stores the image data in a storage unit such as a memory, and provides the document image related information through the communication unit 11. This is a functional unit that transmits to the device 2. The related information display unit 13 includes a display unit such as a display, and is a functional unit for performing screen display using related information acquired through the communication network 3.

  The user terminal 1 may be any device as long as it has a function of a computer including a storage unit such as a memory and a hard disk and a CPU, and a function capable of acquiring an image. The user terminal 1 can be realized by installing a program for performing processing corresponding to each functional unit on the computer. As will be described later, as the user terminal 1, for example, a portable terminal such as a camera-equipped cellular phone, a PC terminal including a video memory, or the like can be used.

  The document image related information providing apparatus 2 includes a communication unit 21, a character recognition unit 22, a word information extraction unit 23, an importance level determination unit 24, and a related information generation unit 25.

  The communication unit 21 is a functional unit for transmitting and receiving data to and from other devices via the communication network 3. The character recognition unit 22 is a functional unit that performs character recognition processing on image data received from the user terminal 1 and extracts a character string and the like. The word information extraction unit 23 is a functional unit that extracts a word group and the like from the character string extracted by the character recognition unit 22. The importance level determination unit 24 is a functional unit that performs importance level determination on the word group extracted by the word information extraction unit 23 and extracts an important keyword that is a keyword having a high importance level. The related information generation unit 25 is a functional unit that generates related information including link information to information related to the important keyword extracted by the importance level determination unit 24 and transmits the related information to the user terminal 1.

  The document image related information providing apparatus 2 can be realized by mounting a program for performing processing corresponding to each functional unit on a general computer including a storage unit such as a memory and a hard disk and a CPU.

  The program may be installed in the computer from a recording medium such as a portable memory or a disk, or may be downloaded from a server on a network to the computer and installed. The document image related information providing apparatus 2 can also be realized by connecting a plurality of computers via a communication network, such as by realizing each functional unit with a separate computer.

(Basic operation of the system)
Next, the basic operation of the document image related information acquisition system according to the embodiment of the present invention will be described with reference to the flowchart of FIG.

  First, the document image acquisition unit 12 of the user terminal 1 acquires image data of a document such as a book (step 1), and transmits the acquired image data to the document image related information providing apparatus 2 via the communication unit 11 ( Step 2).

  In the document image related information providing apparatus 2, the communication unit 21 receives image data (step 3), the image data is stored in a storage unit such as a memory, and the image data is passed to the character recognition unit 22.

  The character recognition unit 22 analyzes the image data using the character recognition function, and extracts a character string included in the document from which the image data is based (step 4). The character recognition function here is a function that recognizes characters from character image data and obtains text data, such as used in general OCR (Optical Character Reader). That is.

  Next, the character string extracted by the character recognition unit 22 is transferred to the word information extraction unit 23, and the word information extraction unit 23 uses the morpheme analysis function and the part-of-speech analysis function, so that the word is extracted from the character string. (Word group) and part-of-speech information are extracted (step 5). Here, the morphological analysis is a technique for extracting a word and a part of speech information by dividing a sentence into meaningful words as described in, for example, Japanese Patent Laid-Open No. 4-64170.

  The extracted word group is transferred to the importance level determination unit 24, and the importance level determination unit 24 performs importance level scoring on the word group (step 6), and the word group is based on a predetermined condition. An important keyword is selected from (Step 7). This condition is, for example, the top N items in descending order of importance.

  The important keyword selected by the importance level determination unit 24 is passed to the related information generation unit 25. The related information generation unit 25 uses, as related information, information including link information (for example, URL of a page related to the word of Wikipedia, URL of a result thrown to a search engine, etc.) that can obtain information related to each important keyword. It produces | generates (step 8) and transmits the produced | generated relevant information to the user terminal 1 via the communication part 21 (step 9).

  The user terminal 1 receives the related information (step 10), and the related information display unit 13 uses the related information, for example, information for indicating an important keyword in an image obtained by photographing a document, Information acquired from the link destination corresponding to the important keyword is displayed on the display.

  Hereinafter, an embodiment will be described in which more specific processing examples based on the above basic configuration and basic processing operation are described. The basic system configuration and processing flow in each embodiment described below are as shown in FIGS. 1 and 2, respectively, but the detailed configuration and processing contents are different in each embodiment. Hereinafter, each embodiment will be described with a focus on differences from the basic configuration.

  Each of the following embodiments can be implemented in combination with any other embodiment. In each of the following embodiments, a storage unit for storing a dictionary may be provided in the document image related information providing apparatus 2 or may be provided outside and accessed via the communication network 3.

Example 1
First, Example 1 will be described. The first embodiment is an example in which a camera-equipped mobile terminal (for example, a mobile phone, a smartphone, or the like) is used as the user terminal 1. Hereinafter, the processing flow of the present embodiment will be described along the processing flow shown in FIG.

  In this embodiment, image data is acquired by photographing a document printed on a paper medium such as a book with a camera attached to the user terminal 1 (step 1), and the user terminal 1 acquires the acquired image data. Is transmitted to the document image related information providing apparatus 2 (step 2).

  The document image related information providing apparatus 2 performs the processing from step 3 to step 8 shown in FIG. 2 to generate related information, and transmits the related information to the user terminal 1 (step 9). The display using the related information is performed (steps 10 and 11).

FIG. 3 is a diagram showing the processing contents of the present embodiment. The display screen of the user terminal 1 is shown on the right side of FIG. 3, and the relevant information received from the document image related information providing apparatus 2 is displayed on the screen. The created information is displayed.
As shown in FIG. 3, in this embodiment, a document image taken by a camera is displayed in a partial area of the screen (in the example of FIG. 3, the upper half of the screen). The important keywords included are highlighted. By performing such a display, the user can grasp which is an important keyword.

  In addition, it is shown that when the user selects one of the highlighted keywords (cursor movement / selection, screen touch, etc.), information related to the keyword can be displayed in the remaining half of the screen. Yes.

  In the present embodiment, in order to enable the display as shown in FIG. 3, the related information generating unit 25 in the document image related information providing apparatus 2 coordinates the important keyword selected by the importance determining unit 24 in the image. Calculate information. This coordinate information is, for example, the relative position of the important keyword in the image, that is, the upper left coordinate and the lower right coordinate of the important keyword region.

  Then, the related information generation unit 25 transmits related information including the coordinate information and link information corresponding to the important keyword to the user terminal 1. The related information display unit 13 in the user terminal 1 realizes highlighting by superimposing and displaying some mark on the image according to the coordinate information included in the received related information. In the example of FIG. 3, highlighting is realized by superimposing a translucent colored BOX on an important keyword corresponding to coordinate information.

  Further, the related information display unit 13 receives operation information (cursor movement / selection, screen touch, etc.) made on the screen of the user terminal 1, and displays link information corresponding to the coordinate information of the image determined by the operation information. To obtain information and display the obtained information. Thereby, the display of the lower half shown in FIG. 3 can be performed.

(Example 2)
Next, Example 2 will be described. In this embodiment, a general PC terminal is used as the user terminal 1.

  The document image acquisition unit 12 in the user terminal 1 according to the present embodiment acquires image data in a range and timing designated by the user from a video memory that stores image data of an image displayed on the display, and acquires the acquired image data. Is transmitted to the document image related information providing apparatus 2.

  FIG. 4 shows a functional configuration example of the document image acquisition unit 12 according to the present embodiment. FIG. 4 also shows an operation unit 14 (mouse, keyboard, etc.) and a video memory 15 in the user terminal 1. As illustrated in FIG. 4, the document image acquisition unit 12 according to the present embodiment receives instruction information (including information indicating an image range and an instruction to acquire an image) from the operation unit 14. And an image data acquisition unit 122 that acquires image data corresponding to the range of the range information included in the instruction information at the time when the instruction information is acquired, and an image data transmission unit that passes the acquired image to the communication unit 11 123. Such a document image acquisition unit 12 can be realized by using an application program having the functions shown in FIG.

  By providing such a document image acquisition unit 12, for example, as shown in FIG. 5, in the image displayed on the display of the user terminal 1, when the user wants related information regarding a certain character string, When the user designates an area including the character string (frame 17 shown in FIG. 5), the related information can be acquired.

  By acquiring image data from the video memory of the user terminal 1, there is an advantage that there is no influence such as distortion caused when a paper medium is photographed by a camera or shade caused by lighting conditions. Thereby, it is possible to improve the character recognition accuracy, and in the document image related information providing apparatus 2, it is possible to extremely reduce the rate of erroneous character recognition.

  In this embodiment, the application program constituting the document image acquisition unit 12 is displayed on the screen of the user terminal 1 by making it an application program different from the application program displaying an image including a character string. Any character string displayed by any application program can be acquired as long as the character string is displayed.

  Note that in the currently popular OS with GUI (graphical user interface), the contents of the GUI screen are stored in the video memory, and the function to acquire image data from the video memory is in each OS. Is provided. For example, on Windows (registered trademark), capture from a video memory can be realized by using Win32API: BitBlt or the like.

(Example 3)
Next, Example 3 will be described. FIG. 6 shows a functional configuration diagram of the document image related information providing apparatus 2 in the present embodiment. As shown in FIG. 6, the document image related information providing apparatus 2 according to the present exemplary embodiment includes a keyword dictionary storage unit 26 and a keyword dictionary generation unit 27 in addition to the function units shown in FIG. 1.
FIG. 7 shows an example of important word dictionary data stored in the important word dictionary storage unit 26. In the example of FIG. 7, the important word dictionary data is data in which a word is associated with a value indicating its importance. The importance level determination unit 24 in this embodiment calculates the importance level of the word group passed from the word information extraction unit 23 by referring to this important word dictionary. A word that does not exist in the important word dictionary is regarded as having zero importance. In addition, when the number of important keywords to be notified to the user terminal 1 is limited, among words existing in the important word dictionary in the word group, only words having an importance level equal to or higher than a predetermined threshold are important. Can be selected as a keyword.

  For example, when ABC and XYZ are included in the word group passed from the word information extraction unit 23, the importance level determination unit 24 refers to the important word dictionary to set the importance levels of ABC and XYZ to 0. Calculated as 45, 0.86. For example, when the important keyword extraction threshold is 0.8, XYZ is selected as an important keyword, but ABC is not selected as an important keyword.

  The keyword dictionary generation unit 27 in the present embodiment has a function of generating keyword dictionary data and storing it in the keyword dictionary storage unit 26. Specifically, the keyword dictionary generation unit 27 in this embodiment generates a keyword dictionary using a search query log.

  The search query log is information that records information related to the query sent to the search engine (server), the date and time when the search was executed, the contents of the issued query, the IP address of the query issuer, the referrer (link source page) ) URL etc. are included. FIG. 8 shows an example of the search query log.

  Among the information in the search query log, the keywords included in the query (such as “typhoon information” in the example of FIG. 8) can be considered to reflect the current interests of Internet users. By counting the number of keywords included in the query in the search query log, it can be used as an index of the importance of the keyword. That is, the higher the appearance frequency of the keyword in the search query log, the higher the importance can be calculated. Also, it is possible to normalize the keyword so that the importance is between 0 and 1.

  For example, if the word ABC in the word group is 100 in the search query log, and the maximum number of XYZ is 1000 in the search query log, the ABC importance is 0. 1. The importance of XYZ can be calculated as 1.

  The keyword dictionary generation unit 27 can acquire a search query log from another server connected to the communication network 3 and store it in a storage unit such as a memory for use. Alternatively, the search query log may be obtained offline and stored in the storage means. Further, all data of the obtained search query log may be used, or only the search query log may be used for the most recent week or the like in order to reflect the trend of interest.

  In the present embodiment, an example of creating a keyword dictionary using a search query log has been described. However, data used to create a keyword dictionary is not limited to a search query log. Any data that can reflect the interests of the user may be used.

  Further, in the present embodiment, an example in which important word dictionary data is stored in the important word dictionary storage unit 26 in advance and importance calculation is performed using the important word dictionary data has been described. The present invention is not limited to this, and various other methods can be used as long as the importance can be determined by processing of the program.

  For example, the importance level determination unit 24 performs an Internet search using each word of the word group passed from the word information extraction unit 23, and the keyword search is performed based on the frequency of the searched Internet sites (the number of searched sites). The importance can also be calculated. For example, if 10 sites are searched as a result of performing an Internet search with the word ABC and 100 sites are searched as a result of performing an Internet search with the word XYZ, the importance of ABC is set to 10, and the XYZ The importance can be set to 100. For example, when only importance 50 or more is selected as an important keyword, ABC is not selected as an important keyword, and XYZ is selected as an important keyword.

(Example 4)
Next, Example 4 will be described. In the fourth embodiment, word position information is used when determining the importance of each word in the word group extracted by the word information extraction unit 23.

  In this embodiment, the character recognizing unit 22 passes the recognized character string and the position information of each character in the image to the word information extracting unit 23 as a result of character recognition. Then, the word information extraction unit 23 determines the word extracted from the character string, the position information of each word (for example, the coordinates of the upper left end point of each character constituting the word), and the part of speech of the word as the importance determination unit 24. To pass.

  The importance determination unit 24 acquires a noun (but not a suffix) word from the word group based on the word group and part of speech information passed from the word information extraction unit 23. Furthermore, the importance level determination unit 24 calculates the centroid position (X, Y) of the word using the position information of each character of the word, and the importance level is closer to the center position of the image. Scoring is performed using a function that increases the score, and the higher the score, the higher the importance. In other words, if the horizontal and vertical lengths of the image are W and H, the distance between (X, Y) and (W / 2, H / 2) is calculated, and the smaller the distance, the higher the importance. The importance is calculated as follows.

  FIGS. 9A and 9B are diagrams for specifically explaining the importance calculation method in the present embodiment. In FIG. 9A, words determined as nouns (but not suffixes) by the word information extraction unit 23 are surrounded by dotted lines. The importance level determination unit 24 calculates the centroid (X, Y) of each word, and calculates the importance level so that the closer the centroid is to (W / 2, H / 2), the higher the score.

  FIG. 9B is an example of the barycentric coordinates of each word and the score calculated therefrom. In this example, the distance from the center (W / 2, H / 2) of the image is taken and normalized. Results are used as scores (= importance). In this example, the “field” near the center is the keyword with the highest importance, and continues in the order of “electronic” and “prime number”.

  When this embodiment is used in combination with the third embodiment, for example, the score obtained based on the position information in this embodiment (or the importance obtained using the important word dictionary in the second embodiment) (or A value obtained by multiplying the score by a predetermined weighting factor) can be used as the importance.

(Example 5)
Next, Example 5 will be described. FIG. 10 shows a configuration diagram of the document image related information providing apparatus 2 of the present embodiment, and FIG. 11 shows a processing flow of the document image related information providing apparatus 2 of the present embodiment.

  As shown in FIG. 10, in the present embodiment, the document image related information providing apparatus 2 includes a concept dictionary storage unit 28 that stores concept dictionary data, and a key word for each field that stores key word dictionary data for each field. A dictionary storage unit 29 is provided.

  Here, the concept dictionary is a dictionary describing the relationship between a concept and other concepts, and in this embodiment, the field represented by the word group is determined by applying the concept dictionary. The important word dictionary for each field is a key word dictionary for each predetermined field including, for example, a key word dictionary specialized in the scientific field. If this dictionary corresponds to the scientific field, for example, the data structure shown in FIG. 7 is a dictionary in which important words in the scientific and technological field are listed in the word column.

  In the processing flow of FIG. 11, the process up to step 5 is the same as the processing flow in the basic configuration. In step 61, the importance level determination unit 24 searches the concept dictionary using the word group (including the important keyword and its peripheral words) extracted by the word information extraction unit, and thereby the document indicated in the image data. Determine the field of content. The word group may be passed to the related information generation unit 25, and the related information generation unit 25 may search the concept dictionary.

  For example, in the example shown in FIG. 9A, by applying “theory”, “spin”, “electron”, etc. to the concept dictionary, it can be determined that the contents of this document are described in the scientific field.

  Then, the importance level determination unit 24 calculates the importance level of each word using the keyword dictionary corresponding to the field determined in step 61 instead of using the general-purpose keyword dictionary (step 62). Thereby, for example, regarding the word “place” in FIG. 9A, the importance of the word “place” as a technical term in the scientific field can be evaluated.

  In the example shown in FIG. 9A, the word “place” is generally considered not to be a very important keyword, but the field is determined using the concept dictionary as in this embodiment. By doing so, it is possible to calculate a more appropriate degree of importance suitable for the content of the document.

  In FIG. 11, the processing after step 7 is the same as the processing in the basic configuration.

(Example 6)
Next, Example 6 will be described. Example 6 is a specific example of processing related to selection of important keywords and selection of related information.

  FIG. 12 shows a configuration example of the document image related information providing apparatus 2 in the present embodiment. In the present embodiment, the document image related information providing apparatus 2 is configured to store condition data related to selection of important keywords, selection of related information, and the like, and a condition data setting to be stored in the condition data storage unit 30. Is sent to the user terminal 1, and the condition setting GUI unit 31 for storing the received condition data in the condition data storage unit 30 is provided.

  With the function of the condition setting GUI unit 31, for example, a GUI screen (Web screen) for setting conditions is displayed on the display unit of the user terminal 1, and the user can input desired conditions while viewing the GUI screen.

  Examples of condition data stored in the condition data storage unit in the present embodiment include the maximum number of words that the importance level determination unit 24 selects from the word group as an important keyword, and the contribution of position information in calculating the importance level. Degree (the weighting factor described above), a part-of-speech list of words to be extracted as important keyword candidates, and the like.

  In addition, the related information generation unit 25 includes a specific expression extraction function that analyzes a proper noun and extracts word profile information such as whether it is a person name, a place name, or an organization name. The type of related information to be created may be customized by word profile information. The customization conditions here are stored in the condition data storage unit 30 as condition data.

  As customization, for example, related information is provided to the user terminal 1 only for words of a specific profile among important keywords. When the important keyword is a place name, a URL of a map provided by a predetermined site is acquired. And providing it to the user terminal 1. In this way, it is possible to set conditions to acquire an appropriate link destination according to the type of word, and the user can efficiently and efficiently need to specify the search destination every time. Information can be collected.

  For example, a technique described in Japanese Patent Application Laid-Open No. 2009-86911 can be used as the specific expression extraction function.

  The present invention is not limited to the above-described embodiments, and various modifications and applications are possible within the scope of the claims.

DESCRIPTION OF SYMBOLS 1 User terminal 2 Document image related information provision apparatus 3 Communication network 11 Communication part 12 Document image acquisition part 13 Related information display part 14 Operation part 15 Video memory 21 Communication part 22 Character recognition part 23 Word information extraction part 24 Importance determination part 25 Related information generation unit 26 Important word dictionary storage unit 27 Important word dictionary generation unit 28 Concept dictionary storage unit 29 Important word dictionary storage unit 30 for each field Condition data storage unit 31 Condition setting GUI unit 121 Instruction information acquisition unit 122 Image data acquisition unit 123 Image data transmitter

Claims (8)

Receiving means for receiving image data including an image of a character string from a user terminal connected to a communication network;
Character recognition means for performing character recognition processing on the image data received by the receiving means and extracting a character string from the image data;
Analyzing the character string extracted by the character recognition means, and extracting word information extraction means for extracting a word group from the character string,
Concept dictionary storage means for storing a concept dictionary in which word groups and fields are associated with each other;
Each field important word dictionary storage means for storing each field important word dictionary in which each field word and importance are associated with each field;
For the word group extracted by the word information extraction unit, the field of the word group is determined by referring to the concept dictionary, and each word in the word group corresponds to the determined field. obtains the importance of the word by referring to the areas each important word dictionary, and a significance determination means severity determined is a word which satisfies a predetermined condition, is selected as the important keywords,
Related information generating means for generating related information including link information to information related to the important keyword selected by the importance determining means;
A document image related information providing apparatus comprising: transmission means for transmitting related information generated by the related information generating means to the user terminal. The related information generation unit acquires position information of the important keyword in the image data, includes the position information in association with the link information, and includes the position information in the related information.
The user terminal that has received the related information highlights the important keyword corresponding to the position information on the image displayed on the display unit of the user terminal, and the highlighted important keyword is selected by the user. 2. The document image related information according to claim 1, wherein information related to the important keyword is acquired using link information associated with the position information and displayed on the display unit. Providing device. The document image related information providing device includes an important word dictionary storing means for storing an important word dictionary which is data in which a word and an importance are associated with each other.
The importance level determination means obtains an importance level for each word in the word group extracted by the word information extraction means by referring to the important word dictionary, and a word whose importance level satisfies a predetermined condition is obtained. The document image related information providing apparatus according to claim 1, wherein the document image related information providing apparatus is selected as the important keyword. The document image related information providing device includes:
Query log storage means for storing search engine query logs;
Generating the important word dictionary by generating the important word dictionary by using the appearance frequency of words included in the query log stored in the query log storage means as the importance, and storing the important word dictionary in the important word dictionary storage unit The document image related information providing apparatus according to claim 3, further comprising: means. The character recognition means extracts the character string from the image data, acquires position information of each character,
The importance level determination unit detects the position in the image of each word in the word group extracted by the word information extraction unit using the position information, and determines that the word closer to the center of the image has a higher level of importance. document image related information providing apparatus according to any one of claims 1 to 4, characterized in that. The document image related information providing device includes:
Condition data storage means for storing data indicating the condition used by the importance level determination means and data indicating a generation method condition used when the related information generation means generates the related information;
2. A condition setting unit that transmits screen data for setting the condition data to the user terminal and stores the condition data received from the user terminal in the condition data storage unit. 6. The document image related information providing apparatus according to any one of items 5 to 5 . A document image related information acquisition system comprising: the document image related information providing apparatus according to any one of claims 1 to 6 ; and the user terminal, wherein the user terminal includes:
Document image acquisition means for acquiring image data of the document by photographing the document;
Transmitting means for transmitting the image data acquired by the document image acquiring means to the document image related information providing apparatus;
Receiving means for receiving the related information from the document image related information providing device;
A document image related information acquisition system comprising: related information display means for displaying information related to the important keyword using the received related information. A document image related information acquisition system comprising: the document image related information providing apparatus according to any one of claims 1 to 6 ; and the user terminal, wherein the user terminal includes:
Document image acquisition means for acquiring the image data from a video memory included in the user terminal;
Transmitting means for transmitting the image data acquired by the document image acquiring means to the document image related information providing apparatus;
Receiving means for receiving the related information from the document image related information providing device;
A document image related information acquisition system comprising: related information display means for displaying information related to the important keyword using the received related information .

Images