Information processing device, information processing method, and program
The information processing device addresses the challenge of understanding medium- to long-term changes by classifying and visualizing future event information, enabling the automatic generation of roadmaps that depict trends across categories, thus facilitating the prediction of future developments with reduced effort.
Patent Information
- Application Number
- PCT/JP2023/019949
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-29
- Publication Date
- 2024-12-05
AI Technical Summary
Existing methods, such as horizon scanning, face difficulties in grasping medium- to long-term changes in specific fields due to the complexity and requirement of extensive information collection and expert experience needed for creating practical roadmaps.
An information processing device that classifies future event information into categories like PEST+E, extracts relevant information using user-specified keywords, and generates a roadmap with a time axis, allowing for automatic creation of a roadmap that visualizes relationships between categories, thereby supporting understanding of medium- to long-term changes.
Enables the creation of practical roadmaps with reduced operational effort, facilitating the visualization of relationships between political, economic, social, and technological trends, aiding in predicting future developments across specialist fields.
Smart Images

Figure JP2023019949_05122024_PF_FP_ABST
Abstract
Description
Information processing device, information processing method, and program
[0001] The present invention relates to an information processing device, an information processing method, and a program.
[0002] Traditionally, one method of predicting the future is "horizon scanning," which involves periodically visiting and crawling specific websites and using natural language processing to automatically identify "signs" of change, such as new technologies or trend shifts, based on the frequency of words that appear.
[0003] KIDSASHI (Kizashi), [online], Internet <URL: https: / / www.nistep.go.jp / wp / wp-content / uploads / KIDSASHI.pdf>
[0004] "Horizon scanning" can capture "signs" of change in the world, such as new technologies and points of change in trends in specific fields, but it is difficult to capture how a specific field will change (develop and progress) in the future over a medium- to long-term time frame.
[0005] The present invention has been made in consideration of the above points, and aims to support the understanding of medium- to long-term changes in a specific field.
[0006] In order to solve the above problem, the information processing device has a classification unit configured to classify information about future events collected via a network into multiple categories based on predetermined classification criteria, an extraction unit configured to extract information related to keywords specified by a user from the information about future events, and a generation unit configured to generate a roadmap in which each piece of extracted information corresponds to the timing information contained in the information on the horizontal axis and is arranged at a position on the vertical axis corresponding to the category into which the information is classified.
[0007] It can help understand medium- to long-term changes in specific fields.
[0008] It is a diagram for explaining an outline of an embodiment of the present invention. It is a diagram for showing an example of a hardware configuration of an information processing device 10 in an embodiment of the present invention. It is a diagram for showing an example of a functional configuration of an information processing device 10 in an embodiment of the present invention. It is a flowchart for explaining an example of a processing procedure executed by the information processing device 10. It is a diagram for showing an example of a roadmap.
[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will now be described with reference to the accompanying drawings. Fig. 1 is a diagram for explaining an outline of an embodiment of the present invention. In this embodiment, an information processing device 10 executes the following processes.
[0010] First, the information processing device 10 collects and stores various (multiple) event information (when and what events are likely to occur or be realized) about the future from government documents, news releases, media articles, etc. via a network by web crawling (S1).
[0011] Next, the information processing device 10 classifies the accumulated event information into multiple categories of PEST+E (Politics, Economy, Society, Technology, Environment), and stores the classified event information together with information on the occurrence and realization time of the event (S2).
[0012] Next, the information processing device 10 accepts input of keywords from the user that indicate a particular viewpoint (a subject on which the user is paying attention), extracts information that is highly relevant to the keywords from the stored event information, and maps the extracted information on a time axis by category, thereby automatically generating the roadmap desired by the user (S3).
[0013] Roadmaps are also used as a method for predicting the future. Roadmaps are often created based on the information gathering, accumulation, and experience of experts in a specific field. Creating a roadmap that takes into account the influence of external factors outside of that field requires extensive information gathering and experience from experts in the influencing field. Therefore, creating a highly practical roadmap is difficult, but according to this embodiment, such a roadmap can be generated with minimal operations.
[0014] The information processing device 10 will be described in detail below. Fig. 2 is a diagram showing an example of the hardware configuration of the information processing device 10 according to an embodiment of the present invention. The information processing device 10 in Fig. 2 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a processor 104, and an interface device 105, all of which are interconnected via a bus B.
[0015] A program that realizes processing in the information processing device 10 is provided by a recording medium 101 such as a CD-ROM. When the recording medium 101 storing the program is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program does not necessarily have to be installed from the recording medium 101, but may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program as well as necessary files, data, etc.
[0016] When an instruction to start a program is received, the memory device 103 reads the program from the auxiliary storage device 102 and stores it. The processor 104 is a CPU or a GPU (Graphics Processing Unit), or a CPU and a GPU, and executes functions related to the information processing device 10 in accordance with the program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.
[0017] FIG. 3 is a diagram showing an example of the functional configuration of an information processing device 10 according to an embodiment of the present invention. In FIG. 3, the information processing device 10 includes an input unit 11, a collection unit 12, a classification unit 13, an extraction unit 14, a generation unit 15, and an output unit 16. Each of these units is implemented by a processor 104 executing one or more programs installed in the information processing device 10. The information processing device 10 also utilizes databases (storage units) such as a crawling destination DB 17 and a classification DB 18. Each of these databases can be implemented using, for example, an auxiliary storage device 102 or a storage device connectable to the information processing device 10 via a network.
[0018] The following describes the processing procedure executed by the information processing device 10. FIG. 4 is a flowchart illustrating an example of the processing procedure executed by the information processing device 10.
[0019] In step S101, the collection unit 12 crawls the web based on the crawling destination DB 17 to collect information (time and content) about future events from government documents, news releases, and media via the network, and saves (accumulates) the collected information in, for example, the auxiliary storage device 102. The crawling destination DB 17 stores a list of crawling destination information (e.g., URLs). The crawling destinations are sites that publish information about future events (information suggesting future events). Therefore, in step S101, information about future events is expected to be collected. The collected and accumulated information about future events (time and content) is hereinafter referred to as "event information." For example, from an information source that states "The Japanese government will achieve carbon neutrality by 2050," event information such as {time: 2050, content: Japan achieves carbon neutrality} is collected and accumulated. Furthermore, from an information source that states "By 2035, 100% of new passenger car sales will be electric vehicles," event information such as {time: 2035, content: 100% of new passenger car sales will be electric vehicles} is collected and accumulated. If the original text is long, summary may be performed as appropriate to collect the content.
[0020] Examples of sites that publish information about upcoming events include government sites (such as government ministries), corporate sites, and news media sites. The list of suitable crawling sites may change daily. To keep the list up to date, the list may be updated through autonomous learning.
[0021] Next, the classification unit 13 classifies the accumulated event information into PEST+E (Politics, Economy, Society, Technology, Environment) categories based on predetermined classification criteria defined in the classification DB 18 (S102). The classification DB 18 stores information indicating criteria for classifying information into PEST+E categories (hereinafter referred to as "classification criteria"). For example, the classification DB 18 registers classification examples for each category. A classification example for a certain category refers to event information or one or more words classified into that category. For example, when classifying certain event information, the classification unit 13 evaluates, for each category, the similarity between the event information and each classification example belonging to that category. For example, natural language processing may be used to convert the event information and each classification example into vectors, and the similarity may be evaluated by calculating the cosine similarity between the converted vectors. The classification unit 13 classifies the event information into the category with the highest similarity (e.g., the largest average cosine similarity). For example, if the event information is "Time: 2050, Content: Japan achieving carbon neutrality," the classification result will be "Category: 'Politics,' Time: 2050, Content: Japan achieving carbon neutrality." Hereinafter, event information with a classification result attached will be referred to as "classification information."
[0022] It is desirable that the classification criteria be updated daily, and therefore the classification criteria may be updated by autonomous learning.
[0023] At any timing thereafter, the extraction unit 14 accepts a character string indicating a viewpoint (hereinafter referred to as a "keyword") from the user (S103). In this embodiment, an example is shown in which "carbon neutral" is specified. Note that step S103 is executed asynchronously with steps S101 and S102.
[0024] Next, the extraction unit 14 extracts classification information related to the keyword from the classification information obtained in step S102 (S104). The keyword and each classification information may be converted into a vector using natural language processing, and classification information related to a vector whose cosine similarity with the vector related to the keyword is equal to or greater than a threshold may be extracted as classification information related to the keyword. In addition to classification information similar to the keyword, classification information including co-occurring words with the keyword may also be extracted as information related to the keyword. Words co-occurring with the keyword may be identified using, for example, a co-occurring word dictionary created in advance. In this embodiment, it is assumed that classification information including words such as "renewable energy" and "solar power generation," which are co-occurring words with "carbon neutral," has been extracted.
[0025] Next, the generation unit 15 generates a roadmap by arranging (mapping) each piece of extracted classification information in a coordinate system with the PEST+E category on the vertical axis and the time axis on the horizontal axis (S105). At this time, the generation unit 15 arranges each piece of classification information at a position on the horizontal axis corresponding to the time information of the classification information and at a position on the vertical axis corresponding to the category of the classification information. As a result, a roadmap such as that shown in FIG. 5 is generated.
[0026] In addition, when the contents of multiple pieces of classification information arranged on the roadmap are similar (the similarity satisfies a predetermined condition) and the multiple pieces of classification information include different time information (years), the generation unit 15 may group the multiple pieces of classification information using a graphic (horizontal double arrows in FIG. 5 ) that indicates the time width of the time information of the multiple pieces of classification information, and may leave a portion of the multiple pieces of classification information (for example, one piece) as a representative piece in the center of the time width. Whether the similarity of the classification information satisfies the predetermined condition may be determined based on the cosine similarity of vectors related to the classification information, etc.
[0027] Next, the output unit 16 outputs the generated roadmap (S106). For example, the output may be performed by displaying it on a display device, or by saving it in the auxiliary storage device 102 or the like in the form of a file, etc. Alternatively, information indicating the identified character string may be transmitted via a network.
[0028] As described above, according to this embodiment, it is possible to automatically generate a roadmap for a specific field that corresponds to the perspective that the user wants to see from a variety of comprehensively accumulated information about the future. Because the event information on the roadmap has mutually influential relationships between PEST+E categories, visualizing this information in a unified manner makes it possible to acquire the knowledge necessary to predict future developments from relationships that take into account political, economic, and social trends, rather than simply looking at technology. Furthermore, because the roadmap is generated based on a variety of information from around the world, it is possible to create a roadmap that spans the fields of experts, which would be difficult (and would require a huge amount of time) to do manually.
[0029] Such a roadmap can help understand medium- to long-term changes in a particular field.
[0030] Although the above example shows the event information being classified into the PEST+E category, it may be classified into other categories. For example, the event information may be classified into the categories of "technology," "product / service," and "market." In this case, the vertical axis of the generated roadmap corresponds to these categories.
[0031] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.
[0032] REFERENCE SIGNS LIST 10 Information processing device 11 Input unit 12 Collection unit 13 Classification unit 14 Extraction unit 15 Generation unit 16 Output unit 17 Crawling destination DB 18 Classification DB 100 Drive device 101 Recording medium 102 Auxiliary storage device 103 Memory device 104 Processor 105 Interface device B Bus
Claims
1. An information processing device comprising: a classification unit configured to classify information about future events collected via a network into a plurality of categories based on predetermined classification criteria; an extraction unit configured to extract information related to keywords specified by a user from the information about the future events; and a generation unit configured to generate a roadmap in which each piece of extracted information corresponds to the timing information contained in the information on the horizontal axis and is arranged at a position on the vertical axis corresponding to the category into which the information is classified.
2. The information processing device according to claim 1, characterized in that the generation unit is configured to place on the roadmap a figure indicating a time span based on timing information contained in each of a plurality of pieces of information whose similarity satisfies a predetermined condition.
3. The information processing apparatus according to claim 2, characterized in that the generating unit is configured to arrange a later part of the plurality of pieces of information in the roadmap.
4. An information processing method characterized in that a computer executes the following steps: a classification step for classifying information about future events collected via a network into a plurality of categories based on predetermined classification criteria; an extraction step for extracting information related to keywords designated by a user from the information about the future events; and a generation step for generating a roadmap in which each piece of extracted information corresponds to the timing information contained in the information on the horizontal axis and is arranged at a position on the vertical axis corresponding to the category into which the information is classified.
5. A program that causes a computer to execute the following steps: a classification step for classifying information about future events collected via a network into multiple categories based on predetermined classification criteria; an extraction step for extracting information related to keywords specified by a user from the information about the future events; and a generation step for generating a roadmap in which each piece of extracted information corresponds to the timing information contained in the information on the horizontal axis and is arranged at a position on the vertical axis corresponding to the category into which the information is classified.
Citation Information
Patent Citations
Information extraction device
JP1998340275A
Event analyzing device and program device stored with event analyzing program
JP2001216311A
Future expression collection system, future expression collection method and future expression collection program
JP2010205006A
