Information processing device, information processing method, and program

Abstract

To make it easier for users to understand what factors are causing the text to be ambiguous. [Solution] The system includes an acquisition unit 141 that acquires target string data containing the target string to be checked for ambiguity, an acceptance unit 142 that accepts the specification of a threshold for determining whether or not the target string is ambiguous for each of the multiple types of ambiguity, an identification unit 143 that identifies the degree of ambiguity of the target string for each of the multiple types, and an output unit 145 that outputs information indicating that the target string is ambiguous for types where the degree of ambiguity is above the threshold.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] Techniques for assisting the work of correcting ambiguous expressions in a text have been proposed. For example, Patent Document 1 describes extracting, from a document, a sentence or a part of a sentence containing an ambiguous word stored in a storage device as an ambiguous part.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The ambiguity of a text is caused by multiple factors such as inappropriate use of particles and absence of a described subject. In the invention described in Patent Document 1, there was a problem that the user could not grasp what factors made the text ambiguous.

[0005] The present invention has been made in view of the above problems, and an object thereof is to provide an information processing apparatus, an information processing method, and a program that enable a user to easily grasp what factors make a text ambiguous.

Means for Solving the Problems

[0006] An information processing device according to a first aspect of the present invention includes: an acquisition unit that acquires target string data including a target string to be checked for ambiguity; a reception unit that accepts the specification of a threshold for determining whether or not the target string is ambiguous for each of a plurality of types of ambiguity; an identification unit that identifies the degree of ambiguity of the target string for each of the plurality of types; and an output unit that outputs information indicating that the target string is ambiguous for the type in which the degree of ambiguity is equal to or greater than the threshold.

[0007] The receiving unit may further accept the specification of an overall threshold for determining whether the target string is overall ambiguous, the identifying unit may further identify the overall ambiguity of the target string, and the output unit may output information indicating that the string is ambiguous in at least one of the multiple categories, provided that the overall ambiguity identified by the identifying unit is equal to or greater than the overall threshold.

[0008] The output unit may output information indicating that the overall ambiguity is not ambiguous in all of the multiple categories, but is ambiguous overall, if the overall ambiguity identified by the identification unit is equal to or greater than the overall threshold, and the ambiguity is not ambiguous in all of the multiple categories.

[0009] The aforementioned target string is included in the claims or specification of the patent document, and the identifying section may, if the target string is included in the claims, specify the degree of ambiguity for each constituent element described in the claims, and if the target string is included in the specification, specify the degree of ambiguity for each sentence described in the specification.

[0010] The target string is included in the claims or specification of the patent document, and the receiving unit may accept the specification of the threshold for each of the multiple types for each of the claims and the specification. The identifying unit may specify the degree of ambiguity of the target string for each first range if the target string does not contain a demonstrative pronoun, and may specify the degree of ambiguity of the target string for each second range which is wider than the first range if the target string contains a demonstrative pronoun.

[0011] The identification unit may determine the ambiguity of the target string based on whether or not there is a string corresponding to the demonstrative pronoun in the sentence preceding the sentence containing the demonstrative pronoun, if the target string contains a demonstrative pronoun. The output unit may output an image indicating the multiple types of ambiguity in association with the target string.

[0012] A program according to a second aspect of the present invention causes a computer to perform the following steps: acquire target string data including a target string to be checked for ambiguity; accept the specification of a threshold for determining whether the target string is ambiguous for each of a plurality of types of ambiguity; identify the degree of ambiguity of the target string for each of the plurality of types; and output information indicating that the target string is ambiguous for the type in which the degree of ambiguity is equal to or greater than the threshold.

[0013] A third aspect of the present invention is an information processing method comprising the steps of: obtaining target string data, which includes a target string to be checked for ambiguity, to be executed by a computer; receiving the specification of a threshold for determining whether or not the target string is ambiguous for each of a plurality of types of ambiguity; identifying the degree of ambiguity of the target string for each of the plurality of types; and outputting information indicating that the target string is ambiguous for the type in which the degree of ambiguity is equal to or greater than the threshold. [Effects of the Invention]

[0014] According to the present invention, it is possible to make it easier for users to understand what factors are causing the ambiguity in the text. [Brief explanation of the drawing]

[0015] [Figure 1] This document outlines the information processing device of this embodiment. [Figure 2] This shows the configuration of the information processing device. [Figure 3] An example of a screen for specifying a threshold is shown. [Figure 4] This example shows how the output unit outputs information indicating that the target string is ambiguous in categories 1 through 3. [Figure 5] An example of a graph image showing the ambiguity level for each type of target string is shown. [Figure 6] This flowchart shows the processing procedure for outputting ambiguity values ​​by an information processing device. [Modes for carrying out the invention]

[0016] [Overview of Information Processing Equipment] Figure 1 shows an overview of the information processing device 100 of this embodiment. The information processing device 100 is for checking ambiguous expressions in strings. The information processing device 100 is, for example, a personal computer. The information processing device 100 acquires target string data, which is text data of a document containing the target string to be checked for ambiguity. For example, the information processing device 100 acquires this target string data when the user specifies the folder in which the target string data is stored and the file name of the target string data. The document is, for example, a patent document including the specification and claims. The target string is a string contained in the sentence, paragraph, or page, etc., that is to be checked for ambiguity.

[0017] The information processing device 100 accepts user input to specify a threshold for determining whether a target string is ambiguous or not. The information processing device 100 accepts user input to specify a threshold for each of several types of ambiguity. The types of ambiguity include, for example, the absence of a subject, the inappropriate use of particles ("te", "ni", "wo", "wa", etc.), or unclear grammatical relationships.

[0018] The information processing apparatus 100 specifies the degree of ambiguity of the target character string included in the acquired target character string data for each of a plurality of types of ambiguity. The information processing apparatus 100 determines whether or not the degree of ambiguity of each specified type is equal to or greater than the threshold value corresponding to that type. When the information processing apparatus 100 determines that the degree of ambiguity of the target character string is equal to or greater than the threshold value in any one of the plurality of types, the information processing apparatus 100 outputs determination result information indicating that the target character string is ambiguous in this type to the display unit.

[0019] By outputting the determination result information indicating that the target character string is ambiguous in the type where the specified degree of ambiguity is equal to or greater than the threshold value, the information processing apparatus 100 enables the user to easily grasp what factors make the sentence ambiguous.

[0020] [Configuration of Information Processing Apparatus 100] FIG. 2 shows the configuration of the information processing apparatus 100. The information processing apparatus 100 includes an operation unit 11, a display unit 12, a storage unit 13, and a control unit 14. The control unit 14 includes an acquisition unit 141, a reception unit 142, a specification unit 143, a determination unit 144, and an output unit 145.

[0021] The operation unit 11 is, for example, a touch panel or a keyboard. The operation unit 11 receives a user's operation. The operation unit 11 inputs the received information to the acquisition unit 141 and the reception unit 142. The display unit 12 is a display for displaying various types of information. The display unit 12 displays the information output from the output unit 145.

[0022] The memory unit 13 is a storage medium including ROM (Read Only Memory) and RAM (Random Access Memory). The memory unit 13 stores the program executed by the control unit 14. The memory unit 13 stores a trained machine learning model that takes a string as input data and outputs the first type of ambiguity, the second type of ambiguity, the third type of ambiguity, and an overall ambiguity of the string. The machine learning model may output one or two types of ambiguity, or it may output four or more types of ambiguity. This machine learning model is referenced by the identification unit 143 to identify one or more types of ambiguity.

[0023] The control unit 14 is, for example, a CPU (Central Processing Unit). The control unit 14 functions as an acquisition unit 141, a reception unit 142, a identification unit 143, a determination unit 144, and an output unit 145 by executing a program stored in the storage unit 13.

[0024] The acquisition unit 141 acquires various types of information entered by the user via the operation unit 11. For example, the acquisition unit 141 acquires target string data that indicates a document containing the target string to be checked for ambiguity. This document is, for example, a patent document such as the claims or specification. The acquisition unit 141 also acquires target string data contained in a document specified by the user from among multiple documents stored in the storage unit 13. For example, the acquisition unit 141 acquires this target string data when the user specifies the folder where the target string data is stored and the file name of the target string data. The acquisition unit 141 outputs the acquired target string data to the identification unit 143.

[0025] The reception unit 142 receives user input via the operation unit 11. The reception unit 142 accepts the specification of a threshold for determining whether a target string is ambiguous for each of the multiple types of ambiguity. For example, the reception unit 142 accepts the specification of a first threshold for determining whether a target string is ambiguous in the first type. The first type of ambiguity is, for example, an expression that is ambiguous because the subject is not stated.

[0026] Similarly, the reception unit 142 accepts the specification of a second threshold for determining whether the target string is ambiguous in the second type, and a third threshold for determining whether the target string is ambiguous in the third type. The second type of ambiguity is, for example, an ambiguous expression due to the inappropriate use of particles ("te", "ni", "wo", "wa", etc.). The third type of ambiguity is, for example, an ambiguous expression due to excessively long modifiers.

[0027] The receiving unit 142 may accept one or more of the first to third thresholds, as well as a fourth threshold for determining whether the target string is ambiguous in a fourth category. The fourth category of ambiguity is, for example, ambiguous dependency. Ambiguous dependency means that the relationship between the subject and the predicate is ambiguous, or that the relationship between the modifier and the word it modifies is ambiguous.

[0028] The receiving unit 142 may accept one or more of the first to fourth thresholds, as well as a fifth threshold for determining whether the target string is ambiguous in a fifth category. The fifth category of ambiguity is, for example, ambiguity in which it is unclear which term a demonstrative pronoun refers to.

[0029] The reception unit 142 may accept one or more of the first to fifth thresholds, as well as a sixth threshold for determining whether the target string is ambiguous in a sixth category. The sixth category of ambiguity is, for example, ambiguity due to the entire text being meaningless. The entire text being meaningless means that it contains expressions that do not fall under the first to fifth categories and make the entire text ambiguous. One example of the entire text being meaningless is the frequent use of languages ​​other than Japanese. The reception unit 142 further accepts the specification of an overall threshold for determining whether the target string is ambiguous overall.

[0030] Figure 3 shows an example of a screen for specifying a threshold. At the top of Figure 3, there is a bar for setting the overall threshold. When the reception unit 142 receives a user operation by sliding a circular knob on this bar left or right, the overall threshold is adjusted. In the example in Figure 3, the overall threshold can be set to a value between 0.00 and less than 1.00.

[0031] In the lower left of Figure 3, there is a bar for setting the first threshold. When the user slides the round knob on this bar left or right, the first threshold is adjusted. In the example in Figure 3, the first threshold can be set to a value between 0.00 and 1.00. In the example in Figure 3, 0.50 is set as the first threshold. In the lower center of Figure 3, there is a bar for setting the second threshold. In the example in Figure 3, the second threshold can be set to a value between 0.00 and 1.00. In the example in Figure 3, 0.75 is set as the second threshold. In the lower right of Figure 3, there is a bar for setting the third threshold. In the example in Figure 3, 0.35 is set as the third threshold. The third threshold can be set to a value between 0.00 and 1.00.

[0032] In patent documents, the expression of the claims defines the scope of the patent rights, and therefore is often checked for ambiguity more strictly than the specification. For this reason, when the document indicated by the target string data acquired by the acquisition unit 141 is a patent document that includes both the claims and the specification, the receiving unit 142 may accept the specification of threshold values ​​for each of multiple types of claims and specifications. In this case, the receiving unit 142 may accept a threshold value for the claims that is higher than the threshold value for the specification. In this way, the receiving unit 142 can check whether the expression of the claims is ambiguous more strictly than the check whether the expression of the specification is ambiguous.

[0033] The receiving unit 142 may accept the specifications of the first to third thresholds and the overall threshold at the same time that the acquisition unit 141 acquires the target string data, or it may accept the specifications of the first to third thresholds and the overall threshold in advance before the acquisition unit 141 acquires the target string data. The receiving unit 142 stores the accepted first threshold, second threshold, third threshold and overall threshold in the storage unit 13. The receiving unit 142 may also output the first threshold, second threshold, third threshold and overall threshold to the determination unit 144.

[0034] [Identifying Ambiguity] The identification unit 143 identifies the degree of ambiguity of the target string for each of the multiple types of ambiguity. The identification unit 143 further identifies the overall degree of ambiguity of the target string. If the document containing the target string is a claim, the identification unit 143 identifies the degree of ambiguity for each claim described in the claim. If the document containing the target string is a specification, the identification unit 143 identifies the degree of ambiguity for each sentence described in the specification. If the document containing the target string is a specification, the identification unit 143 may also identify the degree of ambiguity for each paragraph of the specification.

[0035] The identification unit 143 divides the string contained in the target string data acquired by the acquisition unit 141 into multiple target strings. For example, the identification unit 143 divides the string contained in the target string data into multiple target strings for each number of target strings corresponding to the type of document corresponding to the target string data.

[0036] For example, if the target string data is the string data of a patent specification, the identification unit 143 divides the strings contained in the specification into multiple target strings so that each sentence in the specification becomes one target string. If the target string data is the string data of the claims of a patent, the identification unit 143 divides the strings contained in the target string data into multiple target strings so that each constituent element described in the claims becomes one target string. Constituent elements are elements that make up an invention, and in the claims of a patent, each constituent element is often on a separate line. Therefore, the identification unit 143 identifies multiple constituent elements based on the line break symbols contained in the claim.

[0037] The identification unit 143 identifies the degree of ambiguity of the target string for each of the multiple types of ambiguity. For example, the identification unit 143 identifies the degree of ambiguity of the first type of ambiguity of the target string. Similarly, the identification unit 143 identifies the degree of ambiguity of the second type and the degree of ambiguity of the third type of ambiguity of the target string. The identification unit 143 may identify a fourth type of ambiguity in addition to one or more of the first to third types of ambiguity. The identification unit 143 may identify a fifth type of ambiguity in addition to one or more of the first to fifth types of ambiguity. The identification unit 143 further identifies the overall degree of ambiguity of the target string.

[0038] More specifically, the identification unit 143 inputs the target string after splitting into a trained machine learning model that takes a string as input data and outputs the first type of ambiguity, the second type of ambiguity, the third type of ambiguity, and the overall ambiguity of the string as output data. The identification unit 143 identifies the first type of ambiguity, the second type of ambiguity, the third type of ambiguity, and the overall ambiguity output by the machine learning model as the first type of ambiguity, the second type of ambiguity, the third type of ambiguity, and the overall ambiguity of the target string, respectively. Similarly, the identification unit 143 may use the trained machine learning model to identify one or more of the fourth type of ambiguity, the fifth type of ambiguity, or the sixth type of ambiguity of the target string.

[0039] Furthermore, the identification unit 143 is not limited to cases where the ambiguity of the target string is determined by a machine learning model. For example, the identification unit 143 may determine the ambiguity of the target string by morphological analysis.

[0040] [Identifying ambiguity regarding demonstrative pronouns] The identification unit 143 may further identify a fifth type of ambiguity, which is an ambiguous expression because it is unclear which term the demonstrative pronoun refers to. However, if the sentence containing the demonstrative pronoun is different from the sentence containing the term that the demonstrative pronoun refers to, the identification unit 143 may not be able to identify an appropriate level of ambiguity even if it identifies the fifth type of ambiguity for each sentence. For this reason, the identification unit 143 may, when the target string contains a demonstrative pronoun, identify the ambiguity of the target string based on whether or not there is a string corresponding to the demonstrative pronoun in a sentence preceding the sentence containing the demonstrative pronoun.

[0041] For example, if the target string does not contain a demonstrative pronoun, the identification unit 143 identifies at least one type of ambiguity for each of the multiple target strings within a first range. The first range is, for example, a string obtained by dividing a document into periods.

[0042] The identification unit 143 identifies at least one type of ambiguity for each second range for multiple target strings when the target string contains a demonstrative pronoun. The second range is wider than the first range. The second range is, for example, a range that includes multiple sentences.

[0043] When the identification unit 143 identifies the ambiguity of target strings for each type in order from the beginning of the document, it may set the second range so that the second range for identifying the ambiguity of the current target string and the second range for identifying the ambiguity of the next target string partially overlap. In this way, the identification unit 143 can improve the accuracy of identifying the ambiguity of the fifth type, which is an ambiguous expression because it is not clear which term the demonstrative pronoun refers to. The identification unit 143 outputs the ambiguity of each identified type and the overall ambiguity to the determination unit 144.

[0044] [Determining whether the ambiguity is above a certain threshold] The determination unit 144 determines whether multiple target strings are ambiguous in each category. For example, the determination unit 144 determines that a target string is ambiguous in the first category if the ambiguity of any of the multiple target strings identified by the identification unit 143 is equal to or greater than the first threshold. On the other hand, the determination unit 144 determines that a target string is not ambiguous in the first category if the ambiguity of the first category of this target string is less than the first threshold.

[0045] Similarly, the determination unit 144 determines that a target string is ambiguous in the second category if the ambiguity of the second category of any of the target strings identified by the identification unit 143 is equal to or greater than the second threshold. On the other hand, the determination unit 144 determines that a target string is not ambiguous in the second category if the ambiguity of the second category of this target string is less than the second threshold. The determination unit 144 makes similar determinations for the third, fourth, fifth, and sixth categories.

[0046] The determination unit 144 determines that a target string is generally ambiguous if the overall ambiguity of any of the target strings identified by the identification unit 143 is equal to or greater than the overall threshold. On the other hand, the determination unit 144 determines that a target string is not generally ambiguous if the overall ambiguity of the target string is less than the overall threshold.

[0047] In this way, the determination unit 144 determines whether the ambiguity of each type of target string is equal to or greater than the threshold specified by the user for that type. Therefore, if the user specifies the threshold for each type according to the level required in the document created by the user, the determination unit 144 can automatically determine whether the representation of the target string included in the document created by the user is ambiguous for each type.

[0048] The determination unit 144 determines, if the document indicated by the target string data acquired by the acquisition unit 141 is a patent document including the claims and the specification, whether the ambiguity of any of the multiple types of target strings included in the claims is equal to or greater than the threshold value corresponding to that type received for the claims. The determination unit 144 also determines, whether the ambiguity of any of the multiple types of target strings included in the specification is equal to or greater than the threshold value corresponding to that type received for the specification.

[0049] [Output of various types of information] The output unit 145 outputs various information to the display unit 12. The output unit 145 outputs judgment result information indicating that the target string is ambiguous in the type of ambiguity that the judgment unit 144 has determined to be equal to or greater than a threshold.

[0050] The output unit 145 outputs information indicating that the target string is ambiguous in the first category if the determination unit 144 determines that the ambiguity of the first category of any of the target strings included in the corresponding string data is equal to or greater than the first threshold. On the other hand, the output unit 145 does not output information indicating that the target string is ambiguous in the first category if the determination unit 144 determines that the ambiguity of the first category of any of the target strings included in the corresponding string data is less than the first threshold.

[0051] The output unit 145 processes the case where the determination unit 144 determines that the ambiguity of the second, third, fourth, fifth, or sixth type is equal to or greater than the second, third, fourth, fifth, or sixth threshold, respectively, in the same way as when the determination unit 144 determines that the ambiguity of the first type of the target string is equal to or greater than the first threshold. The output unit 145 also processes the case where the determination unit 144 determines that the ambiguity of the second, third, fourth, fifth, or sixth type is less than the second, third, fourth, fifth, or sixth threshold, respectively, in the same way as when the determination unit 144 determines that the ambiguity of the first type of the target string is less than the first threshold.

[0052] The output unit 145 outputs information indicating that the string is ambiguous in at least one of several categories, provided that the determination unit 144 determines that the overall ambiguity identified by the identification unit 143 is equal to or greater than the overall threshold. Figure 4 shows an example in which the output unit 145 outputs information indicating that the target string is ambiguous in the first to third categories. Multiple target strings are shown on the left side of Figure 4.

[0053] As shown in the second constituent element from the top of Claim 1 in Figure 4, the output unit 145 outputs that the target string "a) Input unit receiving the input," is "normal" if its overall ambiguity is less than the overall threshold, regardless of the ambiguity values ​​in the first to third categories. In this case, the output unit 145 does not output that the target string has "first-category ambiguity (no subject)", "second-category ambiguity (inappropriate particle)", or "third-category ambiguity (long modifier)".

[0054] As shown in the first constituent element from the top of Claim 1 in Figure 4, the output unit 145 outputs that the target string "a display system that receives input via a user interface, processes data based on said input and projects it onto a screen," has "first type ambiguity (no subject)" if the overall ambiguity of the target string is equal to or greater than the overall threshold, the first type of ambiguity of the target string is equal to or greater than the first threshold, the second type of ambiguity of the target string is less than the second threshold, and the third type of ambiguity of the target string is less than the third threshold. In this case, the output unit 145 does not output that the target string has "second type ambiguity (inappropriate particle)" nor does it output that the target string has "third type ambiguity (long modifier)".

[0055] As shown in the second constituent element from the top of Claim 2 in Figure 4, the output unit 145 outputs that the target string "A computer system characterized in that the processing module includes a function to project an image filtered based on the input onto a subscreen." has an overall ambiguity of at least the overall threshold, a first type of ambiguity of the target string is less than the first threshold, a second type of ambiguity of the target string is at least the second threshold, and a third type of ambiguity of the target string is at least the third threshold, in which case the output unit 145 outputs that the target string has "second type of ambiguity (inappropriate particle)" and "third type of ambiguity (long modifier)".

[0056] The output unit 145 does not output information indicating ambiguity in each category if the target string contains ambiguous expressions in one of several categories, but the target string is clear overall. Therefore, the output unit 145 can suppress an increase in the number of places where it notifies the user that an expression is ambiguous in one of the categories, even though no correction is necessary.

[0057] The output unit 145 outputs information indicating that the target string is ambiguous in the "other" category if the overall ambiguity identified by the identification unit 143 is equal to or greater than the overall threshold and is not ambiguous in all of the multiple categories. As shown in the third constituent element from the top of Claim 1 in Figure 4, the output unit 145 outputs that the target string is ambiguous in the "other" category if the overall ambiguity of the target string "b) a processing unit that processes data based on the input, and " is equal to or greater than the overall threshold, the ambiguity of the first category of this target string is less than the first threshold, the ambiguity of the second category of this target string is less than the second threshold, and the ambiguity of the third category of this target string is less than the third threshold.

[0058] In this case, the output unit 145 does not output that the target string has "Type 1 ambiguity (no subject)", "Type 2 ambiguity (inappropriate particle)", or "Type 3 ambiguity (long modifier)". In this way, if the target string does not contain any ambiguous expressions in Type 1, Type 2, or Type 3, but is unclear overall, the output unit 145 outputs information indicating that the target string is unclear in the "Other" category. Therefore, when the reason why the target string is unclear cannot be identified, the output unit 145 can make the user aware that the target string is unclear in a category other than Type 1, Type 2, or Type 3.

[0059] The output unit 145 outputs an image showing multiple types of ambiguity in association with the target string. The image showing multiple types of ambiguity is, for example, a graph image showing multiple types of ambiguity. Figure 5 shows an example of a graph image showing the ambiguity of each type of target string. The output unit 145 outputs the graph image of Figure 5 when the receiving unit 142 receives a user operation to select the image on the right corresponding to "c) a computer system characterized by comprising an output unit for projecting the processed data onto a screen" in the fourth constituent element from the top of Claim 1 in Figure 4.

[0060] In the example shown in Figure 5, the output unit 145 outputs bar graphs from left to right, showing the overall ambiguity of the target string (labeled "Overall" in Figure 5), the ambiguity of the first type, the ambiguity of the second type, and the ambiguity of the third type. The overall ambiguity and the ambiguity of the first to third types are each represented by numerical values ​​between 0.00 and 1.00. In this way, the output unit 145 outputs graph images of multiple types of ambiguity, making it easier for the user to understand the ambiguity of each type.

[0061] [Processing steps during machine learning model training] The following describes the processing steps during training of a machine learning model for identifying ambiguity. The identification unit 143 creates training data for multiple target strings, associating the target string with the first type of ambiguity of the target string determined by an expert in the field of written expression, the second type of ambiguity of the target string determined by the same expert, the third type of ambiguity of the target string determined by the same expert, and the overall ambiguity of the target string determined by the same expert.

[0062] The identification unit 143 trains the machine learning model with multiple training data sets created, thereby generating a trained machine learning model that takes a string as input data and outputs the first type of ambiguity, the second type of ambiguity, the third type of ambiguity, and the overall ambiguity of the string. The identification unit 143 stores the generated machine learning model in the storage unit 13 before the acquisition unit 141 acquires the target string data.

[0063] [Example where the information processing device 100 is a server] The information processing device 100 is not limited to being a personal computer. For example, the information processing device 100 may be a server. The receiving unit 142 of the information processing device 100 may communicate with a personal computer that has received a user operation to specify thresholds for each type of ambiguity, and may receive information from this personal computer indicating the specified multiple thresholds. The output unit 145 of the information processing device 100 may output to the user's personal computer determination result information indicating that the target string is ambiguous in any of the multiple types if it determines that the ambiguity of the target string is greater than or equal to a threshold for that type.

[0064] [Processing procedure for outputting ambiguity by the information processing device 100] Figure 6 is a flowchart showing the processing procedure for outputting ambiguity by the information processing device 100. This processing procedure begins, for example, when the reception unit 142 receives an operation from a user to launch an application for outputting ambiguity.

[0065] First, the reception unit 142 accepts the specification of an overall threshold for determining whether the target string is ambiguous overall. The reception unit 142 accepts the specification of a threshold for determining whether the target string is ambiguous for each of the multiple types of ambiguity (S101). The acquisition unit 141 determines whether or not it has acquired target string data indicating a document containing multiple target strings that are subject to ambiguity check (S102).

[0066] If the target string data is acquired by the acquisition unit 141 (YES in S102), the identification unit 143 divides the acquired target string data into multiple target strings (S103). The identification unit 143 identifies the overall ambiguity of one of these multiple target strings (S104). The identification unit 143 identifies the ambiguity of this target string by type (S105). The output unit 145 generates a graph image showing the ambiguity of this target string by type (S106). The output unit 145 determines whether there is another target string whose ambiguity has not been identified by the identification unit 143 (S107).

[0067] The output unit 145, when there are no more target strings whose ambiguity has not been identified by the ambiguity identification unit 143 (NO in S107), outputs determination result information indicating that the target string is ambiguous in one of the target string types, associated with each of the multiple target strings, and a graph image showing the ambiguity for each target string type (S108), and then terminates the process.

[0068] If the acquisition unit 141 has not acquired the target string data in the determination in S102 (NO in S102), it repeats the process in S102. If the output unit 145 has determined in S107 that there is another target string whose ambiguity has not been determined by the ambiguity determination unit 143 (YES in S107), it returns to the process in S104.

[0069] [Effects of the information processing device 100 of this embodiment] The output unit 145 outputs information indicating that the target string is ambiguous for categories where the ambiguity level identified by the identification unit 143 is above a threshold. In this way, the output unit 145 makes it easier for the user to understand what factors are causing the text to be ambiguous.

[0070] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of its gist. For example, all or part of the apparatus can be configured by functionally or physically distributing and integrating in any unit. Furthermore, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effects of the new embodiments resulting from the combinations are combined with the effects of the original embodiments. [Explanation of Symbols]

[0071] 11 Control section 12 Display section 13 Storage section 14 Control Unit 100 Information Processing Devices 141 Acquisition Department 142 Reception Department 143 Specific section 144 Judgment section Output section of 145

Claims

1. A unit for obtaining target string data that includes the target string to be checked for ambiguity, A receiving unit that accepts the specification of a threshold for determining whether the target string is ambiguous for each of the multiple types of ambiguity, For each of the aforementioned multiple types, there is an identification unit that identifies the degree of ambiguity of the target string, An output unit that outputs information indicating that the target string is ambiguous in the category where the ambiguity is equal to or greater than the threshold, An information processing device equipped with the following features.

2. The receiving unit further receives the specification of an overall threshold for determining whether the target string is ambiguous overall, The aforementioned identification unit further identifies the overall ambiguity of the target string, The output unit outputs information indicating that the information is ambiguous in at least one of the multiple categories, provided that the overall ambiguity identified by the identification unit is equal to or greater than the overall threshold. The information processing apparatus according to claim 1.

3. The output unit outputs information indicating that the overall ambiguity is not ambiguous in all of the multiple categories, but is ambiguous overall, when the overall ambiguity identified by the identification unit is equal to or greater than the overall threshold, and the ambiguity is not ambiguous in all of the multiple categories. The information processing apparatus according to claim 2.

4. The aforementioned target string is included in the claims or specification of the patent document, The identifying unit, if the target string is included in the claims, identifies the degree of ambiguity for each constituent element described in the claims, and if the target string is included in the specification, identifies the degree of ambiguity for each sentence described in the specification. The information processing apparatus according to claim 1.

5. The aforementioned target string is included in the claims or specification of the patent document, The receiving unit accepts the specification of the threshold for each of the multiple categories for each of the claims and the specification. The information processing apparatus according to claim 1.

6. The identifying unit identifies the degree of ambiguity of the target string for each first range if the target string does not contain a demonstrative pronoun, and identifies the degree of ambiguity of the target string for each second range that is wider than the first range if the target string does contain a demonstrative pronoun. The information processing apparatus according to claim 1.

7. The identification unit determines the degree of ambiguity of the target string based on whether or not there is a string corresponding to the demonstrative pronoun in the sentence preceding the sentence containing the demonstrative pronoun, if the target string contains a demonstrative pronoun. The information processing apparatus according to claim 6.

8. The output unit outputs an image indicating the multiple types of ambiguity in association with the target string. The information processing apparatus according to claim 1.

9. On the computer, The steps include obtaining target string data that includes the target string to be checked for ambiguity, A step of accepting the specification of a threshold for determining whether the target string is ambiguous for each of several types of ambiguity, For each of the aforementioned multiple types, the step of determining the degree of ambiguity of the target string, A step of outputting information indicating that the target string is ambiguous in the category where the ambiguity is equal to or greater than the threshold, A program that executes the command.

10. A computer executes The steps include obtaining target string data that includes the target string to be checked for ambiguity, A step of accepting the specification of a threshold for determining whether the target string is ambiguous for each of several types of ambiguity, For each of the aforementioned multiple types, the step of determining the degree of ambiguity of the target string, A step of outputting information indicating that the target string is ambiguous in the category where the ambiguity is equal to or greater than the threshold, An information processing method having

Images