Information processing device, structuring method, and program

Abstract

In order to obtain a valid structuring result for a sentence that lacks at least one among a subject and an object, this information processing device (1) comprises: a classification unit (11) for classifying a sentence according to the content thereof; an estimation unit (12) for applying an estimation method corresponding to the result of the classification and estimating at least one among the subject and the object of the sentence; and a structuring unit (13) for structuring the sentence on the basis of the result of the estimation.

Description

Information processing device, structuring method, and recording medium

[0001] The present invention relates to an information processing device or the like that performs natural language processing.

[0002] In the field of natural language processing, there is a technology for automatically analyzing the relationships between elements that make up a sentence. For example, Patent Document 1 listed below describes a method for extracting predicates from a source document written in natural language, extracting phrases related to the predicates, and generating relationship information that indicates the relationships between them.

[0003] International Publication No. 2017 / 119060

[0004] The technology of Patent Document 1 is based on the premise that a sentence contains a predicate and also contains phrases such as a subject and an object that are related to the predicate. However, in sentences written in natural language, some elements such as the subject or object may be omitted. Therefore, the technology of Patent Document 1 has difficulty obtaining appropriate relational information, i.e., structuring results, for sentences that lack some elements.

[0005] One aspect of the present invention has been made in consideration of the above-mentioned problems, and one example of its purpose is to provide an information processing device, etc. that is capable of obtaining valid structuring results even for sentences that lack at least one of a subject and an object.

[0006] An information processing device according to one aspect of the present invention includes a classification means for classifying sentences according to their contents, an estimation means for estimating at least one of a subject and an object of the sentence by applying an estimation method according to the result of the classification, and a structuring means for structuring the sentence based on the result of the estimation.

[0007] A structuring method according to one aspect of the present invention includes at least one processor classifying sentences according to their content, applying a predetermined estimation method according to the results of the classification to estimate at least one of the subject and object of the sentences, and structuring the sentences based on the results of the estimation.

[0008] A recording medium according to one aspect of the present invention is a computer-readable recording medium that records a structuring program that causes a computer to function as a classification means that classifies sentences according to their content, an estimation means that estimates at least one of the subject and object of the sentence by applying a predetermined estimation method according to the results of the classification, and a structuring means that structures the sentence based on the results of the estimation.

[0009] According to one aspect of the present invention, it is possible to obtain a valid structuring result even for a sentence that lacks at least one of a subject and an object.

[0010] 1 is a block diagram showing the configuration of an information processing device according to a first exemplary embodiment of the present invention. FIG. 2 is a flow diagram showing the flow of a structuring method according to the first exemplary embodiment of the present invention. FIG. 3 is a block diagram showing the configuration of an information processing device according to a second exemplary embodiment of the present invention. FIG. 4 is a diagram showing an example of structuring a sentence by an information processing device according to a second exemplary embodiment of the present invention and displaying the results as a graph. FIG. 5 is a flow diagram showing the flow of processing executed by an information processing device according to a second exemplary embodiment of the present invention. FIG. 6 is a diagram showing an example of element extraction by an element string extraction unit and an example of display of the extraction results. FIG. 7 is a diagram explaining processing related to an element classification unit and an element extraction unit. FIG. 8 is a flow diagram showing the flow of processing for identifying correspondence with documents. FIG. 9 is a diagram showing an example of display of identification results of correspondence between a structured sentence and research materials showing detection results of a predetermined vehicle by a vehicle detection system. FIG. 10 is a diagram showing an example of display of identification results of correspondence between elements of a structured sentence and locations shown in the research materials. FIG. 11 is a diagram showing an example of display of identification results of correspondence between a structured sentence and a call history shown in the research materials. FIG. 12 is a diagram showing an example of display of identification results of correspondence between a structured sentence and a deposit and withdrawal history shown in the research materials. FIG. 13 is a diagram showing an example of display of identification results of correspondence between a structured sentence and a deposit and withdrawal history shown in the research materials.

[0011] [First Exemplary Embodiment] A first exemplary embodiment of the present invention will be described in detail with reference to the drawings. This exemplary embodiment is a basic form of the exemplary embodiments described below.

[0012] (Configuration of Information Processing Apparatus) The configuration of an information processing apparatus 1 according to this exemplary embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing apparatus 1. As shown in the figure, the information processing apparatus 1 includes a classification unit 11, an estimation unit 12, and a structuring unit 13.

[0013] The classification unit 11 classifies sentences according to their contents. For example, as will be described with reference to Fig. 3, the classification unit 11 may classify sentences according to their contents into imperative sentences, questions, greetings, sentences expressing emotions such as gratitude or apology, etc.

[0014] The estimation unit 12 estimates at least one of the subject and object of a sentence by applying an estimation method according to the classification result by the classification unit 11. For example, as will be described later in the section "Regarding an estimation method according to the classification result," the estimation unit 12 may perform at least one of a process of estimating the sender of a sentence classified as an imperative sentence as the subject of the sentence and a process of estimating the receiver of the sentence as the object of the sentence. Furthermore, the estimation unit 12 may estimate at least one of the subject and object of a sentence classified as a sentence other than an imperative sentence based on the sentences before and after the sentence.

[0015] The structuring unit 13 structures the sentence based on the result of the estimation by the estimation unit 12. For example, as will be described with reference to Fig. 3, the structuring unit 13 may use preset sentence analysis rules or analysis models to extract subjects, objects, and words indicating their relationship from the sentence to be structured. Furthermore, for example, the structuring unit 13 may also structure the sentence using a technology called OpenIE (Open Information Extraction).

[0016] As described above, the information processing device 1 according to this exemplary embodiment includes the classification unit 11 that classifies sentences according to their contents, the estimation unit 12 that estimates at least one of the subject and object of the sentence by applying an estimation method according to the result of classification by the classification unit 11, and the structuring unit 13 that structures the sentence based on the result of estimation by the estimation unit 12. Therefore, the information processing device 1 according to this exemplary embodiment has the effect of being able to obtain an appropriate structuring result even for a sentence that lacks at least one of the subject and object.

[0017] (Structuring Program) The functions of the information processing device 1 described above can also be realized by a program. The structuring program according to this exemplary embodiment is configured to cause a computer to function as a classification means for classifying sentences according to their content, an estimation means for estimating at least one of the subject and object of the sentence by applying a predetermined estimation method according to the results of the classification, and a structuring means for structuring the sentence based on the results of the estimation. Furthermore, a recording medium according to this exemplary embodiment is a computer-readable recording medium on which the structuring program is recorded. Therefore, the structuring program according to this exemplary embodiment or the recording medium according to this exemplary embodiment has the effect of enabling appropriate structuring results to be obtained even for sentences lacking at least one of the subject and the object.

[0018] (Flow of Structuring Method) The flow of the structuring method according to this exemplary embodiment will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of the structuring method. Note that the execution entity of each step in this structuring method may be a processor provided in the information processing device 1, or a processor provided in another device, or each step may be executed by a processor provided in a different device.

[0019] In S11, at least one processor classifies the sentences according to their content.

[0020] In S12, at least one processor applies a predetermined estimation method according to the result of the classification in S11 to estimate at least one of the subject and object of the sentence.

[0021] In S13, at least one processor structures the sentence based on the results of the estimation in S12.

[0022] As described above, the structuring method according to this exemplary embodiment includes at least one processor classifying sentences according to their contents, applying a predetermined estimation method according to the results of the classification to estimate at least one of the subject and object of the sentence, and structuring the sentence based on the estimation result. Therefore, the structuring method according to this exemplary embodiment has the effect of making it possible to obtain a valid structuring result even for a sentence that lacks at least one of the subject and object.

[0023] [Exemplary Embodiment 2] (Configuration of Information Processing Device) The configuration of an information processing device 2 according to this exemplary embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the configuration of the information processing device 2. The information processing device 2 is a device that has a function of structuring sentences. Note that the information processing device 2 may be a device whose main function is to structurize sentences, or may be a general-purpose device that also has other functions.

[0024] As shown in the figure, the information processing device 2 includes a control unit 20 that controls all the units of the information processing device 2, and a storage unit 21 that stores various data used by the information processing device 2. The information processing device 2 also includes a communication unit 22 that enables the information processing device 2 to communicate with other devices, an input unit 23 that receives various data input to the information processing device 2, and an output unit 24 that enables the information processing device 2 to output various data.

[0025] As shown in the figure, the control unit 20 of the information processing device 2 has a classification unit 201, an estimation unit 202, a structuring unit 203, a graph generation unit 204, an information presentation unit 205, an element string extraction unit 206, an element classification unit 207, an element extraction unit 208, and a relevance identification unit 209. The storage unit 21 stores a classification model 211, target data 212, and materials 213.

[0026] The element string extraction unit 206, the element classification unit 207, the element extraction unit 208, the relevance identification unit 209, and the document 213 will be described later with reference to Figures 6 to 12. The functions of each block from the storage unit 21 to the output unit 24 may be realized by a device built into the information processing device 2, or may be realized by a device external to the information processing device 2 that is attached to the information processing device 2.

[0027] The classification unit 201 classifies sentences included in the target data 212 according to their contents. The classification results of the classification unit 201 are used to determine the estimation method to be applied by the estimation unit 202. Therefore, the classification unit 201 classifies sentences included in the target data 212 into categories corresponding to the estimation methods applicable to the estimation unit 202. For example, when the estimation unit 202 applies either an estimation method for imperative sentences or an estimation method for sentences other than imperative sentences, the classification unit 201 classifies sentences included in the target data 212 into imperative sentences and other sentences. Note that imperative sentences are merely an example of a classification category. For example, the classification unit 201 may classify sentences included in the target data 212 into questions, greetings, sentences expressing emotions such as gratitude or apology, etc. Furthermore, the classification results of the classification unit 201 can also be used for searching or analyzing sentences included in the target data 212 or structuring results obtained by structuring the sentences.

[0028] The target data 212 is data including sentences to be structured. The target data 212 may be any data including sentences (expressed in natural language) to be structured. For example, the target data 212 may include sentences (which may also be called messages) sent or received via email or a social networking service (SNS). For sent or received sentences, data indicating the sender and receiver are also included in the target data 212.

[0029] The classification method applied by the classification unit 201 is not particularly limited. In this exemplary embodiment, an example will be described in which the classification unit 201 performs classification using a classification model 211. The classification model 211 is a trained model generated by machine learning to classify sentences. For example, the classification model 211 may be generated by learning using training data in which various sentences are associated with labels indicating classification categories according to their contents. The classification categories may include at least categories corresponding to each estimation method applicable to the estimation unit 202. For example, classification categories such as the above-mentioned command sentences and question sentences may be set. The information processing device 2 may also have a function to generate new training data. For example, the information processing device 2 may have a function to associate each sentence included in the target data 212 with a label indicating its classification to generate training data. Furthermore, the information processing device 2 may have a function to re-train the classification model 211 using new training data.

[0030] The estimation unit 202 estimates at least one of the subject and object of the sentence by applying an estimation method according to the classification result by the classification unit 201. Details of the estimation by the estimation unit 202 will be described later in the section "Regarding an estimation method according to the classification result."

[0031] The structuring unit 203 structures the sentence. For a sentence in which at least one of a subject and an object has been estimated by the estimation unit 202, the structuring unit 203 structures the sentence based on the estimation result. The structuring unit 203 may use the subject and object estimated by the estimation unit 202 as part of the structuring result as is, or may structure the sentence by supplementing the subject and object estimated by the estimation unit 202.

[0032] For example, suppose that the estimation unit 202 estimates that the subject of the sentence "I know" is "Person A" and the object is "Person B." In this case, the structuring unit 203 may apply the estimation result as is to generate a structured result (subject: Person A, relation: I know, object: Person B). Alternatively, the structuring unit 203 may add the estimated subject "Person A" before the sentence "I know" and add the estimated object "Person B" after the sentence to generate a sentence such as "Person A knows, Person B." The structuring unit 203 may then perform structuring on the sentence "Person A knows, Person B." Alternatively, the structuring unit 203 may add the estimated subject and object before the sentence "I know." Furthermore, the structuring unit 203 may add particles according to the subject and object. This makes it possible to generate a natural sentence such as "Person A knows Person B."

[0033] Structuring a sentence means dividing the sentence into its constituent elements and clarifying the relationships between the elements. Therefore, structuring unit 203 can also be described as an estimation means for estimating the relationships between the elements that make up a sentence, or an information generation means for generating information indicating the relationships between the elements included in a sentence.

[0034] Furthermore, the structuring method is not particularly limited. For example, the structuring unit 203 may use preset sentence analysis rules or analysis models to extract subjects, objects, and words indicating their relationship from sentences to be structured. The words indicating the relationship between the subject and object may be, for example, predicates. Furthermore, for example, the structuring unit 203 may structure sentences using OpenIE. By using OpenIE, it is possible to extract subjects, objects, and words indicating their relationship from sentences.

[0035] The graph generating unit 204 generates a graph showing the result of structuring by the structuring unit 203. For example, the graph generating unit 204 may generate a graph in which each element constituting a sentence is represented by a node, and the relationship between each element is represented by an edge connecting the nodes.

[0036] The information presentation unit 205 presents various pieces of information related to structuration to the user of the information processing device 2. For example, the information presentation unit 205 displays the graph generated by the graph generation unit 204 on a display device, thereby presenting the structuration results shown in the graph to the user. The display device may be included in the information processing device 2 or may be provided externally to the information processing device 2. The presentation mode of information by the information presentation unit 205 is not limited to display. The information presentation unit 205 may present the information to the user in a presentation mode other than display, such as audio output or printout, depending on the type and content of the information to be presented.

[0037] As described above, the information processing device 2 according to this exemplary embodiment includes the classification unit 201 that classifies sentences according to their contents, the estimation unit 202 that estimates at least one of the subject and object of the sentence by applying an estimation method according to the results of the classification, and the structuring unit 203 that structures the sentence based on the estimation result by the estimation unit 202. Therefore, the information processing device 2 according to this exemplary embodiment has the effect of being able to obtain an appropriate structuring result even for a sentence that lacks at least one of the subject and object.

[0038] (Regarding Estimation Method According to Classification Result) As described above, the estimation unit 202 estimates at least one of the subject and the object of a sentence by applying an estimation method according to the classification result by the classification unit 201. It is only necessary to determine in advance which estimation method the estimation unit 202 should apply depending on which classification result is obtained.

[0039] For example, in general, in an imperative sentence sent from a sender to a receiver, the sender is the entity that issued the command, and the receiver is often the one that received the command. Therefore, for a sentence classified as an imperative sentence by the classification unit 201, the estimation unit 202 may perform at least one of a process of estimating the sender of the sentence as the subject of the sentence and a process of estimating the receiver of the sentence as the object of the sentence. This allows for a valid estimation result and a valid structuring result. Furthermore, with this configuration, a valid estimation result can be obtained even when the target sentence does not have any surrounding sentences and the missing elements of the target sentence cannot be inferred from the surrounding sentences. Note that directive sentences, threatening sentences, etc. are also included in the category of the above-mentioned "imperative sentence."

[0040] On the other hand, for a sentence classified by the classification unit 201 as a sentence other than an imperative sentence, the estimation unit 202 may estimate at least one of the subject and the object based on the sentences before and after the sentence. The method for estimating the subject and the object based on the sentences before and after the sentence is not particularly limited. For example, the estimation unit 202 may estimate the omitted subject and the object using an estimation model that estimates at least one of the omitted subject and the object.

[0041] An estimation model for estimating an omitted subject can be generated by machine learning using training data that associates the omitted subject with a sentence in which the subject is omitted and the sentences before and after it. Furthermore, the input data to the estimation model can include not only the sentence in which the subject is omitted and the sentences before and after it, but also various data related to the omitted subject. For example, if the sentence to be structured is a message such as an email, an estimation model trained using input data including header information, such as information about the sender and recipient, can be used. Similarly, an estimation model for estimating an omitted object can also be generated.

[0042] Furthermore, consecutive sentences often have the same subject and object. Therefore, the estimation unit 202 may extract the subject and object from the sentence before or after the sentence in which at least one of the subject and object is omitted, and use the extracted subject and object as the estimation result. Note that, when extracting the subject and object in a sentence, a technique such as NER may be applied.

[0043] (Processing Example) Fig. 4 is a diagram showing an example in which a sentence is structured by the information processing device 2 and the results are displayed as a graph. In the example of Fig. 4, the sentence to be structured is a sentence sent from sender A to receiver B, and the body of the sentence is "Please submit it immediately." This sentence does not contain a subject, and does not state who it is to be submitted to, so it is difficult to structure this sentence as is.

[0044] When the above sentence is input to the information processing device 2 as target data 212, the classification unit 201 classifies the sentence. For example, the classification unit 201 inputs the above sentence to the classification model 211 and classifies the sentence based on the output value of the classification model 211. In the example of Fig. 4, the classification unit 201 classifies the above sentence as a command sentence.

[0045] Next, the estimation unit 202 estimates the subject and object of the above sentence. Because the above sentence is classified as an imperative sentence, the estimation unit 202 estimates that sender A is the subject of the sentence and receiver B is the object of the sentence.

[0046] The structuring unit 203 then structures the above sentence based on the estimation result. For example, the structuring unit 203 may use the subject and object estimated by the estimation unit 202 as the subject and object of the above sentence. The structuring unit 203 then extracts the character string "please submit," which is an element indicating the relationship between the subject and object supplemented by the estimation unit 202, from the above sentence. This results in a structured result of (subject: sender A, relationship: "please submit," object: receiver B).

[0047] After structuring is performed by structuring unit 203, graph generating unit 204 generates a graph showing the results of structuring by structuring unit 203. Then, information presenting unit 205 displays the generated graph. In this case, specifically, as shown in Fig. 4, a graph is generated and displayed in which a node indicating sender A, which is the subject, and a node indicating receiver B, which is the object, are connected by an edge indicating that sender A has instructed receiver B to "submit."

[0048] (Processing Flow) The processing flow executed by the information processing device 2 will be described with reference to Fig. 5. Fig. 5 is a flow diagram showing an example of processing executed by the information processing device 2.

[0049] In S21, the classification unit 201 acquires target data 212. The target data 212 may include, for example, multiple sentences that are related to each other. For example, messages sent and received by a specific person may be used as the target data 212. In this case, multiple sentences related to the person become the target data 212.

[0050] In S22, the classification unit 201 reads one sentence from the target data 212 acquired in S21. Subsequently, in S23, the classification unit 201 classifies the sentence read in S22 according to its content. For example, as described above, the classification unit 201 may perform classification using the classification model 211.

[0051] In S24, the estimation unit 202 estimates at least one of the subject and object of the sentence read out in S22 by applying a predetermined estimation method according to the result of classification in S23.

[0052] In S25, the structuring unit 203 structures the sentence read out in S22 based on the estimation result of S24. The structuring unit 203 may generate multiple structuring results from one sentence. For example, if the target sentence is "Corporation A is located in Tokyo, the capital of Japan," the structuring unit 203 may generate two structuring results: (subject: Corporation A, relation: there is, object: Tokyo) and (subject: capital of Japan, relation: is, object: Tokyo).

[0053] In S26, the classification unit 201 determines whether structuring has been completed for all sentences included in the target data 212 acquired in S21. If the determination in S26 is NO, the process returns to S22, and a new sentence is read from the target data 212. On the other hand, if the determination in S26 is YES, the process proceeds to S27.

[0054] In S27, the graph generation unit 204 generates a graph showing the structuring result of S25. Then, in S28, the information presentation unit 205 displays the graph generated in S27 on the display device. This completes the processing of FIG. 5.

[0055] Here, when structuring is performed on a plurality of related sentences, the graph generation unit 204 may connect the plurality of graphs via a node that is included in common in the plurality of graphs. For example, suppose that the graph generation unit 204 generates a graph in which a node called "subject 1" and a node called "object 1" are connected by an edge, and a graph in which a node called "subject 1" and a node called "object 2" are connected by an edge. In this case, the graph generation unit 204 may connect these graphs via the node called "subject 1" that is common to these graphs. As a result, a graph is generated in which a node called "object 1" and a node called "object 2" are connected via an edge to the node called "subject 1".

[0056] The process of Fig. 5 described above includes a structuring method according to this exemplary embodiment. That is, the structuring method according to this exemplary embodiment includes classifying sentences according to their contents (S23), inferring at least one of the subject and object of the sentence by applying a predetermined inference method according to the results of the classification in S23 (S24), and structuring the sentence based on the inference result in S24 (S25). This provides the effect of enabling appropriate structuring results to be obtained even for sentences lacking at least one of the subject and object.

[0057] (Element String Extraction Unit) This section describes the element string extraction unit 206. The element string extraction unit 206 extracts a series of elements associated with each other based on the structuring results and the classification results of the classification unit 201 from among the elements constituting the structured sentences. Note that the series of elements is represented as a series of nodes connected by edges in the graph generated by the graph generation unit 204. Therefore, it can be said that the element string extraction unit 206 extracts a series of nodes connected by edges. For example, the element string extraction unit 206 may extract one edge corresponding to a sentence classified by the classification unit 201 into a certain category (e.g., a command statement), and extract each element connected by the extracted edge. Then, for each extracted element, the element string extraction unit 206 may repeat the process of extracting other elements connected to that element by edges in the certain category until no new elements are extracted. This extracts a series of elements associated with each other based on the structuring results and the classification results.

[0058] In addition to the effects of the information processing device 1 according to the first exemplary embodiment, the information processing device 2 equipped with the element string extraction unit 206 can also achieve the effect of being able to extract a series of related elements by utilizing the classification results of each sentence. Note that the classification results of a sentence can also be considered as the classification results of the edges corresponding to that sentence. Therefore, it can be said that the element string extraction unit 206 extracts a series of related elements by utilizing the classification results of the edges.

[0059] When extracting a series of elements, the element string extraction unit 206 may accept specification of conditions for the extraction target. For example, the element string extraction unit 206 may accept specification of a category of sentences classified by the classification unit 201. In this case, the element string extraction unit 206 extracts a series of elements connected by edges from among the sentence elements of the specified category.

[0060] 6 is a diagram showing an example of element extraction by the element string extraction unit 206 and an example of displaying the extraction results. More specifically, Fig. 6 shows graph G1 generated by the graph generation unit 204 and graph G1' showing the element extraction results by the element string extraction unit 206. For example, a user can generate and display a graph such as graph G1 by inputting messages exchanged by persons A to D into the information processing device 2 as target data 212.

[0061] In the example of FIG. 6, it is assumed that after the graph G1 is displayed, a designation is made to extract elements contained in command statements. By making such a designation, it is possible to facilitate the task of inferring the chain of command between people. Furthermore, the classification unit 201 may classify command statements into subcategories such as instructions, threats, and orders. This makes it possible to designate extraction targets on a subcategory basis. For example, it is possible to extract elements corresponding to statements classified as orders. The designation may be received via the input unit 23 or the communication unit 22.

[0062] Upon receiving the above specification, the element string extraction unit 206 extracts, from the structuring results shown in graph G1, a series of elements connected by edges from among the nodes and edges corresponding to the statements classified as imperative statements by the classification unit 201. Specifically, in the example of Fig. 6, the element string extraction unit 206 extracts each of the elements "Person A" to "Person D" and the edges connecting them (edges corresponding to the statements classified as imperative statements).

[0063] Graph G1' reflects this extraction result on graph G1. In graph G1', the nodes of "Person A" to "Person D" and the edges of the command statements connecting them are highlighted with thicker lines than the other nodes and edges. In this way, by highlighting the nodes corresponding to the extracted elements and the edges connecting those nodes on the graph, the extraction result can be recognized by the user. For example, from graph G1' shown in FIG. 6, it can be easily inferred that Person A is at the top of the chain of command, Persons C and D are at the bottom of the chain of command, and Person B is the intermediary between them. Note that the presentation format of the extraction result is not limited to this example, as long as it allows the user to recognize the extraction result.

[0064] (Element Classification Unit and Element Extraction Unit) This section describes the element classification unit 207 and the element extraction unit 208. The element classification unit 207 classifies each element constituting a sentence into a plurality of categories. These multiple categories may include a person category. The classification method is not particularly limited. For example, the element classification unit 207 may classify each element constituting a sentence by applying a method such as NER (Name Entity Recognition).

[0065] The element extraction unit 208 extracts elements associated with the plurality of elements classified into the person category from among the elements constituting the plurality of sentences each structured by the structuring unit 203 .

[0066] In this way, the information processing device 2 includes an element classification unit 207 that classifies each element constituting a sentence into a plurality of categories including at least the person category, and an element extraction unit 208 that extracts elements associated with the plurality of elements classified into the person category from among the elements constituting the plurality of sentences that have been structured.

[0067] According to the above configuration, it is possible to extract elements mentioned by multiple people. Elements mentioned by multiple people are elements that should be noted when investigating those people. Therefore, according to the information processing device 2, in addition to the effects achieved by the information processing device 1 according to the exemplary embodiment 1, it is possible to obtain an effect of facilitating an investigation targeting multiple people.

[0068] The processing flow related to the element classification unit 207 and the element extraction unit 208 will be described with reference to Fig. 7. Fig. 7 is a diagram for explaining the processing related to the element classification unit 207 and the element extraction unit 208. Fig. 7 shows a flow diagram illustrating an example of the processing related to the element classification unit 207 and the element extraction unit 208, and an example display of the extraction results by the element extraction unit 208. Note that the processing shown in Fig. 7 is performed after the structuring unit 203 has completed structuring a plurality of sentences and after the graph generation unit 204 has completed generating a graph based on the structuring results. It is also assumed that the graphs are connected as described in S27 of Fig. 5, i.e., connected via commonly included nodes.

[0069] 7, the element classification unit 207 classifies elements constituting a plurality of structured sentences into a plurality of categories including at least a person category. The processing of S31 and the subsequent steps may be executed in response to, for example, an input operation to instruct the execution of element extraction.

[0070] The classification of elements can be performed at any timing after the sentences have been structured and the elements contained in the sentences have been extracted, and may be performed, for example, after S25 in Fig. 5. If an input operation is performed to instruct the execution of element extraction after the elements have been classified, S31 is omitted and the processes of S32 to S34 are performed.

[0071] In S32, the element extraction unit 208 identifies elements classified into the person category from among the elements included in each sentence structured by the structuring unit 203, based on the classification result of S31. Then, in S33, the element extraction unit 208 extracts elements associated with multiple of the identified elements, i.e., elements connected by edges to multiple of the identified elements.

[0072] In S34, the information presenting unit 205 presents the extraction result of S33 to the user. For example, the information presenting unit 205 may present the extraction result of S33 to the user by displaying the extraction result on a graph generated by the graph generating unit 204.

[0073] Graph G2 shown in Fig. 7 shows an example of the extraction results by the element extraction unit 208. Of the elements shown in graph G2, the elements corresponding to the nodes "Person A" to "Person C" are all elements classified into the person category. Since "falsification of ledger books" is a node connected to these elements by an edge, it is extracted by the element extraction unit 208 and is displayed in a highlighted manner by the information presentation unit 205.

[0074] In this way, by highlighting and displaying the nodes extracted by the element extraction unit 208 on the graph, the user can recognize the extraction results of the element extraction unit 208. For example, from graph G2 shown in Fig. 7, it can be easily inferred that all of Persons A to C were involved in the falsification of the ledger. Note that the presentation mode of the extraction results is not limited to this example, and may be any mode that allows the user to recognize the extraction results.

[0075] Furthermore, the element extraction unit 208 may extract elements that satisfy other conditions in addition to the condition that the elements are associated with multiple elements classified into the person category. The other conditions can be set arbitrarily. For example, a condition that the elements include an element corresponding to a specific person may be set. In this case, elements that are mentioned by a specific person and also mentioned by other people are extracted.

[0076] Furthermore, the element extraction unit 208 may extract elements of a specified category from among elements associated with multiple elements classified into the person category. This allows elements related to multiple people and in a category specified by the user to be presented to the user. For example, by specifying an element of the place category (an element indicating a place), the user can receive presentations of places related to multiple people (such as secret meeting places for those people).

[0077] (Regarding the Relevance Identification Unit) This section describes the relevance identification unit 209. The relevance identification unit 209 identifies correspondences between the multiple sentences or their elements and the document 213 based on the structuring results of the multiple sentences by the structuring unit 203. Then, the information presentation unit 205 presents information indicating the identification results of the relevance identification means.

[0078] The document 213 is material for analyzing each sentence to be structured. For example, the document 213 may be a document showing facts, or may be research material created by conducting a survey or the like. Note that the above-mentioned "survey" also includes investigations or inspections. The target data 212 may also be part of the research material.

[0079] In this way, the information processing device 2 includes a relationship identification unit 209 that identifies the correspondence between multiple sentences or their elements and a specified document 213 based on the structuring results of the multiple sentences by the structuring unit 203, and an information presentation unit 205 that presents information indicating the identification results of the relationship identification unit 209.

[0080] Therefore, in addition to the effects of the information processing device 1 according to the exemplary embodiment 1, the information processing device 2 can also provide the effect of easily recognizing the correspondence between sentences and the document 213. This configuration is particularly effective when investigating target data 212 that includes a large number of sentences.

[0081] 8 is a flowchart showing the flow of processing executed by the relationship specifying unit 209 to specify the correspondence between sentences or their elements and the document 213. Note that the processing in FIG. 8 is performed after the structuring unit 203 has finished structuring multiple sentences.

[0082] In S41, the relevance identification unit 209 acquires the material 213 for which a correspondence is to be identified. For example, the relevance identification unit 209 may acquire the material 213 input to the information processing device 2 via the communication unit 22 or the input unit 23, or may acquire the material 213 stored in advance in the storage unit 21.

[0083] In S42, the relationship identification unit 209 identifies a correspondence between the sentence or its elements structured by the structuring unit 203 and the document 213 acquired in S41. Then, in S43, the information presentation unit 205 presents information indicating the identification result of S42 to the user.

[0084] The identification of the correspondence in S42 may be performed by a method according to the content of the document 213. An example of identifying the correspondence between a plurality of sentences or their elements and the document 213 will be described below with reference to FIGS.

[0085] (Example 1: Using Investigation Materials Showing Vehicle Detection Results) The materials 213 may include investigation materials showing the detection results of a specific vehicle by the vehicle detection system. In this case, the association identification unit 209 may identify a correspondence between the sentence and the investigation materials by comparing the detection time of the vehicle shown in the investigation materials with the time when a person associated with the vehicle sent or received one of the sentences included in the target data 212.

[0086] This provides the effect of facilitating the task of inferring facts by comparing the survey materials showing the detection results of a specified vehicle by the vehicle detection system with the sentences contained in the target data 212, in addition to the effect provided by the information processing device 1 of exemplary embodiment 1.

[0087] The vehicle detection system may be any system capable of detecting a vehicle. For example, the vehicle detection system may be a system that detects a vehicle by reading the vehicle's license plate number using an automatic license plate reader, or a system that detects a vehicle using a surveillance camera.

[0088] Furthermore, the association between vehicles and people may be performed in advance by a user of the information processing device 2 or the like, and the result of the association may be input to the information processing device 2 via the communication unit 22 or the input unit 23. For example, the user may input the person to be investigated in advance to the information processing device 2, and may also input in advance to the information processing device 2 the vehicles owned or used by that person, or vehicles suspected of being associated with that person.

[0089] In the above-described comparison process, the association identification unit 209 may first identify the detection time of a specific vehicle shown in the investigation materials, and then identify a sentence sent or received by a person associated with the vehicle during a time period set based on the identified detection time. Conversely, the association identification unit 209 may first identify a sentence sent or received by a person associated with a specific vehicle and its sending time or receiving time, and then identify, from among the detection results of the vehicle shown in the investigation materials, the detection results during a time period set based on the identified time.

[0090] The result of the relationship identification by the relationship identification unit 209 is presented to the user by the information presentation unit 205. Fig. 9 is a diagram showing an example of the display of the result of identifying the correspondence between a structured sentence and a research document showing the detection result of a predetermined vehicle by the vehicle detection system.

[0091] 9 shows an image 213a indicating the vehicle detection results together with a graph G3 indicating the structuring results by the structuring unit 203. The image 213a is part of the research material indicating the vehicle detection results. Specifically, the image 213a is an image of a vehicle owned by person A, taken in parking lot F at 9:30 PM on April 29, 2023.

[0092] In graph G3, the portion where the node for "Person A" and the node for "Parking Lot F" are connected by an edge to "Arrived" is generated from a sentence indicating that Person A has arrived at Parking Lot F. This portion is highlighted by being enclosed in a dashed line, and is displayed in association with image 213a by being linked to it by a dashed line. The portion of graph G3 also displays that the date and time the sentence was sent is 21:32 on April 29, 2023. This allows the user to easily recognize that image 213a can be used as research material supporting the content of the sentence sent at 21:32 on April 29, 2023.

[0093] (Example 2 Using Investigation Materials Indicating Vehicle Detection Results) The materials 213 may include investigation materials indicating locations around a specific vehicle detected by the vehicle detection system or locations on the vehicle's travel route. In this case, the association identification unit 209 may identify a correspondence between the locations indicated in the investigation materials and elements indicating locations included in sentences sent or received by a person associated with the vehicle during the time period when the vehicle moved on the travel route or the time period when the vehicle was detected by the vehicle detection system.

[0094] This provides the effect of facilitating the task of guessing the type of place mentioned in a sent or received sentence, in addition to the effect provided by the information processing device 1 of exemplary embodiment 1.

[0095] For example, suppose a vehicle owned by a person under investigation is detected by a surveillance camera at point p at 12:00. In this case, investigation materials indicating various locations near point p can be input to the information processing device 2 as materials 213. In this case, the relevance identification unit 209 extracts, from the sentences structured by the structuring unit 203, elements of sentences that were sent or received by the person under investigation or people who were with the person under investigation during a predetermined time period set around 12:00. The relevance identification unit 209 then identifies, from the extracted elements, elements indicating locations as elements related to the investigation materials.

[0096] The element indicating a location may be identified based on, for example, the classification result of the element classification unit 207. That is, the element classification unit 207 may classify each element into a plurality of categories including the location category. In this case, the relationship identification unit 209 may identify the element classified into the location category by the element classification unit 207. The relationship identification unit 209 may associate one location with one element, or may associate multiple locations with one element.

[0097] Furthermore, if multiple locations are indicated in the survey materials, the relevance identifying unit 209 may narrow down the locations to be associated with the elements of the sentence. For example, the element classification unit 207 may classify a location category into multiple subcategories. Subcategories are also set for the locations indicated in the survey materials. This allows the relevance identifying unit 209 to identify locations whose subcategories match the identified elements. For example, assume that the survey materials include store A (subcategory: restaurants) and store B (subcategory: retail stores). In this case, the relevance identifying unit 209 can identify the survey materials related to the element "places to eat" (subcategory: restaurants) as store A.

[0098] When using research materials that indicate locations on the vehicle's travel route, the relevance identification unit 209 identifies the vehicle's travel route and also identifies the time period during which the vehicle traveled on that travel route. For example, the relevance identification unit 209 can identify the vehicle's travel route using a Ground Positioning System (GPS). The relevance identification unit 209 can also identify the vehicle's travel route from the detection results of the vehicle at multiple points. In this case, the relevance identification unit 209 may identify the route connecting the points where the vehicle was detected as the travel route.

[0099] The relevance identification unit 209, which has identified the time period during which the person traveled along the travel route, extracts elements of sentences that were sent or received during the identified time period by the person being investigated or by people who were traveling with the person, from among the sentences structured by the structuring unit 203. The relevance identification unit 209 then identifies, from among the extracted elements, elements that indicate a location as elements related to the research material.

[0100] The research material may be, for example, a map including various information about places such as place names, or materials showing various information about places such as place names, store names, and addresses. Data detected by using various search engines may also be used as the research material. For example, the association identification unit 209 may associate search results related to places obtained by searching using the identified element as a keyword with the element.

[0101] The results of the relationship identification by the relationship identification unit 209 are presented to the user by the information presentation unit 205. Fig. 10 is a diagram showing an example of the display of the results of identifying the correspondence between elements of a structured sentence and places shown in the research material.

[0102] 10 shows a graph G4 indicating the structuring results by the structuring unit 203, as well as an image 213b indicating the vehicle's route and each location on that route. Image 213b is research data indicating each location on a specific vehicle's route detected by the vehicle detection system. Image 213b indicates that the vehicle was detected at point p1 at 23:00 and at point p2 at 24:00, and also indicates that a parking area p3 and an interchange p4 are located on the route connecting points p1 and p2.

[0103] In graph G4, the portion where the node for "Person A" and the node for "Place where you can park your car" are connected by an edge to "arrive" is generated from a sentence indicating that Person A will soon arrive at a place where he can park his car. The character string "Place where you can park your car" is highlighted by being enclosed in a dashed line, and is displayed in association with "p3: Parking Area" in image 213b by being linked with a dashed line. The portion of graph G4 also displays that the time the sentence was sent was 9:10 p.m. This allows the user to easily infer that the "place where you can park your car" in the sentence is parking area p3.

[0104] (Example of using investigation materials showing call history) The materials 213 may include investigation materials showing the call history of a specific person. In this case, the relevance identification unit 209 may identify, as a sentence related to the call, a sentence sent or received by the person around the time when the investigation materials show that the person made a call.

[0105] Generally, before and after a phone call, sentences related to the phone call are transmitted and received. Such sentences may explicitly or implicitly indicate the content of the phone call. Therefore, according to the above configuration, in addition to the effects of the information processing device 1 according to the first exemplary embodiment, an effect of facilitating the task of inferring the content of the phone call from sentences in the research materials can be obtained.

[0106] Specifically, the association identification unit 209 first acquires research materials showing the call history of a specific person and identifies the time period during which the call was made by that person. Next, the association identification unit 209 identifies sentences sent or received by that person before or after the identified time period from among sentences included in the target data 212. This associates the call history of the specific person with sentences sent or received by that person before or after the call time period.

[0107] The result of the relationship identification by the relationship identification unit 209 is then presented to the user by the information presentation unit 205. Fig. 11 is a diagram showing an example of the display of the result of identifying the correspondence between the structured sentences and the call history shown in the research material.

[0108] 11 shows an image 213c showing the call history of a specific person A, along with a graph G5 showing the structuring results by the structuring unit 203. The image 213c is an example of research material. The image 213c shows that person A made calls from 21:30 to 21:35 on April 30, 2023.

[0109] In graph G5, the portion where the node with "Person A" and the node with "Person F" are connected by an edge with "Deposit" is generated from the message "Deposit within three days" sent by Person A to Person F. This portion is highlighted by being enclosed in a dashed line, and is displayed in association with the call history for April 30, 2023 in image 213c by being linked by a dashed line. The portion of graph G5 also displays that the message was sent at 9:40 PM on April 30, 2023. This makes it easy to infer that the content of Person A's call on April 30, 2023, was related to the transfer of money.

[0110] (Example of using investigation materials showing deposit and withdrawal history) The materials 213 may include investigation materials showing the deposit and withdrawal history of a specified account. In this case, the correlation identification unit 209 may identify a correspondence between the sentences and the investigation materials by comparing the times of deposits and withdrawals shown in the investigation materials with the times when sentences related to the transfer of money were sent or received among the multiple sentences included in the target data 212.

[0111] According to the above configuration, in addition to the effects achieved by the information processing device 1 of exemplary embodiment 1, the effect of facilitating the task of verifying facts regarding deposits and withdrawals to an account can be obtained.

[0112] Specifically, the association identification unit 209 may first identify the times of deposits and withdrawals shown in the investigation materials, and then identify statements related to the transfer of money that were sent or received during a time period set based on the identified times. Conversely, the association identification unit 209 may first identify statements related to the transfer of money and the times at which the statements were sent or received. In this case, the association identification unit 209 identifies the history of deposits or withdrawals during a time period set based on the identified times, among the times of deposits and withdrawals shown in the investigation materials.

[0113] The results of the relationship identification by the relationship identification unit 209 are presented to the user by the information presentation unit 205. Fig. 12 is a diagram showing an example of the display of the results of identifying the correspondence between the structured sentences and the deposit and withdrawal history shown in the investigation materials.

[0114] 12 shows an image 213d showing the deposit and withdrawal history together with a graph G6 showing the results of structuring by the structuring unit 203. Image 213d is a survey document showing the deposit and withdrawal history, and shows that a deposit was made on May 1, 2023.

[0115] In graph G6, the portion where the node for "Person F" and the node for "Payment of Compensation" are connected by an edge with "Necessary" is generated from a statement that Person F needs to pay compensation. This portion is highlighted by being enclosed in a dashed line, and is displayed in association with the payment history for May 1, 2023 in image 213d by connecting it with a dashed line. The above portion of graph G6 also displays that the date and time the above statement was sent was 14:20 on May 1, 2023. This provides factual evidence that the payment on May 1, 2023 was prompted by the above statement sent at 14:20 on the same day.

[0116] [Variations] The information processing device 2 can operate in cooperation with various external systems, not limited to vehicle detection systems. By cooperating with an external system, the information processing device 2 can acquire materials 213 collected by the system with which it is to be coordinated, and associate the acquired materials 213 with sentences or elements thereof included in the target data 212. Furthermore, the information processing device 2 may acquire all or part of the target data 212 from the external system.

[0117] The information processing device 2 that cooperates with an external system can also be considered as part of that system, and various systems that include the information processing device 2 are included in the scope of the present invention. For example, in addition to a vehicle detection system that includes the information processing device 2, a traffic control system that includes the information processing device 2, a monitoring system that includes the information processing device 2, and a security system that includes the information processing device 2 are also included in the scope of the present invention.

[0118] The execution entity of each process described in the above-described embodiment is arbitrary and is not limited to the above-described example. In other words, the functions of the information processing devices 1 and 2 can be realized by multiple devices (which can also be called processors) that can communicate with each other. For example, the execution of each process described in the flow charts of Figures 2, 5, 7, and 8 can be shared among multiple processors. In other words, the execution entity of the structuring method in the above-described embodiment may be one processor or multiple processors.

[0119] [Reference Example] An information processing device according to one reference example includes an element classification means for classifying elements in a plurality of structured sentences into a plurality of categories including at least a person category, and an element extraction means for extracting elements associated with the plurality of elements classified into the person category from among the elements. This configuration has the effect of facilitating a survey targeting a plurality of people. Note that the above structuring may be performed by any method. Furthermore, it is not essential to infer the subject or object of a sentence when performing the structuring.

[0120] An information processing device according to one reference example includes a relationship identification unit that identifies a correspondence between a plurality of sentences or their elements and a predetermined document based on the result of structuring the plurality of sentences, and an information presentation unit that presents information indicating the identification result of the relationship identification unit. This configuration has the effect of making it possible to easily recognize the correspondence between the sentences and the document. Note that the structuring can be performed by any method. Furthermore, it is not necessary to infer the subject or object of the sentence when performing the structuring.

[0121] [Example of Software Implementation] Some or all of the functions of the information processing devices 1 and 2 may be implemented by hardware such as an integrated circuit (IC chip), or may be implemented by software.

[0122] In the latter case, the information processing devices 1 and 2 are realized, for example, by a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in FIG. 13. The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program (structured program) P for operating the computer C as the information processing device 1 or 2. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing each function of the information processing device 1 or 2.

[0123] The processor C1 may be, for example, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0124] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, a mouse, a display, and a printer.

[0125] The program P can also be recorded on a non-transitory, tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0126] [Additional Note 1] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technical means disclosed in the above-described embodiments are also included in the technical scope of the present invention.

[0127] [Additional Note 2] Part or all of the above-described embodiment can also be described as follows: However, the present invention is not limited to the following described aspects.

[0128] (Supplementary Note 1) An information processing device comprising: a classification means for classifying sentences according to their contents; an estimation means for estimating at least one of a subject and an object of the sentence by applying an estimation method according to the result of the classification; and a structuring means for structuring the sentence based on the result of the estimation.

[0129] (Supplementary Note 2) The information processing device according to Supplementary Note 1, wherein for a sentence classified as an imperative sentence by the classification means, the estimation means performs at least one of a process of estimating the sender of the sentence as the subject of the sentence and a process of estimating the recipient of the sentence as the object of the sentence.

[0130] (Supplementary Note 3) The information processing device according to Supplementary Note 1 or 2, further comprising an element sequence extraction means for extracting a series of elements that are associated based on the result of the structuring and the result of classification by the classification means, from among the elements that constitute the plurality of sentences that have been structured.

[0131] (Supplementary Note 4) An information processing device according to any one of Supplementary Notes 1 to 3, comprising: an element classification means for classifying each element constituting a sentence into a plurality of categories including at least a person category; and an element extraction means for extracting elements associated with the plurality of elements classified into the person category from among the elements constituting the plurality of sentences each of which has been structured.

[0132] (Appendix 5) An information processing device described in any of Appendices 1 to 4, comprising: a relationship identification means for identifying a correspondence between the plurality of sentences or their elements and a specified document based on the results of structuring the plurality of sentences by the structuring means; and an information presentation means for presenting information indicating the results of the identification by the relationship identification means.

[0133] (Appendix 6) An information processing device as described in Appendix 5, wherein the specified materials include research materials showing the detection results of a specified vehicle by a vehicle detection system, and the correlation identification means identifies the correspondence between the sentences and the research materials by comparing the detection time of the vehicle shown in the research materials with the time when a person associated with the vehicle sent or received one of the sentences.

[0134] (Supplementary Note 7) The information processing device according to Supplementary Note 5 or 6, wherein the specified materials include research materials indicating locations around a specified vehicle detected by a vehicle detection system or locations on the vehicle's travel route, and the correlation identification means identifies a correspondence between an element indicating a location included in a sentence sent or received by a person associated with the vehicle during the time period when the vehicle moved on the travel route or the time period when the vehicle was detected by the vehicle detection system and the location indicated in the research materials.

[0135] (Appendix 8) An information processing device described in any of Appendices 5 to 7, wherein the specified materials include research materials showing the call history of a specified person, and the relevance identification means identifies, as a sentence related to the call, a sentence sent or received by the person before or after a time period when the research materials show that the person made a call.

[0136] (Appendix 9) An information processing device described in any of Appendices 5 to 8, wherein the specified materials include investigation materials showing the deposit and withdrawal history of a specified account, and the correlation identification means identifies the correspondence between the sentences and the investigation materials by comparing the times of deposits and withdrawals shown in the investigation materials with the times when sentences related to the transfer of money among the multiple sentences were sent or received.

[0137] (Supplementary Note 10) A structuring method including: classifying, by at least one processor, sentences according to their contents; inferring at least one of a subject and an object of the sentences by applying a predetermined inference method according to a result of the classification; and structuring the sentences based on a result of the inference.

[0138] (Appendix 11) A computer-readable recording medium having recorded thereon a structuring program that causes a computer to function as a classification means that classifies sentences according to their contents, an estimation means that estimates at least one of the subject and object of the sentences by applying a predetermined estimation method according to the results of the classification, and a structuring means that structures the sentences based on the results of the estimation.

[0139] (Supplementary Note 12) The information processing device includes a relationship identification means for identifying a correspondence between a plurality of sentences or their elements and a specified document based on the result of structuring the plurality of sentences, and an information presentation means for presenting information indicating the identification result of the relationship identification means.

[0140] [Additional Note 3] Part or all of the above-described embodiment can also be expressed as follows.

[0141] (Supplementary Note 1) An information processing device comprising at least one processor, the at least one processor executing a process of classifying sentences according to their contents, a process of inferring at least one of a subject and an object of the sentences by applying an inference method according to the results of the classification, and a process of structuring the sentences based on the results of the inference.

[0142] The information processing device may further include a memory that stores a structuring program for causing the processor to execute the classification process, the estimation process, and the structuring process. The structuring program may be recorded on a computer-readable, non-transitory, tangible recording medium.

[0143] (Supplementary Note 2) The information processing device described in Supplementary Note 1, wherein the at least one processor performs at least one of a process of inferring the sender of a sentence classified as an imperative sentence in the classification process as the subject of the sentence and a process of inferring the recipient of the sentence as the object of the sentence.

[0144] (Supplementary Note 3) The information processing device according to Supplementary Note 1 or 2, wherein the at least one processor further executes a process of extracting a series of elements that are associated with each other based on the result of the structuring and the result of classification by the classification means, from among the elements that constitute the plurality of sentences that have been structured.

[0145] (Supplementary Note 4) The information processing device described in any one of Supplementary Notes 1 to 3, wherein the at least one processor further executes an element classification means for classifying each element constituting a sentence into a plurality of categories including at least a person category, and a process for extracting elements associated with the plurality of elements classified into the person category from among the elements constituting the plurality of sentences each of which has been structured.

[0146] (Appendix 5) An information processing device described in any of Appendices 1 to 4, wherein the at least one processor further executes a process of identifying a correspondence between the plurality of sentences or their elements and a specified material based on the results of structuring the plurality of sentences by the structuring means, and a process of presenting information indicating the identification results of the process.

[0147] (Appendix 6) The information processing device described in Appendix 5, wherein the specified materials include research materials showing the detection results of a specified vehicle by a vehicle detection system, and the at least one processor identifies a correspondence between the sentences and the research materials by comparing the detection time of the vehicle shown in the research materials with the time when a person associated with the vehicle sent or received any of the sentences.

[0148] (Supplementary Note 7) The information processing device described in Supplementary Note 5 or 6, wherein the specified materials include research materials indicating locations around a specified vehicle detected by a vehicle detection system or locations on the vehicle's travel path, and the at least one processor identifies a correspondence between locations indicated in the research materials and elements included in sentences sent or received by a person associated with the vehicle during the time period when the vehicle moved on the travel path or the time period when the vehicle was detected by the vehicle detection system.

[0149] (Appendix 8) An information processing device described in any of Appendices 5 to 7, wherein the specified materials include research materials showing the call history of a specified person, and the at least one processor identifies, as sentences related to the call, sentences sent or received by the person around the time period when the research materials show that the person made a call.

[0150] (Appendix 9) An information processing device described in any of Appendices 5 to 8, wherein the specified materials include investigation materials showing the deposit and withdrawal history of a specified account, and the at least one processor identifies a correspondence between the sentences and the investigation materials by comparing the times of deposits and withdrawals shown in the investigation materials with the times when sentences related to the transfer of money among the multiple sentences were sent or received.

[0151] (Supplementary Note 10) An information processing device comprising at least one processor, the at least one processor executing a process of identifying a correspondence between a plurality of sentences or their elements and a specified material based on the result of structuring the plurality of sentences, and a process of presenting information indicating the identification result of the relevance identification means.

[0152] REFERENCE SIGNS LIST 1 Information processing device 11 Classification unit (classification means) 12 Estimation unit (estimation means) 13 Structuring unit (structuring means) 2 Information processing device 201 Classification unit (classification means) 202 Estimation unit (estimation means) 203 Structuring unit (structuring means) 205 Information presentation unit (information presentation means) 206 Element string extraction unit (element string extraction means) 207 Element classification unit (element classification means) 208 Element extraction unit (element extraction means) 209 Relationship identification unit (relationship identification means)

Claims

1. a classification means for classifying sentences according to their content; an estimation means for estimating at least one of a subject and an object of the sentence by applying an estimation method according to the result of the classification; and structuring means for structuring the sentence based on the result of the estimation.

2. 2. The information processing device according to claim 1, wherein, for a sentence classified as an imperative sentence by the classification means, the estimation means performs at least one of a process of estimating a sender of the sentence as a subject of the sentence and a process of estimating a receiver of the sentence as an object of the sentence.

3. 3. The information processing device according to claim 1, further comprising: an element string extraction means for extracting, from among the elements constituting the plurality of sentences each subjected to the structuring, a series of elements associated based on the result of the structuring and the result of classification by the classification means.

4. an element classification means for classifying each element constituting a sentence into a plurality of categories including at least a person category; 3. The information processing device according to claim 1, further comprising: an element extraction means for extracting elements associated with a plurality of elements classified into a person category from among the elements constituting the plurality of sentences each of which has been structured.

5. a correlation specifying means for specifying a correspondence between the plurality of sentences or elements thereof and a predetermined material based on the structuring result of the plurality of sentences by the structuring means; The information processing apparatus according to claim 1 , further comprising: information presenting means for presenting information indicating the result of the determination by the correlation determining means.

6. the predetermined data includes survey data showing the detection results of the predetermined vehicle by the vehicle detection system; The information processing device described in claim 5, wherein the correlation identification means identifies the correspondence between the sentence and the investigation material by comparing the detection time of the vehicle shown in the investigation material with the time when a person associated with the vehicle sent or received any of the sentences.

7. The predetermined materials include investigation materials showing the call history of the predetermined person, The information processing device according to claim 5, wherein the relevance identification means identifies, as a sentence related to the call, a sentence sent or received by the person before or after a time period in which the investigation materials indicate that the person made a call.

8. The predetermined materials include research materials showing the deposit and withdrawal history of the predetermined account, The information processing device described in claim 5, wherein the correlation identification means identifies the correspondence between the sentences and the survey material by comparing the times of deposits and withdrawals indicated in the survey material with the times when sentences related to the transfer of money among the plurality of sentences were sent or received.

9. At least one processor Classifying sentences according to their content; applying a predetermined estimation method according to the result of the classification to estimate at least one of a subject and an object of the sentence; and structuring the sentence based on a result of the estimation.

10. Computer, a classification means for classifying sentences according to their content; an estimation means for estimating at least one of a subject and an object of the sentence by applying a predetermined estimation method according to the result of the classification; and a structuring program that functions as a structuring means for structuring the sentence based on the result of the estimation.