JP2021170276A - Information processing device and program - Google Patents

Abstract

To provide an information processing device and a program capable of supporting information input based on documents with various types of formats different from each other.SOLUTION: An information processing device 1 acquires document information scanned and extracts character string information from the acquired document information by character recognition processing, divides or integrates the extracted character string information based on a predetermined rule, and presents the character string information acquired by dividing or integrating as a candidate for input information when a user inputs a character string in an input field.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing device and a program that support information input.

There is a need for a technique that assists in the task of filling out a form by referring to an optically read document. As an example, there is a technology that executes character recognition processing (OCR) on a read document and sets by drag and drop which input field of the form the information of the character string obtained by character recognition is associated with. It exists (Patent Document 1).

Japanese Unexamined Patent Publication No. 2014-137605

The above-mentioned conventional technique is effective when processing a form of a standard form, but in reality, the form may be different even if the form has a common purpose. For example, although there is not much difference in the contents to be described in the application form for the use of nursery schools used by local government agencies, the forms are generally different from each other, so the position of the entry field for each information is different for each local government agency. It is divided into districts.

In order to support input from various types of forms in which the forms are different from each other, the above-mentioned conventional techniques cannot be used.

The present invention has been made in view of the above circumstances, and one of its objects is to provide an information processing device and a program capable of supporting information input based on forms of various types different from each other.

One aspect of the present invention that solves the problems of the above-mentioned conventional example is an information processing device, which is an acquisition means for acquiring document information obtained by scanning, and characters from the acquired document information by character recognition processing. The extraction means for extracting the column information, the division / integration means for dividing or integrating the extracted character string information based on a predetermined rule, and the character string information obtained by the division or integration are used as candidates for input information. It is intended to include a presentation means to be presented when the user inputs a character string in the input field.

According to the present invention, it is possible to support information input based on forms of various types different from each other.

It is a block diagram which shows the example of the information processing apparatus which concerns on embodiment of this invention. It is a functional block diagram which shows the example of the information processing apparatus which concerns on embodiment of this invention. It is explanatory drawing which shows the example of the document information which is the object of processing of the information processing apparatus which concerns on embodiment of this invention. It is a flowchart which shows the example of the processing of the information processing apparatus which concerns on embodiment of this invention. It is explanatory drawing which shows the example of the user interface displayed by the information processing apparatus which concerns on embodiment of this invention.

Embodiments of the present invention will be described with reference to the drawings. As illustrated in FIG. 1, the information processing device 1 according to the embodiment of the present invention includes a control unit 11, a storage unit 12, an operation unit 13, a display unit 14, and an input / output unit 15. Further, the information processing device 1 is connected to the scanner device 2.

The control unit 11 is a program control device such as a CPU, and operates according to a program stored in the storage unit 12. In the present embodiment, the control unit 11 acquires the document information obtained by scanning with the scanner device 2. This document information shall be image data. Further, the control unit 11 extracts character string information from the acquired document information by character recognition processing. The control unit 11 divides the character string information extracted here based on a predetermined rule, and the user uses the character string information (referred to as divided character string information) obtained by dividing or integrating the character string information as a candidate for input information. It is used for the process to be presented when inputting a character string in the input field. The details of the operation of the control unit 11 will be described later.

The storage unit 12 includes a disk device and a memory device. The storage unit 12 holds a program executed by the control unit 11. This program may be provided stored in a computer-readable and non-temporary recording medium and installed in the storage unit 12. The storage unit 12 also operates as a work memory for the control unit 11.

In an example of the present embodiment, it is assumed that the storage unit 12 records in advance the form-related information representing the item of information to be extracted from the form for each type of form. Specifically, when the receipt is the target form, items such as the store name, store address, store phone number, purchased items, number of purchases, unit price, and amount are specified in association with the information that identifies the receipt. The information is stored as form-related information.

The operation unit 13 includes a keyboard, a mouse, and the like. The operation unit 13 accepts the user's operation and outputs information representing the content of the operation to the control unit 11. The display unit 14 is a display or the like, and displays and outputs information according to an instruction input from the control unit 11.

The input / output unit 15 is, for example, a USB interface or the like, and is connected to the scanner device 2 in the example of the present embodiment. The input / output unit 15 outputs the document information obtained by being optically read by the scanner device 2 to the control unit 11.

Next, an operation example of the control unit 11 will be described. As illustrated in FIG. 2, in an example of the present embodiment, the control unit 11 functionally has a document acquisition unit 21, a character string extraction unit 22, a division / integration processing unit 23, and a candidate setting unit 24. And the information input unit 25.

Here, the document acquisition unit 21 accepts the input of the document information obtained by scanning with the scanner device 2. As described above, the document information acquired by the document acquisition unit 21 here is assumed to be image data obtained by optically reading a form such as a receipt.

The character string extraction unit 22 extracts character string information from the document information acquired by the document acquisition unit 21 by character recognition processing. This character recognition process may be so-called OCR (optical character recognition). The character string extraction unit 22 outputs information for specifying the circumscribed rectangular area circumscribing the image portion of the character string recognized on the document information and character string information in the circumscribed rectangular area.

The division / integration processing unit 23 divides or integrates the character string information extracted by the character string extraction unit 22 into a plurality of division character string information based on a predetermined rule. As a specific example, the document information is image data obtained by optically reading the receipt as illustrated in FIG. 3, and the character string information for each extrinsic rectangular area recognized by the character string extraction unit 22 is each. ,
(1) XX store (2) ZA, Y city, X prefecture
(3) M month D day H hour m minute (4) miscellaneous (5) currency (6) 1 point @ 240
(7) 240
(8) α tablet (9) 1 point ... @ 500
(10) 500
(11) Subtotal (12) 740
(13) Tax (14) 10%
(15) 74
(16) Total (17) 814
It is assumed that

In the document information, the division / integration processing unit 23 has the main scanning direction (the direction in which the character strings are arranged) as the X-axis and the sub-scanning direction as the Y-axis, and the extrinsic rectangular area containing the character string information is positioned in the Y-axis direction. Clustering (first clustering). Here, the position of the circumscribed rectangle region may be the coordinates of the center of the circumscribed rectangle (the intersection of the two diagonal lines). The clustering method is not limited, but for example, one circumscribed rectangular area P whose cluster to which the member belongs is selected, and another circumscribed rectangular area that overlaps with the extension area extending left and right in the X-axis direction. If there are Q and R, the processing such as setting the circumscribed rectangular areas P, Q and R to be one cluster (P, Q and R belong to one cluster) does not belong to the cluster. It may be repeated until the circumscribed rectangular area disappears.

Further, the division / integration processing unit 23 rearranges the circumscribed rectangular regions in ascending (or larger) order of the X coordinates of the positions when there are a plurality of circumscribed rectangular regions belonging to the same cluster by the first clustering. Does the division integration processing unit 23 exceed a predetermined division threshold value for each of the rearranged circumscribed rectangular regions Ri (i = 1, 2, ...) In the X-axis direction to the adjacent circumscribed rectangular regions Ri + 1. Judge whether or not. Then, when the distance between the adjacent circumscribed rectangular regions Ri and Ri + 1 in the X-axis direction exceeds the division threshold value, the division integration processing unit 23 forms a cluster between the circumscribed rectangular regions Ri and Ri + 1. Divide (second clustering). As a result, if there is a relatively large blank area between the pair of circumscribed rectangular regions, it is determined that the pair of circumscribed rectangular regions belong to different clusters. Here, the distances between the circumscribed rectangular regions adjacent to each other are the X coordinate of the right side of the circumscribed rectangular region Ri (the maximum value if it is tilted) and the adjacent circumscribed rectangle when rearranged in ascending order of the X coordinate of the position. It shall be represented by the difference from the X coordinate (the minimum value if it is tilted) on the left side of the region Ri + 1.

Further, when the distance in the X-axis direction between the extrinsic rectangular regions Ri and Ri + 1 adjacent to each other does not exceed the predetermined division threshold value, the division integration processing unit 23 performs the extrinsic rectangle by the second clustering process. The character strings included in each of the areas Ri and Ri + 1 are integrated (the character strings are concatenated in the order of the main scanning direction). That is, the division / integration processing unit 23 determines, for each cluster obtained by the first clustering, a character string in the extrinsic rectangular region within the extrinsic rectangular region included in the cluster at a distance less than the division threshold. (The position of the circumscribing rectangular area is above the Y-axis, the earlier it is, and if it is the same Y coordinate, the more it is to the left in the X-axis direction), and the information of the character string after the connection is divided into characters. It is stored in the storage unit 12 as column information (integrated processing).

For the document information in the example of FIG. 3, there is a space of about one character between the circumscribed rectangular area "(4) miscellaneous" and the circumscribed rectangular area "(5) currency", and the circumscribed rectangular area "(5) currency" There is a space of about 3 characters between "(5) coin" and the circumscribed rectangular area "(6) 1 point ... @ 240". Therefore, if the above-mentioned predetermined value, which is the threshold value, is set to two characters or more, the circumscribed rectangular area "(4) miscellaneous" and the circumscribed rectangular area "(5)" are processed by the division / integration processing unit 23. The "currency" is integrated, and the circumscribed rectangular area "(5) currency" and the circumscribed rectangular area "(6) 1 point ... @ 240" are divided into separate clusters.
Cluster 1. "XX store"
Cluster 2. "ZA, Y City, X Prefecture"
Cluster 3. "M month D day H hour m minute"
Cluster 4. "general merchandise"
Cluster 5. "1 point ... @ 240"
Cluster 6. "240"
Cluster 7. "Α tablet"
Cluster 8. "1 point ... @ 500"
Cluster 9. "500"
Cluster 10. "subtotal"
Cluster 11. "740"
...
As such, the character string information obtained by OCR or the like is divided into a plurality of clusters, and the divided character string information for each cluster is obtained.

The candidate setting unit 24 presents the divided character string information obtained by dividing or integrating the divided character string information as a candidate for the input information when the user inputs the character string to the input field. Specifically, the candidate setting unit 24 uses, among the divided character string information for each cluster stored in the storage unit 12 by the divided integrated processing unit 23, the divided character string information satisfying a predetermined condition as an input character string candidate. Set.

The predetermined condition here may be, for example, the length of the divided character string information (the number of characters included in the divided character string information). For example, when the number of characters included in the divided character string information for each cluster is "2" or more and "10" or less, the candidate setting unit 24 sets the divided character string information as an input character string candidate.

Each time the document acquisition unit 21 acquires the document information, the information input unit 25 displays an input field for information to be transcribed from the document information and prompts the user to input the information. There may be multiple input fields displayed here, and the type of each input field displayed (title indicating what kind of information to be input, information defining the conditions of information to be input, etc.) , It shall be decided in advance. Further, the information input unit 25 displays a button (for example, a “registration” button) for instructing the completion of the information input.

As an example, here, it is assumed that input fields for each type of information of "purchase store", "purchase date", "purchase item", and "amount" are displayed. The "purchase item" and "amount" are displayed repeatedly a plurality of times. The user specifies an input field (for example, clicks on the input field to focus on the input field for inputting information), and operates the keyboard to input the information.

The information input unit 25 displays a character string set as an input character string candidate by the candidate setting unit 24 in a state in which it can be selected as a candidate for an input character string when the user specifies an input field. When the user selects one of the displayed input character string candidates, the information input unit 25 is in a state of inputting the selected input character string candidate in the designated input field.

Further, when the user inputs a character string in the designated input field without selecting one of the displayed input character string candidates, the information input unit 25 may cancel the display of the input character string candidate.

Further, when a character string is input in the input field designated by the user, the information input unit 25 inputs the input character string candidate if there is an input character string candidate that matches (or partially matches) the input character string. The character string candidate may be displayed in a state in which it can be selected as a character string candidate to be input.

When the user instructs the completion of the information input, the information input unit 25 executes a predetermined process such as registering the information input in each input field in the database, and ends the process. At this time, the information input unit 25 may delete the input character string candidates stored in the storage unit 12.

[motion]
The information processing device 1 according to the example of the present embodiment has the above configuration and operates as follows. The user of the information processing device 1 operates the scanner device 2 to optically read an image formed on a medium (receipt or the like) such as a paper surface. The scanner device 2 outputs the image data obtained by optically reading the receipt or the like to the information processing device 1 as document information.

When the information processing device 1 receives the document information output by the scanner device 2, the processing illustrated in FIG. 4 is started, and the characters recognized on the document information by the optical character recognition processing from the received document information. Information for specifying the extrinsic rectangular area circumscribing the image portion of the column and character string information in the extrinsic rectangular area are obtained (S1).

The information processing device 1 divides the character string information obtained in step S1 into a plurality of divided character string information based on a predetermined rule (S2). Here, as in the example described above, the predetermined rule is to concatenate the character strings in the extrinsic rectangular area relatively close to the direction in which the character strings are arranged (integration processing), and to concatenate the characters in the extrinsic rectangular area relatively far away. The rule may be to divide the columns. Further, in this rule, the character strings in the circumscribing rectangular area in the direction orthogonal to the direction in which the character strings are arranged are divided.

According to this rule, the information processing apparatus 1 has, for example, from the document information illustrated in FIG. 3, as already shown.
Cluster 1. "XX store"
Cluster 2. "ZA, Y City, X Prefecture"
Cluster 3. "M month D day H hour m minute"
Cluster 4. "general merchandise"
Cluster 5. "1 point ... @ 240"
Cluster 6. "240"
Cluster 7. "Α tablet"
Cluster 8. "1 point ... @ 500"
Cluster 9. "500"
Cluster 10. "subtotal"
Cluster 11. "740"
...
Get the split character string information like this.

The information processing device 1 stores the divided character string information satisfying a predetermined condition among the divided character string information for each cluster obtained by the division as an input character string candidate (S3). Here, the condition is the length of the divided character string information, and when the number of characters is "2" or more and "10" or less, the divided character string information is set as an input character string candidate.

The information processing device 1 displays an input field (X) of information to be transcribed from the received document information as illustrated in FIG. 5 (S4). Here, the information processing device 1 displays input fields for "purchase store", "purchase date", "purchase item", and "amount", and also a button for instructing the completion of input (for example, a "registration" button). Etc. shall be displayed. Further, the information processing device 1 displays the received document information (image data) together with this input field (FIG. 5 (Y)). Then, the information processing device 1 waits for the input of information from the user (S5).

After that, the user specifies an input field and inputs the information corresponding to the designated input field while referring to the document information. When the input field is specified by the user (S5: Yes), the information processing device 1 displays a list of input character string candidates stored in step S3 (S6), and waits for the user's selection or character string input (S6). S7).

Here, when the user selects one of the input character string candidates from the list displayed in step S6 (S7: selection), the information processing apparatus 1 selects the input character string candidate in the input field specified in step S5. (S8), the process returns to step S5 and the process is continued.

On the other hand, in step S7, when the user directly inputs a character string by operating a keyboard or the like (S7: direct input), the information processing apparatus 1 is included in the list of input character string candidates stored in step S3. Selects an input character string candidate whose prefix matches the character string input from (S9), and displays the selected input character string candidate (S10).

Here, when the user selects one of the input character string candidates from the list displayed in step S10 (S11: selection), the information processing apparatus 1 selects the input character string candidate in the input field specified in step S5. (S12), the process returns to step S5 and the process is continued.

On the other hand, in step S11, when the user continues to directly input the character string by operating the keyboard or the like (S11: direct input), the information processing apparatus 1 returns to step S9 and continues the process.

If the user specifies another input field during the processes of steps S7 to S12, the information processing apparatus 1 returns to the process S6 and continues the process (A).

Further, when the user instructs the completion of the input during the processes of steps S6 to S12, the information processing apparatus 1 executes a predetermined process such as registering the information input in each input field in the database (B). , S21), the stored input character string candidate is deleted (S22).

Further, in the processing here, the information processing apparatus 1 may control the input character string candidate once selected so as not to be displayed as a candidate again. Specifically, in this example, a flag indicating whether or not the input character string candidate has already been selected (input in the input field) is associated and stored. At this time, the initial value is set to a value indicating that it has not been selected (for example, False).

In this example, when the input character string candidate is selected in step S7 or step S11, the information processing device 1 indicates that the flag associated with the selected input character string candidate has already been selected (a value indicating that the flag associated with the selected input character string candidate has already been selected. For example, set to True). Then, the information processing apparatus 1 displays a list of input character string candidates associated with the flag indicating unselected at the time of list display in step S6 or selection in step S9, or is associated with the flag indicating unselected. Among the input character string candidates that have been input, the input character string candidate that prefixes the input character string is selected.

[Conditions for input character string candidates]
Further, in the description so far, the control unit 11 of the information processing device 1 is set as an input character string candidate among the divided character string information obtained by dividing or integrating when operating as the candidate setting unit 24. The split character string information to be processed is set based on the length of the split character string information (the number of characters included in the split character string information). However, the conditions for input character string candidates are not limited to this.

In an example of the present embodiment, the candidate setting unit 24 may use the length of the divided character string information as a condition for the input character string candidate, as well as whether or not it matches a predetermined pattern. In this example, the candidate setting unit 24 may set the divided character string information that matches the predetermined pattern (or does not match the predetermined pattern) as the input character string candidate. This pattern can be, for example, a so-called regular expression. The candidate setting unit 24 is, for example,
"* County * City *"
Etc. Set the divided character string information that matches the candidate patterns listed in advance as input character string candidates. The candidate setting unit 24 is listed separately.
"*point…@*"
It may be controlled not to set the divided character string information matching the non-candidate pattern such as as the input character string candidate. Here, "*" is assumed to be a regular expression indicating that it matches any one character. Further, regarding the divided character string information that does not match the listed candidate patterns and non-candidate patterns, it is determined in advance whether or not to set as an input character string candidate, and the candidate setting unit 24 determines the input character string according to the determination. It may be set (or not set) as a candidate.

Further, here, the candidate pattern and the non-candidate pattern may be set for each input field to be displayed in the processing as the information input unit 25.

For example, for the "address" input field, as a candidate pattern,
"* [Prefecture] * [City] * [Town] *"
And for "Purchase item", "[0-9] +" as a non-candidate pattern
And so on. Here, [ABC] or [AC] is assumed to match any of A, B, and C, and "+" indicates that the pattern is an array of one or more characters of the immediately preceding type. In other words, "[0-9] +" means that it consists only of numerical values.

In the case of this example, the candidate setting unit 24 checks whether each of the divided character string information obtained by dividing or integrating matches the candidate pattern or the non-candidate pattern predetermined for each input field. Then, when the candidate setting unit 24 matches the candidate pattern (or does not match the non-candidate pattern), the candidate setting unit 24 provides information (input field) for specifying the input field corresponding to the candidate pattern or the non-candidate pattern in the divided character string information. (Name, etc.) is associated and stored as an input character string candidate.

In this example, for example
Cluster 1. "XX store" Purchase store, purchase item cluster 2. "ZA, Y city, X prefecture" Address cluster 3. "M month D day H hour m" Purchase date cluster 4. "Miscellaneous goods" Purchase store, purchase item cluster 5. "1 point ... @ 240" (none)
Cluster 6. "240" Purchase price ...
As such, input character string candidates are set for each input field.

In this case, the information input unit 25 is an input character string candidate associated with the information that identifies the specified input field among the character strings set as the input character string candidates when the user specifies the input field. Is displayed in a selectable state as a candidate for the character string to be input.

When the user selects one of the displayed input character string candidates, the information input unit 25 is in a state of inputting the selected input character string candidate in the designated input field.

Further, when the user inputs a character string in the designated input field without selecting the input character string candidate, the information input unit 25 starts with (or partially matches) the input character string candidate. If there is an input character string candidate associated with the information that identifies the specified input field, the input character string candidate is displayed in a selectable state as a character string candidate to be input. May be good. Also in this case, when the user selects one of the displayed input character string candidates, the information input unit 25 sets the selected input character string candidate in the designated input field (the user is in the middle). The information you have entered up to will be replaced).

Here, when setting the input character string candidate, the input field that is the candidate for the input destination is specified, but the present embodiment is not limited to this example. For example, an input character string candidate is set without specifying an input field, and when displaying a character string candidate to be input for a certain input field, among the set input character string candidates, the input is concerned. An input character string candidate that matches a predetermined pattern (which may be represented by a regular expression as described above) associated with the field may be selected and displayed.

[Other examples of input string candidates]
Further, the input character string candidate is not limited to the one set by the candidate setting unit 24 based on the character string information obtained by OCR. The information processing device 1 stores character string information set in advance by a user, an administrator, or the like as an input character string candidate (hereinafter, referred to as a preliminary candidate in order to distinguish it from the one set by the candidate setting unit 24). When the user specifies an input field, the input character string candidates set by the candidate setting unit 24 and the pre-candidates stored in advance are displayed in a state where they can be selected as candidates for the character string to be input. You may.

In this case as well, information that specifies an input field that is a candidate for the input destination may be associated with the prior candidate. The information input unit 25 is associated with information that identifies a designated input field among the character string set as the input character string candidate and the character string of the pre-candidate when the user specifies the input field. Input character string candidates and advance candidates are displayed in a state in which they can be selected as candidates for the character string to be input.

[Other input methods]
Further, in the present embodiment, when the information input unit 25 displays the document information as illustrated in FIG. 5, for each cluster obtained by the division integration processing unit 23, the circumscribed rectangle related to the division character string information belonging to the cluster is obtained. The areas may be overlapped and displayed. This circumscribed rectangular area is a rectangular area further circumscribed to each circumscribed rectangular area of the character string information (character string information before division) included in the cluster.

Then, when the user performs an operation of associating the circumscribed rectangular area for each cluster with the input field, the information input unit 25 inputs the divided character string information corresponding to the cluster of the circumscribed rectangular area in the input field. Make it a state.

As an example, the operation of associating the circumscribed rectangular area with the input field may be a drag-and-drop operation using a pointing device such as a mouse. At this time, when there is a character string already input in the associated input field, the information input unit 25 connects the divided character string information corresponding to the cluster of the extrinsic rectangular area to the character string and inputs it in the input field. May be. Furthermore, at this time, when the user drags and drops while pressing the modifier key (for example, the shift key), the character string already entered in the associated input field is replaced with the divided character string information corresponding to the cluster in the extrinsic rectangular area. , You may enter in the input field.

[Use of dictionary]
Further, in the example of the present embodiment, the candidate setting unit 24 may use a character string registered in a preset candidate dictionary (or non-candidate dictionary) as the candidate pattern (or non-candidate pattern). In this example, the candidate setting unit 24 uses the character string information determined to be similar to the character string registered in the preset candidate dictionary among the divided character string information as the input character string candidate. Further, the candidate setting unit 24 may control the divided character string information so that the character string information determined to be similar to the character string registered in the preset non-candidate dictionary is not used as the input character string candidate. ..

Here, whether or not the character strings are similar may be determined by adopting a widely known method such as the Levenshtein distance (editing distance). Further, in this example, when the candidate setting unit 24 determines that the divided character string information is similar to the character string registered in the preset candidate dictionary, the candidate setting unit 24 uses the divided character string information as an input character string candidate. Alternatively, a character string registered in the candidate dictionary, which is determined to be similar, may be used as an input character string candidate.

Further, each character string registered in the candidate dictionary (or non-candidate dictionary) may be further associated with information specifying the corresponding input field. In this example, when the candidate setting unit 24 finds the divided character string information similar to the character string (candidate character string) registered in the candidate dictionary, the candidate setting unit 24 inputs the input field associated with the similar candidate character string. The specified information is associated with the divided character string information (or candidate character string) and stored as an input character string candidate.

In such a case, as described above, when the user specifies an input field, the information input unit 25 identifies the specified input field among the character strings set as the input character string candidates. The input character string candidates associated with are displayed in a selectable state as input character string candidates.

Further, registration in the candidate dictionary may be performed when the actual input is made. Specifically, the information input unit 25 registers the character string input in each input field in the candidate dictionary when the character string is input in the input field specified by the user or when the completion of the information input is instructed. .. Alternatively, for each input field, the information for specifying the input field and the character string input in the corresponding input field may be associated and registered in the candidate dictionary.

[Effect of Embodiment]
As described above, according to the present embodiment, the character string information obtained by extracting from the image data (document information) read by the scanner device 2 by character recognition processing such as OCR and further dividing or integrating into predetermined units. (Split character string information) is set as a candidate for auto-complete when inputting information in the input field. As a result, even if there are a plurality of types of document information forms read, it is possible to support information input based on the forms of the different forms.

1 Information processing device, 2 Scanner device, 11 Control unit, 12 Storage unit, 13 Operation unit, 14 Display unit, 15 Input / output unit, 21 Document acquisition unit, 22 Character string extraction unit, 23 Division integration processing unit, 24 Candidate setting Department, 25 Information input unit.

Claims (7)

An acquisition method for acquiring document information obtained by scanning,
An extraction means for extracting character string information from the acquired document information by character recognition processing,
A division / integration means that divides or integrates the extracted character string information based on a predetermined rule, and
The presentation means presented when the user inputs a character string in the input field using the character string information obtained by the division or integration as a candidate for input information.
Information processing equipment including. The information processing device according to claim 1.
The presenting means inputs the character string information obtained by the division or integration when the character string information obtained by the division or integration satisfies the condition relating to the length of the predetermined character string information. An information processing device presented when a user inputs a character string in an input field as a candidate for information. The information processing device according to claim 1 or 2.
When the character string information obtained by the division or integration satisfies the conditions predetermined for each input field, the presentation means uses the character string information obtained by the division or integration as a candidate for the input information. , An information processing device presented when a user inputs a character string in an input field. The information processing device according to any one of claims 1 to 3.
The presenting means refers to a candidate dictionary in which a character string is registered in advance, and when a character string determined to be similar to the character string information obtained by dividing or integrating is registered in the candidate dictionary, An information processing device that presents when a user inputs a character string in an input field, using the character string information or a character string similar to the character string information registered in the candidate dictionary as a candidate for input information. The information processing device according to claim 4.
The character string registered in the candidate dictionary is associated with information that identifies an input field in which the character string can be input.
The presenting means is a character string registered in association with information that identifies the input field when the user inputs a character string in the input field, and is the character string information obtained by dividing or integrating the information. When a character string judged to be similar is registered in the candidate dictionary, the character string information or a character string registered in the candidate dictionary and similar to the character string information is presented as a candidate for input information. Information processing device. The information processing device according to any one of claims 1 to 5.
The extraction means extracts character string information by optical character recognition and obtains character string information.
The dividing means is an information processing device that divides or integrates the extracted character string information based on a rule related to position information in the document information including the character string information extracted by the extracting means. An information processing device that assists the user in inputting information into a predetermined input field.
An acquisition method for acquiring document information obtained by scanning,
An extraction means for extracting character string information from the acquired document information by character recognition processing,
A division / integration means that divides or integrates the extracted character string information based on a predetermined rule, and
A means for presenting information specifying each of the input fields as an input destination candidate for each part of the character string information obtained by dividing or integrating the information.
A program that functions as.

Images