Information processing device, information processing method, and program

Abstract

Create a timeline that displays the relationships between a specific subject and their associates, based on information about that subject obtained from multiple documents. [Solution] The information acquisition means acquires subject-related information related to a specific subject from multiple documents. The extraction means extracts multiple strings that meet predetermined criteria from the subject-related information. The analysis means organizes the multiple strings according to a predetermined format for the specific subject and for people other than the specific subject, and detects strings that have a predetermined relationship among the multiple strings, and outputs the organized strings and information indicating the relationship. The timeline creation means creates a timeline that displays strings related to the specific subject and strings related to people other than the specific subject in parallel on a timeline, and also displays information indicating the strings that have a relationship among the multiple strings.

Description

Technical Field

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

Background Art

[0002] In an organization that conducts criminal investigations such as the police, when conducting an investigation of a case, a written statement or evidence document recording information collected for each case is created. Generally, even for one case, a large amount of documents need to be created. Therefore, the amount of documents related to multiple cases becomes enormous. Thus, various management systems have been introduced for the management of investigation-related documents.

[0003] For example, in Patent Document 1, an event evidence management system has been proposed that can perform a cross-sectional search of a plurality of different types of data related to the same case in a batch, improve the search efficiency, and improve the convenience for users. According to this, it is possible to efficiently access necessary information from a large amount of information related to the same case.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, information about suspects and individuals associated with them during a criminal investigation may be recorded in multiple documents, such as personal records, even for a single case. Furthermore, information about the same person may appear in personal records or other documents related to multiple different cases. In this case, investigators must search for information about the same person across multiple different documents and then review the information they find. While reviewing information about a specific person in a chronological format can reduce the burden, cross-referencing information about multiple individuals requires an even greater amount of time. Therefore, in criminal investigations conducted with limited time and human resources, it is difficult to grasp the relationships between multiple individuals from a large volume of documents. [Means for solving the problem]

[0006] The information processing device according to this disclosure includes: information acquisition means for acquiring subject-related information relating to a specific subject from multiple documents; extraction means for extracting multiple strings that satisfy predetermined criteria from the subject-related information; analysis means for organizing the multiple strings according to a predetermined format for the specific subject and persons other than the specific subject, detecting strings having a predetermined relationship among the multiple strings, and outputting the organized strings and information indicating the relationship; and timeline creation means for creating a timeline that displays strings relating to the specific subject and strings relating to persons other than the specific subject in parallel on a timeline, and displays information indicating the strings having the relationship among the multiple strings.

[0007] The information processing method described herein involves obtaining subject-related information relating to a specific subject from multiple documents, extracting multiple strings that satisfy predetermined criteria from the subject-related information, organizing the multiple strings according to a predetermined format for the specific subject and for persons other than the specific subject, detecting strings that have a predetermined relationship among the multiple strings, outputting the organized strings and information indicating the relationship, and creating a timeline that displays the strings relating to the specific subject and the strings relating to persons other than the specific subject in parallel on a timeline, and also displays information indicating the strings that have the relationship among the multiple strings.

[0008] The program disclosed herein causes a computer to perform the following steps: a process of obtaining subject-related information relating to a specific subject from multiple documents; a process of extracting multiple strings that satisfy predetermined criteria from the subject-related information; a process of organizing the multiple strings according to a predetermined format for the specific subject and for persons other than the specific subject, detecting strings that have a predetermined relationship among the multiple strings, and outputting the organized strings and information indicating the relationship; and a process of creating a timeline that displays the strings relating to the specific subject and the strings relating to persons other than the specific subject in parallel on a timeline, and displays information indicating the strings that have the relationship among the multiple strings. [Effects of the Invention]

[0009] According to this disclosure, it is possible to provide an information processing device, an information processing method, and a program that can create a timeline displaying the relationships between a specific subject and their related parties, as contained in information about a specific subject obtained from multiple documents. [Brief explanation of the drawing]

[0010] [Figure 1]This figure shows a schematic example of the configuration of the information processing device related to this disclosure. [Figure 2] This diagram schematically shows the configuration of an information processing device according to one embodiment. [Figure 3] This diagram shows the format for extracting strings of text from investigation-related documents. [Figure 4] This figure shows an example of how the analysis department organized the data by applying the 5W1H items to a format. [Figure 5] This diagram shows an example of the organized data when the main category of focus is criminal record. [Figure 6] This figure shows an example of how to organize data when the main category of focus is work history. [Figure 7] This figure shows an example of organized information when the main category of focus is educational background or official rank, decorations, and pensions. [Figure 8] This figure shows an example of a timeline created by an information processing device according to one embodiment. [Figure 9] This figure shows another example of a timeline created by an information processing device according to one embodiment. [Figure 10] A flowchart showing the processing of an information processing device according to one embodiment. [Figure 11] This diagram schematically shows the configuration of an information processing device according to one embodiment. [Figure 12] This diagram schematically shows the configuration of an information processing device according to one embodiment. [Figure 13] This figure shows an example of how the presence of inconsistent information is displayed in a timeline created by an information processing device according to one embodiment. [Figure 14] A flowchart showing the processing of an information processing device according to one embodiment. [Figure 15] This figure shows an example of a computer configuration for realizing an information processing device. [Modes for carrying out the invention]

[0011] Before describing the embodiments of the present disclosure, an overview of the present disclosure will be described. FIG. 1 is a diagram showing a schematic configuration example of an information processing apparatus according to the present disclosure. The information processing apparatus 10 includes an information acquisition unit 11, an extraction unit 12, an analysis unit 13, and a chronology creation unit 14.

[0012] The information acquisition unit 11 searches for and acquires target-related information INF1 related to a specific target person from a plurality of documents including information related to the specific target person.

[0013] The extraction unit 12 divides and extracts a character string indicating information related to a specific target person from the target-related information INF1 into items defined by a predetermined criterion. Then, the extraction unit 12 outputs extraction item information INF2 composed of the extracted information to the analysis unit 13.

[0014] The analysis unit 13 fits a plurality of items included in the extraction item information INF2 into a predetermined format and arranges them in chronological order for each of the target person OBJ and other related persons R1 to Rn. The analysis unit 13 outputs chronological information TS0 to TSn indicating items related to the target person OBJ and other related persons R1 to Rn, and labeling information LBL indicating the relationship when there are items having a certain relationship among the items after fitting, to the chronology creation unit 14.

[0015] The chronology creation unit 14 creates a chronology CT in which items related to the target person and items related to persons other than the target person are arranged in parallel on the time axis, based on the information received from the analysis unit 13.

[0016] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In each drawing, the same reference numerals are assigned to the same elements, and redundant descriptions will be omitted as necessary.

[0017] When referring to an embodiment hereinafter, it means that it is applicable to any one of the embodiments described hereinafter, or a combination of two or more embodiments, and the application is not limited to a specific embodiment.

[0018] Embodiment 1 An information processing device according to Embodiment 1 will now be described. Figure 2 is a schematic diagram showing the configuration of an information processing device according to one embodiment. The information processing device 100 has an information acquisition unit 110, an extraction unit 120, an analysis unit 130, and a timeline creation unit 140. The information acquisition unit 110, the extraction unit 120, and the analysis unit 130 in the information processing device 100 correspond to the information acquisition unit 11, the extraction unit 12, and the analysis unit 13 in the information processing device 10, respectively. Physically, the information processing device 100 can be configured as, for example, an information processing device having one or more processors and one or more memories, or as a server device. At least a part of the functions of each part of the information processing device 100 may be realized by one or more processors operating according to a program read from one or more memories.

[0019] Some or all of the information acquisition unit 110, extraction unit 120, analysis unit 130, and timeline creation unit 140 may perform their respective processes using various natural language processing (NLP) techniques, for example, artificial intelligence (AI).

[0020] The information processing device 100 can access, for example, a database 1000 that stores investigation-related documents such as reports and evidence documents created for each of multiple criminal cases.

[0021] The information acquisition unit 110 is configured to access, for example, multiple investigation-related documents 1100 used for analysis from the database 1000. The information acquisition unit 110 searches for information on a specific subject to be analyzed from the multiple investigation-related documents 1100. The information to be analyzed includes, for example, the subject's family structure, criminal record, work history, residence history, educational background, and decorations history as described in the investigation-related documents. The specific subject in the investigation-related documents may be, for example, the suspect, relatives of the suspect, and witnesses. The information acquisition unit 110 retrieves the retrieved information on the specific subject from the database 1000. In Figure 2, the information on the specific subject retrieved by the information acquisition unit 110 from the database 1000 is displayed as subject-related information INF1.

[0022] The extraction unit 120 extracts strings such as keywords and phrases that represent the 5W1H items from the subject-related information INF1 acquired by the information acquisition unit 110. The 5W1H items are information classified into categories such as "when," "where," "who," "what," "why," and "how" or "what happened."

[0023] The extraction unit 120 may determine a sentence based on keywords using "dependency parsing." Since there may be variations in expression when statements or other written materials are transcribed, keyword searches may appropriately apply general methods such as natural language AI.

[0024] The extraction unit 120 may, for example, apply NSP (Next Sentence Prediction) to extract parts of speech such as the subject, predicate, and object within a sentence. Then, based on the extracted information about parts of speech, it may extract the 5W1H items in the sentence. Furthermore, since proper nouns in the sentence are highly likely to correspond to information such as "what," "how," or "what happened," the extraction unit 120 may also extract them.

[0025] The extraction unit 120 may extract 5W1H items using a format for extracting 5W1H items from subject-related information INF1. For example, assuming that the document obtained by the information processing device 100 from the database 1000 is an investigation-related document 1100, the strings contained in the investigation-related document can be empirically estimated to be within a certain range. Figure 3 shows a diagram of the extraction format for strings contained in the investigation-related document. The extraction unit 120 may extract 5W1H items from subject-related information INF1 based on the classification guidelines shown in Figure 3.

[0026] For example, let's assume that the statement of the subject, "Jiro Tanaka," is included as a sentence in the subject-related information INF1. The statement might be something like this: "I was born as the second of two brothers to a father who was a taxi driver at the time and a mother who was a housewife. After graduating from junior high school, I got a job at a company called F Civil Engineering Co., Ltd. in City B and worked as a civil engineering worker. While working at this company, I started using drug X out of curiosity, and when I was 16 years old, I was arrested by the PA Police and PB Police for using drug X, sent to a juvenile detention center, and quit my job." In this case, the extraction unit 120 may extract strings corresponding to the major and minor items shown in Figure 3, which correspond to the 5W1H items, according to the extraction format created for investigation-related documents.

[0027] The extraction unit 120 outputs the extracted item information INF2, which shows the extracted 5W1H items, to the analysis unit 130.

[0028] The analysis unit 130 organizes the 5W1H items included in the extracted item information INF2 according to a predetermined format. Then, the analysis unit 130 outputs information that includes information indicating strings that have a predetermined relationship among the multiple strings included in the extracted item information INF2.

[0029] The analysis unit 130 includes a time-series organization unit 131 and a relationship analysis unit 132. The time-series organization unit 131 may organize the 5W1H items included in the extracted item information INF2 according to the items shown in Figure 3. For example, for the "educational background" item, items such as "school attended" and "highest level of education" may be selected and arranged from the 5W1H items.

[0030] Figure 4 shows an example of how the analysis unit organizes the 5W1H items by applying them to a format. The time-series organization unit 131 organizes the 5W1H items included in the extracted item information INF2 for each subject OBJ in chronological order, and creates subject time-series information TS0. In the example in Figure 4, the strings indicating the 5W1H items related to the subject's family structure are organized in chronological order along the vertical time axis. Note that Figure 4 is merely displayed to make the organization of the 5W1H items easier to understand, and does not mean that the 5W1H items are visually arranged as shown in Figure 4.

[0031] Furthermore, the time-series organization unit 131 organizes the 5W1H items included in the extracted item information INF2 in chronological order for each of the related parties R1 to Rn, who are individuals other than the subject and included in the extracted item information INF2, and creates related party time-series information TS1 to TSn.

[0032] The relationship analysis unit 132 searches for common or similar items among the subject time series information TS0 and the related party time series information TS1 to TSn. If the relationship analysis unit 132 finds common or similar items among the subject time series information TS0 and the related party time series information TS1 to TSn, it labels those items as common items. Subsequently, the relationship analysis unit 132 outputs the subject time series information TS0 and the related party time series information TS1 to TSn, along with the labeling information LBL showing the labeling results, to the timeline creation unit 140.

[0033] The above example, referring to Figure 4, illustrates how to organize the 5W1H items related to the subject's family structure. However, the items to focus on in this organization can vary. Figure 5 shows an example of the information after organization when the main item of focus is criminal history. Figure 6 shows an example of the information after organization when the main item of focus is work history. Figure 7 shows an example of the information after organization when the main item of focus is educational history or official rank, medals, and pensions. As shown in Figures 5 to 7, it can be seen that regardless of the main item of focus, information can be obtained that shows the 5W1H items organized chronologically, as well as the results of the analysis of the relationships between the items.

[0034] The timeline creation unit 140 creates a timeline that displays the time-series information of subject OBJ and related parties R1 to Rn in parallel, based on the subject time-series information TS0, related party time-series information TS1 to TSn, and labeling information LBL. It also displays items that are common or similar across the subject time-series information TS0 and related party time-series information TS1 to TSn.

[0035] Figure 8 shows an example of a timeline created by an information processing device according to one embodiment. In the timeline shown in Figure 8, the "where" items from the subject time-series information TS0 and the related party time-series information TS1 to TSn are organized. In the timeline of Figure 8, the horizontal direction is the time axis, and the time-series information of three people is arranged in parallel in the vertical direction. The "where" items that are common to at least two of the three people are indicated by colored areas and arrows.

[0036] In Figure 8, a timeline was created focusing on "where," but a timeline showing chronological information indicating the status of multiple people at a specific location may also be created. Figure 9 shows another example of a timeline created by an information processing device according to one embodiment. In the timeline shown in Figure 9, the changes in the positions of the subject and related parties are shown when "where" is specified as "M Family" and the renamed "M Family H Group." In Figure 9, the parts corresponding to the positions of each person at the time when subject OBJ belonged to "M Family H Group" as a "young member" are indicated by colored parts and arrow lines.

[0037] Next, the processing in the information processing device 100 will be described. Figure 10 is a flowchart of the processing in the information processing device according to one embodiment.

[0038] Step S11 The information acquisition unit 110 acquires information about the subject from the investigation-related documents 1100 in the database 1000.

[0039] Step S12 The extraction unit 120 extracts extraction item information INF2 from the subject-related information INF1.

[0040] Step S13 The time-series organization unit 131 organizes the 5W1H items included in the extracted item information INF2 in chronological order for each item for the subject OBJ, and creates the subject time-series information TS0.

[0041] Step S14 The time-series organization unit 131 organizes the 5W1H items included in the extracted item information INF2 in chronological order for each of the stakeholders R1 to Rn, and creates stakeholder time-series information TS1 to TSn.

[0042] Step S15 The relationship analysis unit 132 searches for common or similar items among the subject time series information TS0 and the related party time series information TS1 to TSn. If the relationship analysis unit 132 finds common or similar items among the subject time series information TS0 and the related party time series information TS1 to TSn, it generates labeling information LBL indicating that those items have been labeled.

[0043] Step S16 The timeline creation unit 140 creates a timeline CT that displays the time-series information of subject OBJ and related parties R1 to Rn in parallel, for example, as shown in Figure 8, based on the subject time-series information TS0, related party time-series information TS1 to TSn, and labeling information LBL.

[0044] In this way, by visualizing common or similar matters across multiple individuals and related parties, users of the information processing device 100 can easily and efficiently grasp common or similar matters across multiple individuals.

[0045] The timeline CT may be displayed in a way that is visible to the user of the information processing device 100. As shown in Figure 8, the information processing device 100 may output the timeline CT to the display unit 190. The display unit 190 may display the timeline CT in a way that is visible to the user of the information processing device 100. In this case, the display unit 190 may, for example, display the image of the timeline CT shown in Figure 8 to the user of the information processing device 100.

[0046] The display unit 190 may be included in the information processing device according to this embodiment. Figure 11 is a schematic diagram showing the configuration of an information processing device according to one embodiment. As shown in Figure 11, the display unit 190 may be incorporated as part of the information processing device 101. This makes it possible to provide the information processing device according to this embodiment entirely using general hardware resources.

[0047] As explained above, users of the information processing device can view the 5W1H items at each point in time across multiple users. Furthermore, by obtaining information that shows the relationships between items, such as the colored areas and arrow lines in Figures 8 and 9, users of the information processing device can visually and easily grasp the relationships between common or similar items across multiple users.

[0048] Embodiment 2 Documents containing information about a subject, such as investigation-related documents, include various types of documents, such as statements made by the subject themselves, summaries of the subject's statements from the perspective of a third party such as an investigator, and documents recording facts about the subject. Therefore, even information about the same event concerning the subject may not be consistent across multiple documents. Here, "event" refers to matters and events that indicate the subject's attributes and actions, such as information indicating the subject's status, such as family structure, place of residence at a certain time, and place of employment, and information about incidents and other events in which the subject was involved.

[0049] Documents that record facts concerning a subject are considered to have a high degree of reliability. Examples of documents that record facts related to a subject include criminal record inquiry reports, vehicle inspection certificate copies, family registers, and court judgments. Because these documents are prepared after careful review of their contents, or are prepared by public institutions, the reliability of the information recorded about the subject can be expected to be high.

[0050] In contrast, it is conceivable that the information about oneself expressed by the subject may include false information and inaccurate information due to errors, or other information that is contrary to the facts. Therefore, the information about oneself expressed by the subject may be less reliable than the information contained in documents that record facts related to the subject.

[0051] Here, documents that record information about a subject as expressed by the subject, whether orally or in writing, are referred to as documents based on the subject's statements. Documents based on the subject's statements may be created by the subject themselves. In the context of investigative documents, for example, statements of opinion and affidavits correspond to documents based on the subject's statements that were created by the subject themselves. Furthermore, documents based on the subject's statements may be created by a third party other than the subject, who obtained information about the subject as expressed by the subject. In the context of investigative documents, for example, various reports created by investigators correspond to documents based on the subject's statements that were created by a third party.

[0052] In the following, this embodiment describes an information processing device that evaluates the consistency between information contained in a document based on the subject's statement and information contained in a document recording facts about the subject.

[0053] Figure 12 is a schematic diagram showing the configuration of an information processing device according to one embodiment. The information processing device 200 has a configuration in which the analysis unit 130 of the information processing device 100 according to Embodiment 1 is replaced with an analysis unit 230. The analysis unit 230 has a configuration in which a consistency determination unit 233 is added to the analysis unit 130.

[0054] The consistency determination unit 233 determines whether the information regarding the same event is consistent across multiple documents, based on the 5W1H items included in the extracted item information INF2. This will be explained below with specific examples.

[0055] Assume that, as in Embodiment 1, the subject was employed by F Civil Engineering Co., Ltd. in City B after graduating from junior high school. Then, consider the case where the subject intentionally or mistakenly states a false place of employment, such as, "After graduating from junior high school, I was employed by a company called Z Construction Co., Ltd. in City B and worked as a civil engineering worker."

[0056] In this case, the consistency determination unit 233 can obtain information indicating the correct place of employment after graduating from junior high school by referring to the 5W1H items contained in documents that record facts about the subject, such as a copy of a judgment and a criminal record inquiry result report, as the item corresponding to "where" in the 5W1H items.

[0057] In this case, the consistency determination unit 233 can detect that the "Z Construction Co., Ltd." stated by the subject and the "F Civil Engineering Co., Ltd." recorded in the document containing facts about the subject are inconsistent. The consistency determination unit 233 then creates an information DIS indicating that the information stated by the subject is inaccurate. The consistency determination unit 233 outputs the information DIS to the timeline creation unit 140.

[0058] Subsequently, the timeline creation unit 140 displays, based on the information DIS, that there is inconsistent information in the timeline CT created in the same manner as in Embodiment 1.

[0059] Figure 13 shows an example of how inconsistent information is displayed in a timeline created by an information processing device according to one embodiment. In this example, to show that the company "Z Construction Co., Ltd." stated by the subject and "F Civil Engineering Co., Ltd." in the document recording facts about the subject are inconsistent, the corresponding display box is shown with a thick line (reference numeral 60 in Figure 13). Furthermore, to indicate the inconsistency in information, text information is displayed using a callout (reference numeral 70 in Figure 13).

[0060] The methods for displaying inconsistencies in information are not limited to those described above. For example, the text within the display frame may be formatted. Formatting of text may include various methods such as bolding, italics, changing the font, changing the font size, changing the text color, shading the text, and making the text blink. The text frame may also be formatted. Formatting of the text frame may include various methods such as changing the thickness of the frame's lines, changing the color of the frame, coloring the text within the frame, displaying patterns within the frame, and making the frame blink. In addition, although the above example describes displaying text information using a callout, the same formatting as the text frame and the text within the frame may be applied to the callout. Various display methods other than callouts may also be used. The callout may be displayed at all times or displayed only upon user request. For example, the callout may appear as a pop-up when the user moves the mouse cursor over a text frame displaying inconsistencies in information.

[0061] Next, the processing in the information processing device 200 will be described. Figure 14 is a flowchart showing the processing of the information processing device according to one embodiment.

[0062] Steps S11-S15 Steps S11 to S15 in Figure 14 are the same as steps S11 to S15 in Figure 10, so redundant explanations are omitted.

[0063] Step S21 The consistency determination unit 233 determines whether there are any inconsistencies among the 5W1H items included in the extracted item information INF2 regarding information about the same event concerning the subject across multiple documents. If there are no inconsistencies among the multiple documents, the consistency determination unit 233 proceeds to step S16.

[0064] Step S22 If the consistency determination unit 233 detects inconsistent items across multiple documents, it creates a Disability Information (DIS) indicating the inconsistency of the detected items.

[0065] Step S16 Step S16 in Figure 14 is the same as step S16 in Figure 10, so the redundant explanation is omitted.

[0066] Step S23 The timeline creation unit 140 displays the presence of information inconsistencies in the timeline CT, for example, as shown in Figure 13, based on the information DIS indicating information inconsistencies.

[0067] As described above, with this configuration, if there are inconsistencies among the 5W1H items included in the extracted item information INF2 regarding the same event, their existence can be displayed in the timeline. This allows the user of the information processing device 200 to easily understand that inconsistencies in the information about the subject have arisen due to differences in source.

[0068] In this case, the user of the information processing device 200 can analyze whether the inconsistency in the information is due to a false statement by the subject or simply an error by the subject. For example, in a criminal investigation, knowing whether or not the subject made a false statement allows the investigator, as the user, to proceed with the investigation while understanding the subject's intentions.

[0069] Furthermore, the consistency determination unit 233 may select information to display in the timeline CT from among the inconsistent information. The consistency determination unit 233 may also display the most recent information in time in the timeline CT. In this case, past information that does not match the latest information may be displayed in the timeline CT as supplementary information.

[0070] The above described an example of information inconsistency occurring between documents recording facts related to a subject and documents based on the subject's statements. However, information inconsistencies are not limited to this example.

[0071] Information inconsistencies can occur even in documents based on the statements of the subject. For example, a subject's statements may change between multiple cases or between multiple statements within a single case. In this case, the information processing device 200 can detect and display these changes in statements.

[0072] Furthermore, inconsistencies in information can occur in documents that record facts related to the subject. For example, the address may be written differently in a family register and a resident registration. In this case, the information processing device 200 can detect and display the discrepancy in the address written in the documents.

[0073] In this embodiment, the explanation assumes the use of investigative materials, but this is merely an example. For instance, in addition to investigative materials, other information managed by public institutions, such as the subject's resident registration and social insurance records, and other various types of information may also be referenced.

[0074] Other embodiments Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure can be made as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0075] In the above-described embodiment, the case where the document from which the information processing device acquires subject-related information is an investigation-related document was explained, but this is merely an example. For example, subject-related information may be acquired by the information processing device from various documents other than investigation-related documents, such as websites or documents containing personnel information of companies, etc., that contain records about a specific subject.

[0076] Furthermore, the information processing device may create a timeline CT based on subject-related information obtained from documents other than investigation-related documents.

[0077] Information related to the subject may include not only documents, but also text data obtained by using speech recognition to capture what the subject or other people have said. The information processing device may read the text data obtained by speech recognition. Alternatively, speech recognition may be implemented in the information acquisition unit of the information processing device to generate text data from the read speech data.

[0078] In the embodiments described above, the information processing apparatus according to the Disclosure was mainly described as a hardware configuration, but it is not limited thereto. It is also possible to realize the information processing apparatus according to the Disclosure by having a computer execute a computer program to perform any processing. These processing may be realized by having a computer, which includes at least one processor (e.g., a microprocessor, CPU, GPU, MPU, or DSP (Digital Signal Processor)), execute a program. Specifically, one or more programs including a set of instructions for causing a computer to perform algorithms related to these transmission signal processing or reception signal processing can be created and supplied to the computer.

[0079] Computer programs can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memory (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (random access memory)). Programs may also be supplied to a computer using various types of transient computer-readable media. Examples of transient computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable media can be supplied to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0080] The following shows an example of a computer configuration for realizing the information processing device according to the above-described embodiment. Figure 15 is a diagram showing an example of a computer configuration for realizing an information processing device. The information processing device can be realized by a computer 9000 such as a dedicated computer or a personal computer (PC). However, the computer does not need to be physically single; there may be multiple computers when performing distributed processing. As shown in Figure 15, the computer 9000 has, for example, a processor 9001, a ROM (Read Only Memory) 9002, a RAM (Random Access Memory) 9003, a storage unit 9004, a communication interface 9005, and a user interface 9006.

[0081] The processor 9001, ROM 9002, RAM 9003, memory unit 9004, communication interface 9005, and user interface 9006 are interconnected via bus 9007, enabling them to communicate with each other. While the operating system software necessary to run the computer is not described here, it will be implemented in the computer 9000 as appropriate.

[0082] ROM is composed of, for example, non-volatile semiconductor memory devices. ROM 9002 stores information such as various programs used by the computer 9000.

[0083] The storage unit 9004 is composed of various storage devices, such as hard disks and solid-state disks. Furthermore, the storage unit 9004 is not limited to storage devices installed in the computer 9000, but may also be external storage devices. External storage devices may include various communication means, such as cloud storage connected to the computer 9000 via a network. The storage unit 9004 stores information such as various programs and data used by the computer 9000.

[0084] RAM 9003 is composed of volatile semiconductor memory devices. Programs and data used by the processor 9001 are loaded into RAM 9003 as needed from either ROM 9002 or memory unit 9004, or both.

[0085] The processor 9001 may be composed of, for example, a CPU (Central Processing Unit). Alternatively, the processor 9001 may include not only a CPU but also a GPU (Graphics Processing Unit). A GPU is suitable for parallel processing of routine tasks, and by applying it to, for example, neural network processing, it is possible to improve processing speed compared to a CPU. The processor 9001 executes various processes as appropriate, based on various programs stored in the ROM 9002 or various programs and data held in the RAM 9003. The processor 9001 may also store the data generated by the processing in the RAM 9003 or the storage unit 9004 as appropriate.

[0086] The communication interface 9005 is an interface that connects the computer 9000 to a communication network such as the Internet or an intranet via various wired or wireless communication means. This allows the computer 9000 to communicate with other devices, systems, and sensors connected to the communication network.

[0087] The user interface 9006 includes, for example, a display unit that provides information so that the user can perceive it, such as through a display device, and an audio output unit that provides audio. The user interface 9006 also includes an input unit that allows the user to input information into the computer 9000 through user operation, such as a keyboard, mouse, and touch panel. Furthermore, the user interface 9006 may include devices such as sensors that acquire information useful to the user.

[0088] Here, the computer 9000 is described as a single device, but this is merely an example. The computer 9000 may consist of multiple physically separate devices. Some of these devices may be portable, while others may be stationary.

[0089] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments rather than with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings, for example, to create embodiments not explicitly shown or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate.

[0090] Some or all of the above embodiments may also be described as follows, but are not limited to the following:

[0091] (Note 1) Information acquisition means for obtaining subject-related information related to a specific subject from multiple documents, An extraction means for extracting multiple strings that meet predetermined criteria from the aforementioned subject-related information, Analysis means that organizes the aforementioned plurality of strings according to a predetermined format for the aforementioned specific subject and persons other than the aforementioned specific subject, detects strings among the plurality of strings that have a predetermined relationship, and outputs the organized strings and information indicating the relationship. The system includes a timeline creation means that, based on the organized strings and relationship-related information, displays strings relating to a specific subject and strings relating to a person other than the specific subject in parallel on a timeline, and creates a timeline that displays information indicating the strings having the relationship among the plurality of strings. Information processing device.

[0092] (Note 2) The timeline creation means displays, in a direction perpendicular to the direction of the time axis, a string of characters relating to the specific subject and a string of characters relating to a person other than the specific subject side by side. The information processing device described in Appendix 1.

[0093] (Note 3) The extraction means extracts the plurality of strings corresponding to the 5W1H, The aforementioned timeline creation means creates the timeline displaying a string corresponding to any of the 5W1H. The information processing device described in Appendix 1 or 2.

[0094] (Note 4) If a string of characters relating to a specific subject at the same time period and a string of characters relating to a person different from the specific subject indicate common or similar facts, the timeline creation means shall display information in the timeline indicating the existence of the string of characters indicating the common or similar facts. An information processing device as described in any one of the appendices 1 to 3.

[0095] (Note 5) The timeline creation means displays, as information indicating the existence of strings representing the common or similar facts, the regions in the timeline that correspond to the same period among the regions where strings representing the common or similar facts exist, in a way that makes them distinguishable. The information processing device described in Appendix 4.

[0096] (Note 6) The timeline creation means displays, as information indicating the existence of strings representing the common or similar facts, lines connecting the regions corresponding to the same period in the timeline where the strings representing the common or similar facts exist. The information processing device described in Appendix 4.

[0097] (Note 7) The aforementioned timeline creation means outputs the timeline to the display means, The display means displays the timeline. An information processing device as described in any one of the appendices 1 to 6.

[0098] (Note 8) The system further comprises a display means for displaying the timeline created by the timeline creation means. An information processing device as described in any one of the appendices 1 to 7.

[0099] (Note 9) If the analysis means finds that there are inconsistent strings among the multiple strings relating to the same event, it outputs information indicating the inconsistent strings to the timeline creation means. The aforementioned timeline creation means displays information indicating the inconsistent string in the timeline. An information processing device as described in any one of the appendices 1 to 8.

[0100] (Note 10) By obtaining subject-related information related to a specific subject from multiple texts, From the aforementioned information related to the subject, multiple strings that meet predetermined criteria are extracted, The plurality of strings are organized according to a predetermined format for the specific target person and persons other than the specific target person, and strings having a predetermined relationship among the plurality of strings are detected, and the organized strings and information indicating the relationship are output. Based on the organized strings and the relationship information, a timeline is created that displays the strings relating to the specific subject and the strings relating to a person other than the specific subject in parallel on a timeline, and displays information indicating the strings that have the relationship among the multiple strings. Information processing methods.

[0101] (Note 11) A process to retrieve subject-related information related to a specific subject from multiple documents, The process involves extracting multiple strings that meet predetermined criteria from the aforementioned information related to the subject, The process involves organizing the aforementioned multiple strings according to a predetermined format for the specified target person and persons other than the specified target person, detecting strings among the multiple strings that have a predetermined relationship, and outputting the organized strings and information indicating the relationship. The computer is instructed to perform the following processes: create a timeline that displays, on a timeline, the strings relating to a specific person and the strings relating to a person other than the specific person, based on the organized strings and the information indicating the relationships between them; and create a timeline that displays the information indicating the strings that have the relationships among the multiple strings. program. [Explanation of symbols]

[0102] 10, 100 Information Processing Devices 11, 110 Information acquisition section 12, 120 Extraction part 13, 130, 230 Analysis Department 14, 140 Chronology Creation Department 131 Chronological Order Section 132 Relationship Analysis Department 233 Consistency judgment part 1000 databases 1100 Investigation-related documents 9000 Computers 9001 Processor 9002 ROM 9003 RAM 9004 Storage section 9005 Communication Interface 9006 User Interface 9007 Bus CT chronology DIS Information INF1 Participant-Related Information INF2 extraction item information LBL Labeling Information TS0 Target audience time-series information TS1~TSn Related Personnel Timeline Information

Claims

1. Information acquisition means for obtaining subject-related information related to a specific subject from multiple documents, An extraction means for extracting multiple strings that meet predetermined criteria from the aforementioned subject-related information, Analysis means that organizes the aforementioned plurality of strings according to a predetermined format for the aforementioned specific subject and persons other than the aforementioned specific subject, detects strings among the plurality of strings that have a predetermined relationship, and outputs the organized strings and information indicating the relationship. The system includes a timeline creation means that, based on the organized strings and relationship-related information, displays strings relating to a specific subject and strings relating to a person other than the specific subject in parallel on a timeline, and creates a timeline that displays information indicating the strings having the relationship among the plurality of strings. Information processing device.

2. The timeline creation means displays, in a direction perpendicular to the direction of the time axis, a string of characters relating to the specific subject and a string of characters relating to a person other than the specific subject side by side. The information processing apparatus according to claim 1.

3. The extraction means extracts the plurality of strings corresponding to the 5W1H, The aforementioned timeline creation means creates the timeline displaying a string corresponding to any of the 5W1H. The information processing apparatus according to claim 1 or 2.

4. If a string of characters relating to a specific subject at the same time period and a string of characters relating to a person different from the specific subject indicate common or similar facts, the timeline creation means shall display information in the timeline indicating the existence of the string of characters indicating the common or similar facts. The information processing apparatus according to claim 1 or 2.

5. The timeline creation means displays, as information indicating the existence of strings representing the common or similar facts, the regions in the timeline that correspond to the same period among the regions where strings representing the common or similar facts exist, in a way that makes them distinguishable. The information processing apparatus according to claim 4.

6. The timeline creation means displays, as information indicating the existence of strings representing the common or similar facts, lines connecting the regions corresponding to the same period in the timeline where the strings representing the common or similar facts exist. The information processing apparatus according to claim 4.

7. The aforementioned timeline creation means outputs the timeline to the display means, The display means displays the timeline. The information processing apparatus according to claim 1 or 2.

8. The system further comprises a display means for displaying the timeline created by the timeline creation means. The information processing apparatus according to claim 1 or 2.

9. By obtaining subject-related information related to a specific subject from multiple texts, From the aforementioned information related to the subject, multiple strings that meet predetermined criteria are extracted, The plurality of strings are organized according to a predetermined format for the specific target person and persons other than the specific target person, and strings having a predetermined relationship among the plurality of strings are detected, and the organized strings and information indicating the relationship are output. Based on the organized strings and the relationship information, a timeline is created that displays the strings relating to the specific subject and the strings relating to a person other than the specific subject in parallel on a timeline, and displays information indicating the strings that have the relationship among the multiple strings. Information processing methods.

10. A process to retrieve subject-related information related to a specific subject from multiple documents, The process involves extracting multiple strings that meet predetermined criteria from the aforementioned information related to the subject, The process involves organizing the aforementioned multiple strings according to a predetermined format for the specified target person and persons other than the specified target person, detecting strings among the multiple strings that have a predetermined relationship, and outputting the organized strings and information indicating the relationship. The computer is instructed to perform the following process: Based on the organized strings and the information indicating the relationships, the computer displays the strings relating to the specific subject and the strings relating to a person other than the specific subject in parallel on a timeline, and creates a timeline that displays information indicating the strings that have the relationships among the multiple strings. program.

Images