Information generation device, information generation method, and program

Abstract

This information generation device comprises: an associated information acquisition unit that acquires information associated with a selected field; a subject matter extraction unit that extracts a subject matter from the acquired information; and a temporal sequence information generation unit that generates temporal sequence information relating to the extracted subject matter.

Description

Technical Field

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

Background Art

[0002] In recent years, various risks such as the spread of infectious diseases at the global level, server attacks, climate change, and resource shortages have been a concern. Moreover, the international situation has become extremely complex. For companies, it is desirable to formulate business strategies after predicting the social image in the near future to some extent. However, against the backdrop described above, it has become extremely difficult to accurately predict the future. Among them, in a method called scenario planning, a method has been proposed in which, after analyzing the current situation, a plurality of future scenarios are created, and business strategies for companies are formulated in each of the future scenarios (Non-Patent Document 1).

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional techniques described above, since rich knowledge and experience of experts are required, such as the structuring of events and the way of thinking about future prospects, there is a problem that it is difficult for laypersons to analyze information such as practical scenarios.

[0005] The disclosed technology aims to facilitate the analysis of information.

Means for Solving the Problems

[0006] The disclosed technology includes a related information acquisition unit that acquires information related to a selected field, and from the acquired information A plurality of a subject extraction unit that extracts a subject, and the extracted A plurality of subject For each of them, based on the information about the subject, extract events from the past to the future in chronological order, and summarize the extracted events time series summarized in a time series information generation unit that generates information, and An output unit that outputs an image in which the plurality of subjects extracted by the subject extraction unit are plotted in the selected analysis frame; is an information generation device comprising the same.

Advantages of the Invention

[0007] The analysis of information can be facilitated.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Modes for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention (the present embodiment) will be described with reference to the drawings. The embodiments described below are merely examples, and the embodiments to which the present invention is applied are not limited to the following embodiments.

[0010] (Regarding the prior art) First, the prior art will be described. Conventionally, in a method called scenario planning, a method has been proposed in which, after analyzing the current situation, a plurality of future scenarios are created, and business strategies for each future scenario are formulated.

[0011] FIG. 1 is a diagram showing an example of a conventional scenario planning method (Non-Patent Document 1). Non-Patent Document 1 discloses, as a first procedure, a procedure for structuring the current business in the world and classifying events that are easy to predict the future and events that are difficult to predict the future. And, as a second procedure, a procedure for further deeply analyzing events that are difficult to predict the future and have a large impact, taking into account several possibilities, and creating a plurality of scenarios is disclosed. Furthermore, as the last procedure, a procedure for devising strategies in each scenario is disclosed.

[0012] However, in the prior art, since rich knowledge and experience of experts are required, such as structuring of events and ways of thinking about future prospects, there is a problem that it is difficult for laypersons to generate practical scenarios.

[0013] (Outline of this embodiment) The information generation device according to this embodiment is a device that extracts a theme from related information such as news and statistical reports based on a selected field, analysis frame, etc., and generates time-series information in which events for each theme are arranged in time series. The time-series information may be called a scenario. Also, the theme may be called a player in the scenario. As a result, practical scenario planning becomes possible even for a person who does not have specialized knowledge and expertise.

[0014] (Example of functional configuration of the information generation device according to this embodiment) FIG. 2 is a diagram showing an example of the functional configuration of the information generation device according to this embodiment. The information generation device 100 includes an extraction source DB 110, an arithmetic unit 120, an evaluation formula DB 130, a data storage unit 140, an input unit 150, and an output unit 160.

[0015] The extraction source DB 110 is a database that stores the information to be extracted. Specifically, the extraction source DB 110 includes a news DB 111, a report DB 112, a basic field DB 113, a basic analysis framework DB 114, and a theme DB 115.

[0016] The news DB 111 is a database that stores text data indicating news articles.

[0017] The report DB 112 is a database that stores report data such as statistical reports.

[0018] The basic field DB 113 is a database that stores information indicating the basic fields (basic fields) to be extracted. The basic fields may be, for example, the "environmental energy field", the "information processing field", etc.

[0019] The basic analysis framework DB 114 stores information indicating the basic framework (basic analysis framework) for analyzing the information to be extracted. The basic analysis framework may be, for example, an analysis framework such as the PEST analysis framework often used in scenario planning methods, or the three-layer structure framework called the SDGs wedding cake.

[0020] The theme DB 115 is a database that stores information indicating the themes to be extracted. The themes may be, for example, "electric vehicles", "energy industry (oil)", etc.

[0021] The calculation unit 120 performs various processes on the extracted information to generate time-series information. Specifically, the calculation unit 120 includes a related information acquisition unit 121, a preprocessing unit 122, a theme extraction unit 123, a ranking calculation unit 124, and a time-series information generation unit 125.

[0022] The related information acquisition unit 121 searches for and extracts relevant articles from the news DB 111 and the report DB 112 according to the selected basic field and basic analysis framework. Note that the related information acquisition unit 121 may acquire daily news articles, industry analysis reports, etc. from other server devices via a communication network (such as the Internet). The related information acquisition unit 121 stores the acquired information in the data storage unit 140.

[0023] The preprocessing unit 122 performs preprocessing on the acquired related information. For example, the preprocessing unit 122 may reconstruct the sentences included in the related information. Specifically, the preprocessing unit 122 may split long sentences into short sentences or complement the subject in sentences without a subject. By the preprocessing unit 122, the sentences included in the related information are converted into sentences whose meaning can be read more accurately by machine learning techniques or the like.

[0024] The theme extraction unit 123 extracts themes from the related information on which preprocessing has been performed. For example, the theme extraction unit 123 may extract themes in the evaluation field by natural language processing and display an image in which the themes extracted in the selected basic analysis framework are plotted on a screen or the like. The theme extraction unit 123 may select words that can be themes from the theme DB 114. The theme extraction unit 123 may extract a plurality of themes, and may also extract an index indicating the relationship between the plurality of extracted themes, occurrence events, etc.

[0025] When a plurality of themes are extracted, the ranking calculation unit 124 ranks the themes based on the frequency of occurrence of words indicating the themes in the text, or an index indicating the relationship with other themes, occurrence events, etc. Note that the ranking of the themes may reflect the result of receiving the user's selection. The ranking calculation unit 124 may extract the theme with the highest rank as the key theme based on the ranking result.

[0026] The time-series information generation unit 125 extracts events (policies, plans, etc.) from the past to the future in time series based on the main information regarding the theme (or the key theme), and generates information (time-series information) organized in time series. When the time-series information generation unit 125 cannot achieve consistency (or a branch occurs), it may generate time-series information grouped for each of a plurality of information groups. At this time, each information group may be called a story.

[0027] The evaluation formula DB 130 is a database in which information indicating an evaluation formula for evaluating related information is stored. For example, the evaluation formula DB 130 stores information indicating a ranking calculation formula 131. The ranking calculation formula 131 is a calculation formula for ranking the theme (or the key theme).

[0028] The data storage unit 140 stores information such as news and statistical reports acquired by the related information acquisition unit 121.

[0029] The input unit 150 receives an input operation by the user. For example, the input unit 150 receives an operation for selecting a basic field, a basic analysis framework, etc.

[0030] The output unit 160 outputs various types of information. For example, the output unit 160 may display information on a screen or the like, or may transmit information to another device via a communication network or the like.

[0031] (Example of the operation of the information generation device according to the present embodiment) Next, the operation of the information generation device 100 will be described. The information generation device 100 executes information generation processing by a user operation or the like, or periodically.

[0032] FIG. 3 is a flowchart showing an example of the flow of information generation processing according to the present embodiment. The input unit 150 receives the selection of the basic field and the basic analysis framework (step S11). The user selects, for example, the field to be evaluated and the analysis framework to be used from the basic field DB 113 and the basic analysis framework 114.

[0033] Next, the related information acquisition unit 121 acquires related information by searching for and extracting related articles from the news DB 111 and the report DB 112 (step S12). The acquired related information is stored in the data storage unit 140.

[0034] Subsequently, the preprocessing unit 122 performs preprocessing on the acquired related information (step S13). Next, the theme extraction unit 123 extracts a theme from the related information on which the preprocessing has been performed (step S14).

[0035] When a plurality of themes are extracted, the ranking calculation unit 124 ranks the themes using the ranking calculation formula 131 (step S15). Then, the time series information generation unit 125 generates time series information regarding the theme (or the key theme) (step S16).

[0036] The output unit 160 outputs the generated time series information (step S17). For example, the output unit 160 may display the generated time series information on a screen or the like.

[0037] (Implementation Results) Next, an example of the specifically implemented results of the information generation apparatus 100 according to the present embodiment will be described. Hereinafter, an example of generating time series information indicating the impact on the environmental energy field in the United States due to the change of power in the United States by President XXX of the United States and future scenarios will be shown.

[0038] In step S11 shown in FIG. 3, the input unit 150 received the selection of "environmental energy field" as the basic field. In addition, the input unit 150 received the selection of "PEST analysis framework" as the basic analysis framework.

[0039] FIG. 4 is a diagram showing an example of the basic analysis framework according to the present embodiment. The basic analysis framework shown in FIG. 4 is a PEST analysis framework, and is an analysis framework for analyzing the relationship between each piece of information by plotting information on four indicators of politics, economy, society, and technology.

[0040] FIG. 5 is a diagram showing an example of an extraction source of related information according to the present embodiment. In step S12 shown in FIG. 3, the extraction target by the related information acquisition unit 121 is, for example, an article of a news site publicly available on the Internet or the like, an analysis report, or the like.

[0041] In step S13 of the information generation process, the preprocessing unit 122 preprocessed the original text as follows. The original text is as follows.

[0042] "In the area of infrastructure investment, invest $2 trillion in clean energy infrastructure and the like over four years to rebuild roads, bridges, water supply facilities, power grids, etc., and create millions of jobs. Also, to promote the spread of electric vehicles (EVs), install EV charging facilities at 500,000 locations across the United States. The federal government and local governments are to procure zero-emission vehicles."

[0043] The preprocessing result by the preprocessing unit 122 for the above-described original text is as follows.

[0044] "In the area of infrastructure investment, the federal government invests $2 trillion in clean energy infrastructure and the like over four years. The federal government uses this investment to rebuild roads, bridges, water supply facilities, power grids, etc., and create millions of jobs. Also, to promote the spread of electric vehicles (EVs), the federal government invests and installs EV charging facilities at 500,000 locations across the United States. The federal government and local governments are to procure zero-emission vehicles."

[0045] FIG. 6 is a diagram showing an example of an extraction result of a theme according to the present embodiment. In step S14 of the information generation process, the theme extraction unit 123 generated information in which the theme extracted as shown in FIG. 6 was plotted in the basic analysis framework.

[0046] FIG. 7 is a diagram showing an example of ranking of the subject according to the present embodiment. In step S15 of the information generation process, the ranking calculation unit 124 ranks players (subjects) in the order of (1) electric vehicle, (2) energy industry (oil),... based on the appearance frequency of words as subjects.

[0047] Then, in step S16 of the information generation process, the time-series information generation unit 125 generated time-series information regarding the subject with the highest priority as follows.

[0048] · The penetration rate of EVs in the United States was 3% in 2018, but increased to 7% in 2019 and 8% in 2020. · By the end of 2025, U.S. automakers will invest $27 billion in electric vehicles (EVs) and autonomous technology, and ZZZ will also invest $29 billion during the same period. · By 2025, AAA has announced a goal of making 40% of the new cars sold in the U.S. market electric models, including hybrid cars. · By 2025, BBB will install 500,000 EV charging stations. · By 2030, the three major U.S. automakers (Big Three) will announce on the 5th that they aim to increase the ratio of electric vehicles (EVs) in new car sales to 40-50% by 2030. · By 2035, the state of California will ban the sale of new gasoline-powered cars.

[0049] The user may separately use a scenario planning method or the like to analyze the impact of the change of the Biden administration on the U.S. environmental energy field, particularly on the electric vehicle industry. According to the information generation device 100 according to the present embodiment, the analysis becomes easier.

[0050] According to the information generation device 100 according to the present embodiment, based on the selected field, analysis frame, etc., a subject is extracted from related information such as news and statistical reports, and time-series information in which events for each subject are arranged in time series is generated. Therefore, the analysis of information can be facilitated.

[0051] (Hardware configuration example according to this embodiment) The information generation device 100 can be realized, for example, by causing a computer to execute a program describing the processing contents described in this embodiment. Note that this "computer" may be a physical machine or a virtual machine on the cloud. When using a virtual machine, the "hardware" described here is virtual hardware.

[0052] The above program can be recorded on a computer-readable recording medium (such as a portable memory), saved, or distributed. It is also possible to provide the above program through a network such as the Internet or email.

[0053] FIG. 8 is a diagram showing a hardware configuration example of the above computer. The computers in FIG. 4 each have a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., which are mutually connected by a bus B.

[0054] A program for realizing the processing on the computer is provided, for example, by a recording medium 1001 such as a CD-ROM or a memory card. When the recording medium 1001 storing the program is set in the drive device 1000, the program is installed from the recording medium 1001 to the auxiliary storage device 1002 via the drive device 1000. However, the installation of the program does not necessarily have to be performed from the recording medium 1001, and it may be downloaded from another computer via a network. The auxiliary storage device 1002 stores the installed program and also stores necessary files, data, etc.

[0055] When there is an instruction to start a program, the memory device 1003 reads and stores the program from the auxiliary storage device 1002. The CPU 1004 realizes the functions related to the device according to the program stored in the memory device 1003. The interface device 1005 is used as an interface for connecting to a network. The display device 1006 displays a GUI (Graphical User Interface) etc. according to the program. The input device 1007 is composed of a keyboard, a mouse, buttons, or a touch panel etc., and is used to input various operation instructions. The output device 1008 outputs the calculation result. Note that the above computer may be provided with a GPU (Graphics Processing Unit) or a TPU (Tensor processing unit) instead of the CPU 1004, or may be provided with a GPU or a TPU in addition to the CPU 1004. In that case, for example, the GPU or the TPU may execute the processing that requires special calculations, and the CPU 1004 may execute the other processing, and the processing may be executed in a shared manner.

[0056] (Summary of the Embodiment) This specification describes at least an information generation device, an information generation method, and a program described in each of the following items. (Item 1) A related information acquisition unit that acquires information related to a selected field, A theme extraction unit that extracts a theme from the acquired information, A time series information generation unit that generates time series information related to the extracted theme, and An information generation device. (Item 2) When a plurality of themes are extracted, it further includes a ranking calculation unit that calculates the priority order of the plurality of themes, The time series information generation unit preferentially generates the time series information with the higher priority theme, The information generation device according to Item 1. (Item 3) The information generation apparatus further includes a preprocessing unit that performs preprocessing for converting the sentences of the information acquired by the related information acquisition unit into sentences suitable for natural language processing. The subject extraction unit extracts a subject from the preprocessed information by natural language processing. The information generation apparatus according to claim 1 or 2. (Item 4) The information generation apparatus further includes an output unit that outputs an image in which the subject extracted by the subject extraction unit is plotted on a selected analysis frame. The information generation apparatus according to any one of claims 1 to 3. (Item 5) An information generation method executed by an information generation apparatus, A step of acquiring information related to a selected field, A step of extracting a subject from the acquired information, A step of generating time-series information related to the extracted subject, and comprising. Information generation method. (Item 6) A program for causing a computer to function as each unit in the information generation apparatus according to any one of claims 1 to 4.

[0057] According to any of the above configurations, a technique is provided that enables easy analysis of information. According to the second aspect, time-series information can be generated with priority given to the subjects with high priority. According to the third aspect, the sentences can be converted into sentences suitable for natural language processing to improve the accuracy of processing. According to the fourth aspect, an image in which the subject is plotted on the analysis frame can be output.

[0058] As described above, the present embodiment has been described, but the present invention is not limited to such a specific embodiment, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.

Explanation of Signs

[0059] 100 Information generation apparatus 110 Extraction source DB 120 Calculation Unit 121 Related Information Acquisition Unit 122 Pretreatment Unit 123 Subject Extraction Unit 124 Ranking Calculation Unit 125 Time-Series Information Generation Unit 130 Evaluation Formula DB 131 Ranking Calculation Formula 140 Data Storage Unit 150 Input Unit 160 Output Unit 1000 Drive Device 1001 Recording Medium 1002 Auxiliary Storage Device 1003 Memory Device 1004 CPU 1005 Interface Device 1006 Display Device 1007 Input Device 1008 Output Device

Claims

1. a related information acquisition unit that acquires information related to a selected field; a subject extraction unit that extracts a plurality of subjects from the acquired information; for each of the plurality of extracted subjects, based on information related to the subject, an event series information generation unit that extracts events from the past to the future in time series and generates information that summarizes the extracted events in time series; an output unit that outputs an image in which the plurality of subjects extracted by the subject extraction unit are plotted in a selected analysis frame; and an information generation device.

2. The information generation device according to claim 1, further comprising a ranking calculation unit that calculates the priority order of the plurality of subjects when the plurality of subjects are extracted, wherein the event series information generation unit preferentially generates the event series information for the subject with the higher priority. The information generation device according to claim 1.

3. The information generation device according to claim 1 or 2, further comprising a preprocessing unit that performs preprocessing for converting the text of the information acquired by the related information acquisition unit into text suitable for natural language processing, wherein the subject extraction unit extracts subjects by natural language processing from the information that has been preprocessed. The information generation device according to claim 1 or 2.

4. An information generation method executed by an information generation device, comprising: a step of acquiring information related to a selected field; a subject extraction step of extracting a plurality of subjects from the acquired information; for each of the plurality of extracted subjects, based on information related to the subject, a step of extracting events from the past to the future in time series and generating information that summarizes the extracted events in time series; a step of outputting an image in which the plurality of subjects extracted in the subject extraction step are plotted in a selected analysis frame. An information generation method.

5. A program for causing a computer to function as each unit in the information generation device according to any one of claims 1 to 3.

Images