Information processing method, information processing system, and program

The information processing method and system effectively filter out irrelevant information by matching internal topics from organizational text with general text information, ensuring that only relevant data is output, thus addressing the challenge of acquiring interesting information for organizations.

WO2024228291A1PCT designated stage expired Publication Date: 2024-11-07PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2024/007705
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-01
Filing Date
2024-03-01
Publication Date
2024-11-07

AI Technical Summary

Technical Problem

Organizations face challenges in acquiring and filtering information that is relevant to their interests from both internal and external sources, leading to the dissemination of uninteresting information.

Method used

An information processing method and system that acquires internal text information, analyzes it to extract relevant topics, and matches them with general text information using topic model analysis and similarity determination to output only the information that is of interest, thereby filtering out irrelevant data.

Benefits of technology

This approach ensures that organizations receive information that is pertinent to their interests, improving the relevance and usefulness of the information provided.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2024007705_07112024_PF_FP_ABST
    Figure JP2024007705_07112024_PF_FP_ABST
Patent Text Reader

Abstract

This information processing method includes: an internal information acquisition step (S10) of acquiring information expressed by a person as internal text information (it); a general information acquisition step (S30) of acquiring general text information (ig) included in disclosed general information (IG); an internal topic acquisition step (S20) of acquiring, by analyzing the internal text information (it), one or more internal topics (tp) related to the internal text information (it); a matching determination step (S40) of determining matching between the internal topics (tp) and the general text information (ig); and an output step (S50) of outputting general information (IG) including the general text information (ig) matched in the matching determination step.
Need to check novelty before this filing date? Find Prior Art

Description

Information processing method, information processing system, and program

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

[0002] Patent Literature 1 discloses an information processing device that allows users to browse articles and comments that match their interests. This information processing device sets themes that include articles from news articles and extraction conditions for articles included in the themes, and accepts the selection of a theme from a user. Comments posted on articles included in the theme are then accepted from the user who has selected the theme, and are sent together with the articles to other users who have selected the same theme.

[0003] JP 2014-49094 A

[0004] When an organization such as a company undertakes a new initiative, it acquires a variety of information from both internal and external sources. However, the information acquired from internal and external sources may include information that is not of interest to the organization or individuals belonging to the organization. As shown in Patent Document 1, even if a topic selection is accepted from a user, the information obtained may not necessarily be of interest to the user, or even to the organization to which the user belongs.

[0005] The information processing method and the like disclosed herein aim to provide information that is of interest to an organization or an individual.

[0006] An information processing method according to one aspect of the present disclosure includes an internal information acquisition step of acquiring information expressed by a person as internal text information, a general information acquisition step of acquiring general text information contained in disclosed general information, an internal topic acquisition step of acquiring one or more internal topics related to the internal text information by analyzing the internal text information, a matching determination step of determining a match between the internal topic and the general text information, and an output step of outputting the general information including the general text information matched in the matching determination step.

[0007] An information processing system according to one aspect of the present disclosure includes an internal information acquisition unit that acquires information expressed by a person as internal text information, a general information acquisition unit that acquires general text information contained in disclosed general information, an internal topic acquisition unit that analyzes the internal text information to acquire one or more internal topics related to the internal text information, a matching determination unit that determines a match between the internal topic and the general text information, and an information output unit that outputs the general information including the general text information matched by the matching determination unit.

[0008] A program according to one aspect of the present disclosure is a program for causing a computer to execute the above-described information processing method.

[0009] According to an information processing method and the like according to one aspect of the present disclosure, it is possible to provide information that is of interest to an organization or an individual.

[0010] FIG. 1 is a schematic diagram showing an information processing system according to a first embodiment. FIG. 2 is a diagram showing the block configuration of the information processing system according to the first embodiment and an information processing device included in the information processing system. FIG. 3 is a diagram showing an overview of processing executed in the information processing system. FIG. 4 is a diagram showing internal text information obtained from information expressed by a person and internal topics extracted from the internal text information. FIG. 5 is a diagram showing an example of topic model analysis used when analyzing text information. FIG. 6 is a diagram showing an example of a matching determination between internal topics and general text information. FIG. 7 is a diagram showing another example of topic model analysis. FIG. 8 is a diagram showing an example of extracting internal topics according to an organizational hierarchy. FIG. 9 is a diagram showing an example of extracting internal topics based on sentiment analysis. FIG. 10 is a flowchart showing an information processing method according to the first embodiment. FIG. 11 is a diagram showing the block configuration of an information processing system according to a second embodiment and an information processing device included in the information processing system. FIG. 12 is a diagram showing an overview of processing executed in the information processing system. FIG. 13 is a diagram showing general text information included in general information and general topics extracted from the general text information. FIG. 14 is a diagram showing an example of a matching determination between internal topics and general topics. Fig. 15 is a diagram showing another example of topic model analysis. Fig. 16 is a diagram showing an example of extracting general topics according to organizational hierarchy. Fig. 17 is a diagram showing an example of extracting general topics based on sentiment analysis. Fig. 18 is a flowchart showing an information processing method according to embodiment 2.

[0011] The information processing method etc. disclosed herein includes the following information processing etc. in order to provide information of interest to an organization or an individual.

[0012] The information processing method of Example 1 is an information processing method including an internal information acquisition step of acquiring information expressed by a person as internal text information, a general information acquisition step of acquiring general text information included in disclosed general information, an internal topic acquisition step of acquiring one or more internal topics related to the internal text information by analyzing the internal text information, a matching determination step of determining a match between the internal topic and the general text information, and an output step of outputting the general information including the general text information matched in the matching determination step.

[0013] In this way, by acquiring an internal topic based on internal text information and determining whether the internal topic matches general text information, it is possible to output general information that matches the internal topic. This information processing method makes it possible to provide information that is of interest to organizations or individuals.

[0014] The information processing method of Example 2 is the information processing method of Example 1, and may further include a general topic acquisition step of acquiring one or more general topics related to the general text information by analyzing the general text information, wherein the matching determination step determines a match between the internal topic and the general topic related to the general text information, and the output step outputs the general information related to the general topic matched in the matching determination step.

[0015] In this way, by further acquiring general topics based on general text information and determining whether the internal topics match the general topics, it is possible to output general information that matches the internal topics and the general topics, thereby providing information that is of interest to organizations or individuals.

[0016] The information processing method of Example 3 is the information processing method of Example 1, wherein in the matching determination step, a similarity between the internal topic and the general text information is calculated, and the matching is determined based on the similarity.

[0017] In this way, by determining whether a match is made based on the similarity between the internal topic and general text information, the accuracy of the match determination can be improved, thereby providing information that is of interest to organizations or individuals.

[0018] An information processing method of Example 4 is the information processing method according to Example 2, wherein in the matching determination step, the matching may be determined by calculating a similarity between the internal topic and the general topic.

[0019] In this way, by determining matching based on the similarity between the internal topic and the general topic, the accuracy of the matching determination can be improved, thereby providing information that is of interest to organizations or individuals.

[0020] The information processing method of Example 5 is the information processing method of any one of Examples 1 to 4, wherein the internal text information may be information obtained from information expressed by the person in at least one of a meeting, a chat, and an email transmission.

[0021] This allows a match to be determined based on at least one of information from online meetings, face-to-face meetings, hybrid meetings, online chats, and email transmissions. This allows information of interest to organizations or individuals to be provided. Note that, for example, when organization A is the target, "meetings held within an organization" is not limited to meetings within organization A, but also includes information posted by members of organization A in meetings between organization A and organization B (an organization outside organization A). The same applies to chats and email transmissions.

[0022] The information processing method of Example 6 is the information processing method according to any one of Examples 1 to 5, wherein the general text information may be information obtained from at least one of news, papers, and patent publications.

[0023] This allows for the acquisition of a wide range of general text information with a high level of specialization. This allows for the output of a wide range of general information with a high level of specialization. This allows for the provision of information of interest to organizations or individuals.

[0024] The information processing method of Example 7 is the information processing method according to any one of Examples 1 to 6, and in the internal topic acquisition step, the internal topic may be acquired by analyzing the latent meaning of the internal text information using topic model analysis.

[0025] In this way, by analyzing the latent meaning of internal text information using topic model analysis of statistical latent semantic analysis, it is possible to obtain internal topics that match the content of the internal text information, and to make matching decisions based on these internal topics, thereby providing information that is of interest to organizations or individuals.

[0026] The information processing method of Example 8 is the information processing method described in any one of Examples 1 to 6, and in the internal topic acquisition step, the internal text information may be analyzed by determining the number of times a word appears in the internal text information, and the word that appears most frequently may be acquired as the internal topic.

[0027] In this way, by analyzing the internal text information by determining the frequency of occurrence of words in the internal text information, it is possible to obtain internal topics according to the frequency of occurrence of words, and to determine matching based on the internal topics, thereby providing information that is of interest to organizations or individuals.

[0028] The information processing method of Example 9 is the information processing method of Example 2, wherein in the general topic acquisition step, the latent meaning of the general text information may be analyzed using a topic model analysis to acquire the general topic.

[0029] In this way, by analyzing the latent meaning of general text information using topic model analysis of statistical latent semantic analysis, it is possible to obtain general topics that match the content of the general text information, and to make matching decisions based on these general topics, thereby providing information that is of interest to organizations or individuals.

[0030] The information processing method of Example 10 is the information processing method described in Example 2, and in the general topic acquisition step, the general text information may be analyzed by determining the number of times that words appear in the general text information, and the words that appear most frequently may be acquired as the general topics.

[0031] In this way, by analyzing general text information by determining the frequency of occurrence of words in the general text information, it is possible to obtain general topics according to the frequency of occurrence of words, and to determine matching based on the general topics, thereby providing information of interest to organizations or individuals.

[0032] An information processing method of Example 11 is the information processing method described in Example 3, wherein the internal topic includes information regarding the affiliation probability of the internal topic in the internal text information, and in the matching determination step, the matching may be determined based on the similarity and the affiliation probability of the internal topic.

[0033] In this way, by determining whether a match exists based on the similarity and the probability of belonging to the internal topic, the accuracy of the match determination can be improved, thereby providing information that is of interest to organizations or individuals.

[0034] An information processing method of Example 12 is the information processing method of Example 4, wherein the general topic includes information regarding the probability of the general topic belonging to the general text information, and in the matching determination step, the matching may be determined based on the similarity and the probability of the general topic belonging to the general text information.

[0035] In this way, by determining whether a match exists based on the similarity and the probability of belonging to a general topic, the accuracy of the match determination can be improved, thereby providing information that is of interest to organizations or individuals.

[0036] The information processing method of Example 13 is the information processing method according to any one of Examples 1 to 12, and in the internal topic acquisition step, the internal topic may be acquired by performing sentiment analysis on the internal text information.

[0037] In this way, by performing sentiment analysis on internal text information, it is possible to obtain internal topics that match the user's sentiment, thereby providing information that is of interest to organizations or individuals.

[0038] An information processing method of Example 14 is the information processing method of Example 2, wherein in the general topic acquisition step, the general topic may be acquired by performing sentiment analysis on the general text information.

[0039] In this way, by performing sentiment analysis on general text information, it is possible to obtain general topics that match the user's sentiment, thereby providing information that is of interest to organizations or individuals.

[0040] An information processing method of Example 15 is the information processing method according to Examples 1 to 14, wherein each of the internal text information and the general text information may include text information incidental to video data.

[0041] This allows topics to be extracted based on text information attached to video data, and matches to be determined based on the extracted topics, thereby providing information of interest to organizations or individuals.

[0042] The information processing system of Example 16 includes an internal information acquisition unit that acquires information expressed by a person as internal text information, a general information acquisition unit that acquires general text information included in disclosed general information, an internal topic acquisition unit that analyzes the internal text information to acquire one or more internal topics related to the internal text information, a matching determination unit that determines a match between the internal topic and the general text information, and an information output unit that outputs the general information including the general text information matched by the matching determination unit.

[0043] In this way, by acquiring an internal topic based on internal text information and determining whether the internal topic matches general text information, it is possible to output general information that matches the internal topic. This information processing system can provide information that is of interest to organizations or individuals.

[0044] The information processing system of Example 17 is the information processing system described in Example 16, further comprising a general topic acquisition unit that acquires one or more general topics related to the general text information by analyzing the general text information, the matching determination unit determines a match between the internal topic and the general topic related to the general text information, and the information output unit may output the general information related to the general topic matched by the matching determination unit.

[0045] In this way, by further acquiring general topics based on general text information and determining whether the internal topics match the general topics, it is possible to output general information that matches the internal topics and the general topics, thereby providing information that is of interest to organizations or individuals.

[0046] The program of Example 18 is a program for causing a computer to execute the information processing method according to any one of Examples 1 to 15.

[0047] This makes it possible to cause a computer to execute the above information processing method in accordance with the program.

[0048] These comprehensive or specific aspects may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM, or may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium.

[0049] Hereinafter, embodiments will be described with reference to the drawings. Note that the embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, the arrangement and connection of the components, steps, the order of steps, and the like shown in the following embodiments are merely examples and are not intended to limit the scope of the claims.

[0050] First Embodiment [Configuration of Information Processing System] The configuration of an information processing system according to a first embodiment will be described with reference to FIGS. 1 to 9. FIG.

[0051] Fig. 1 is a schematic diagram showing an information processing system 1 according to embodiment 1. Fig. 2 is a diagram showing a block configuration of the information processing system 1 and an information processing device 10 included in the information processing system 1.

[0052] 1 and 2, the information processing system 1 includes an information processing device 10 and a database 50. The information processing device 10 and the database 50 are connected to each other via a communication network.

[0053] The information processing device 10 is a device that provides information that is of interest to an organization or an individual.

[0054] An organization is a group of two or more people. While corporate organizations and group organizations are typical examples of modern organizations, they are not limited to these. Furthermore, consortiums and communities that span multiple corporate organizations, public institutions, and group organizations, as well as DAOs (Decentralized Autonomous Organizations), are also included in the term "organization" here.

[0055] The information processing device 10 is, for example, a computer device, and performs input / output and calculation processing of various types of information. The information processing device 10 accesses the database 50 and acquires necessary information.

[0056] The database 50 is, for example, a computer device that inputs, outputs, edits, and stores various types of information. The database 50 also includes an external storage device such as a NAS (Network Attached Storage).

[0057] The database 50 includes a first database 51 and a second database 52. The first database 51 and the second database 52 are provided in a facility managed by an organization such as a company, for example.

[0058] The first database 51 stores information expressed by people within the organization. The information expressed by people within the organization is stored, for example, as a text file, an audio file, or an image file. The audio file and the image file may be stored in a state converted into a text file. The text file may include text information accompanying video data. Hereinafter, the text information related to the information expressed by people within the organization will be referred to as internal text information it.

[0059] The second database 52 is, for example, an internal organization database. The second database 52 stores information about new initiatives such as research and development themes, and information about the internal organizational hierarchy. The information about the organizational hierarchy is stored in a hierarchical structure, such as a research and development center, a research and development department, and a development section, in which multiple smaller organizations are linked to a larger organization. The second database 52 may also store contact information, such as email addresses, of people (employees) who belong to the organization.

[0060] The database 50 also includes a third database and a fourth database 54 .

[0061] The third database 53 is provided, for example, in a facility managed by an organization such as a company. The third database 53 stores information related to in-house papers and technical reports that are disclosed only within the organization such as a company. The information stored in the third database 53 is general information that is disclosed within the organization.

[0062] The fourth database 54 is provided, for example, on an external server on the Internet. The fourth database 54 stores information related to news, patent documents, and papers. The information stored in the fourth database 54 is general information that is disclosed outside the organization. Hereinafter, the information stored in the third database 53 and the fourth database 54 and that is disclosed inside and outside the organization, i.e., in people's surroundings, will be referred to as general information IG. The general information IG is information that can be accessed by general employees within the organization using the internal communication network and the external communication network. The general information IG includes not only text information but also audio information and video information.

[0063] FIG. 3 is a diagram showing an outline of the processing executed by the information processing system 1. As shown in FIG.

[0064] Fig. 3A shows internal text information it, which is information expressed by people during a web conference. Fig. 3B shows multiple internal topics tp extracted based on the internal text information it. Fig. 3C shows multiple pieces of general text information ig obtained from general information IG stored in the third database 53 and the fourth database 54. Fig. 3D shows an example of a match determination between the internal topic tp and the general text information ig.

[0065] 3, the information processing system 1 extracts internal topics tp based on internal text information it, determines whether the internal topics tp match with general text information ig, and provides general information IG including the matching general text information ig to the user. This information processing system 1 can provide information of interest to organizations or individuals.

[0066] 2, information processing device 10 includes internal information acquisition unit 11, internal topic acquisition unit 12, general information acquisition unit 13, matching determination unit 15, and information output unit 16. Internal information acquisition unit 11, internal topic acquisition unit 12, general information acquisition unit 13, matching determination unit 15, and information output unit 16 are processing units realized by programs and processors that execute the programs.

[0067] The internal information acquisition unit 11 is a processing circuit that acquires internal text information it. The internal information acquisition unit 11 acquires information expressed by a person within the organization to which the person belongs as the internal text information it.

[0068] Information expressed by a person is information that is given out by a person when multiple people communicate with each other, and includes information that a person utters and information that a person writes down.

[0069] The internal text information it is information obtained by information expressed by people in at least one of meetings, chats, and email transmissions held within the organization. This information expressed by people is stored as necessary in the first database 51 as in-house intellectual property information.

[0070] The internal information acquisition unit 11 acquires information expressed by people as internal text information it from the first database 51. The internal text information it acquired by the internal information acquisition unit 11 is output to the internal topic acquisition unit 12.

[0071] The internal topic acquisition unit 12 is a processing circuit that acquires internal topics tp. The internal topic acquisition unit 12 analyzes the internal text information it to acquire multiple internal topics tp related to the internal text information it. A topic is a category of latent meaning, and is called a "latent topic" or simply a "topic." It is a term that concisely and comprehensively represents the semantic content indicated by multiple words. A topic may be a word present in the text information, or may be a term formed by compounding and processing words present in the text information.

[0072] FIG. 4 shows internal text information it obtained from information expressed by a person and internal topics tp extracted from the internal text information it.

[0073] In the example shown in Figure 4, matters related to a research and development theme are discussed in a meeting, and the information expressed by people during the meeting is shown as internal text information it. The information expressed by people during the meeting also includes information about chats and emails sent during the meeting.

[0074] In the example shown in the figure, from the internal text information it discussed in the meeting, "hydrogen" is extracted as the first internal topic tp1, "electric vehicles" is extracted as the second internal topic tp2, "new business development" is extracted as the third internal topic tp3, "rechargeable batteries" is extracted as the fourth internal topic tp4, and "sustainability" is extracted as the fifth internal topic tp5. In this example, multiple internal topics tp are arranged from top to bottom in order of highest topic affiliation probability.

[0075] The topic affiliation probability is the probability that a term corresponding to the topic is included in the text information. Although five topics are shown in the figure, the number of topics extracted from the text information is not limited to five, and may be, for example, between one and twenty.

[0076] The internal topic acquisition unit 12 analyzes the internal text information it using topic model analysis, which is an example of latent semantic analysis, to extract multiple internal topics tp from the internal text information it. Topic model analysis is a natural language processing method that categorizes multiple pieces of text information based on the content contained in each piece of text information, interprets the meanings of words present in the text information by applying them to the classified categories, and extracts topics of the text information. For example, the term "hydrogen" contained in the internal text information it in Figure 4 is not hydrogen used in the category "cosmetics," but is interpreted as a term used in the category "automobiles" from the context of the internal text information it, and is extracted as a topic.

[0077] FIG. 5 is a diagram showing an example of topic model analysis used when analyzing internal text information it.

[0078] As shown in Figure 5A, an internal topic tp is represented by a combination of multiple words. For example, the figure shows that the probability of word w1 belonging to internal topic tp1 is 45%, the probability of word w2 belonging to internal topic tp1 is 10%, and the probability of word w3 belonging to internal topic tp1 is 0%.

[0079] As shown in Figure 5(b), a document that is internal text information it contains multiple internal topics. For example, the figure shows that the probability of internal topic tp1 in document d1 is 5%, the probability of internal topic tp2 is 0%, and the probability of internal topic tp3 is 20%.

[0080] By performing topic model analysis, multiple words that have the same meaning can be grouped together as a single topic, making it possible to understand the underlying meaning of a document.

[0081] The internal topic acquisition unit 12 may acquire the internal topic t by excluding topics that may not be related to research and development from among the multiple internal topics tp related to the internal text information it. Topics that may not be related to research and development include, for example, proper nouns such as people's names and place names, and entertainment that is not related to work.

[0082] The information about the internal topics tp1 to tp5 acquired by the internal topic acquisition unit 12 is output to the matching determination unit 15.

[0083] The general information acquisition unit 13 is a processing circuit that acquires general text information ig from the general information IG. The general information acquisition unit 13 acquires information related to in-house papers and technical reports from the third database 53, and acquires information related to news, patent documents, and papers from the fourth database 54. When the information acquired by the general information acquisition unit 13 is a video, the title of the video and text tags associated with the video become the general text information ig. The general text information ig acquired by the general information acquisition unit 13 is output to the matching determination unit 15.

[0084] The matching determination unit 15 is a processing circuit that determines whether the internal topic tp matches the general text information ig. The matching determination unit 15 determines whether the internal topic tp matches the general text information ig by calculating the similarity between each of the internal topics tp1 to tp5 and the general text information ig.

[0085] The similarity between the internal topic tp and the general text information ig is calculated using a cosine (cos) similarity method. Cosine similarity is a numerical representation of how closely two vectors point in the same direction. Specifically, cosine similarity is the angle between two vectors expressed as a cosine value, and is obtained by calculating the inner product of the two vectors as the numerator and the magnitude of the two vectors as the denominator. For example, a cosine similarity of 0 indicates low similarity, and a cosine similarity of 1 indicates high similarity.

[0086] Before calculating the similarity, the matching determination unit 15 performs language conversion using Word2vec (word to vector). Word2vec is a natural language processing method that converts words in a sentence into numerical vectors to understand their meaning. The words handled by this matching determination unit 15 are the word "internal topic tp" and words in the general text information ig. Performing the conversion using Word2vec makes it possible to perform an operation between two words, the word "internal topic tp" and the word in the general text information ig, specifically, to calculate the similarity.

[0087] FIG. 6 is a diagram showing an example of a matching determination between an internal topic tp and general text information ig.

[0088] The matching determination unit 15 derives similarities s1, s2, s3, s4, and s5 between multiple internal topics tp1, tp2, tp3, tp4, and tp5 and general text information ig1, respectively, and calculates the total similarity s between the multiple internal topics tp1 to tp5 and the general text information ig1 by summing these similarities s1 to s5. Note that when calculating the similarity s1 between one internal topic tp1 and one piece of general text information ig1, the matching determination unit 15 derives the similarity between the internal topic tp1 and multiple words w1, w2, and w3 included in the general text information ig1, and calculates the similarity s1 between the internal topic tp1 and one piece of general text information ig1 by summing these similarities. The matching determination unit 15 similarly calculates similarities s2 to s5 for the other internal topics tp2 to tp5.

[0089] The matching determination unit 15 determines whether or not there is a match based on the calculated total similarity s. The matching determination unit 15 determines that the higher the value of the total similarity s, the higher the matching degree MA. The matching determination unit 15 similarly calculates similarities for the other general text information ig2 and ig3, and determines whether or not there is a match.

[0090] Although the above example shows the case where the internal topic tp is used as is, the present invention is not limited to this. The matching determination unit 15 may determine the degree of similarity by using the probability of the internal topic tp belonging to the internal text information it, and determine whether or not the internal topic tp is a matching topic.

[0091] FIG. 6 shows an example in which the belonging probability of the internal topic tp1 in the internal text information it is 0.9%, the belonging probability of the internal topic tp2 is 0.8%, the belonging probability of the internal topic tp3 is 0.8%, the belonging probability of the internal topic tp4 is 0.7%, and the belonging probability of the internal topic tp5 is 0.6%.

[0092] For example, the matching determination unit 15 may calculate the similarity between multiple internal topics tp1 to tp5 and the general text information ig1 by multiplying the affiliation probability of each internal topic tp1 to tp5 in correspondence with the similarity between each internal topic tp1 to tp5 and the general text information ig1. In the case shown in FIG. 6, the similarity s can be calculated using the formula s = s1 x 0.9 + s2 x 0.8 + s3 x 0.8 + s4 x 0.7 + s5 x 0.6. The higher the affiliation probability of the internal topic tp, the more important the internal topic tp is in the internal text information it, and therefore the higher the affiliation probability, the higher the matching degree MA. The results determined by the matching determination unit 15 are output to the information output unit 16.

[0093] The information output unit 16 is a circuit that outputs the general information IG. The information output unit 16 outputs the general information IG including the general text information ig1 that has been matched as determined by the matching determination unit 15. The information output unit 16 outputs the general information IG having a high matching degree MA between the internal topic tp and the general text information ig, and does not output the general information IG having a low matching degree MA.

[0094] The information output unit 16 outputs the general information IG to, for example, a computer or mobile terminal used by the user. The general information IG can be provided by, for example, distributing information to pre-registered users using application software. The information output unit 16 may automatically distribute general information IG with a high matching degree MA to conference attendees. The output general information IG may be the title and URL of the general information IG, or may be only the general text information ig. A highlight may be drawn on the portion of the general text information ig that matches the internal topic tp.

[0095] The information processing system 1 of this embodiment includes an internal information acquisition unit 11 that acquires information expressed by a person as internal text information it, a general information acquisition unit 13 that acquires general text information ig included in disclosed general information, an internal topic acquisition unit 12 that acquires one or more internal topics tp related to the internal text information it by analyzing the internal text information it, a matching determination unit 15 that determines a match between the internal topic tp and the general text information ig, and an information output unit 16 that outputs general information IG including the general text information ig matched by the matching determination unit 15.

[0096] In this way, by acquiring an internal topic tp based on internal text information it and determining whether the internal topic tp matches general text information ig, it is possible to output general information IG that matches the internal topic tp. This information processing system 1 can provide information that is of interest to organizations or individuals.

[0097] Although the above example shows that the internal topic tp is a term formed based on a plurality of words, the present invention is not limited to this.

[0098] FIG. 7 is a diagram showing another example of topic model analysis.

[0099] 7 shows that the number of times that internal topic tp1 (=word w1) appears in document d1 is 5, the number of times that internal topic tp2 (=word w2) appears is 0, and the number of times that internal topic tp3 (=word w3) appears is 20. The internal topic acquisition unit 12 may simply analyze the internal text information it by finding the number of times that words appear in the internal text information it, and acquire one word that appears frequently as the internal topic.

[0100] Furthermore, the internal topic acquisition unit 12 may extract the internal topic tp according to the organization to which the user belongs.

[0101] FIG. 8 is a diagram showing an example of extracting internal topics tp according to the hierarchy of an organization.

[0102] As shown in (a) of FIG. 8, the internal topic acquisition unit 12 may extract an internal topic tp according to an organization called First Development Department to which the user belongs. As shown in (b) of FIG. 8, the internal topic acquisition unit 12 may extract an internal topic tp according to an organization called First Business Department, which is a higher level than First Development Department. In this case, since First Development Department is located in a level below First Business Department, a specialized internal topic tp is extracted in (a), and a more general internal topic tp than (a) is extracted in (b). Note that information about the organization to which the user belongs is acquired from the second database 52. In this way, the internal topic acquisition unit 12 may extract an internal topic tp according to the level of the organization to which the user belongs. Alternatively, the internal topic acquisition unit 12 may extract an internal topic tp based on the level of the organization selected by the user.

[0103] Furthermore, the internal topic acquisition unit 12 may extract an internal topic based on emotion information requested by a user.

[0104] FIG. 9 is a diagram showing an example of extracting an internal topic tp based on sentiment analysis.

[0105] Emotion information is information about human emotions categorized as "joy, anger, sadness, happiness, etc." The emotion requested by the user may be the user's current emotion or the emotion the user desires in the future.

[0106] For example, if the information processing device 10 has an input unit that accepts user emotion information, the internal topic acquisition unit 12 performs emotion analysis on the internal text information it based on the emotion information accepted by the input unit, and extracts internal topics. The matching determination unit 15 determines whether the extracted internal topics match the general text information ig, and the information output unit 16 outputs general information IG including the matching general text information ig. The output general information IG includes information that matches the user's emotion.

[0107] The internal topic acquisition unit 12 may extract internal topics tp based on not only "joy, anger, sorrow, and pleasure" but also ten types of emotions: "joy, anger, excitement, sadness, like, fear, relief, disgust, surprise, and shame." The internal topic acquisition unit 12 may extract internal topics based on Russell's emotional circle model. The internal topic acquisition unit 12 may extract internal topics based on frequently occurring expressions related to seven emotions in the Japanese IWC Dictionary of Emotion Expressions (JIWC-Dictionary): "sadness, anxiety, anger, disgust, trust, surprise, and joy."

[0108] The internal topic acquisition unit 12 may also determine whether the words included in the internal text information it are based on positive information or negative information, and acquire a topic based on the determination. Whether the words included in the internal text information it are based on positive information or negative information may be determined by sentiment analysis using feature transformation of character data, using a model of a transformer-based machine learning method for pre-learning of natural language processing, such as BERT (Bidirectional Encoder Representations from Transformers).

[0109] For example, if the internal text information IT contains negative information such as "new business development is pointless," using the word "new business development" to count the number of occurrences or calculate the probability of belonging to the internal topic will result in data analysis with an intention different from that intended by the context. Therefore, if the internal topic acquisition unit 12 determines that the information contained in the internal text information IT is based on negative information, it is desirable that the internal topic acquisition unit 12 not analyze the internal text information IT based on the negative information.

[0110] [Information Processing Method] The information processing method according to the first embodiment will be described with reference to FIG.

[0111] 10 is a flowchart showing an information processing method according to embodiment 1. This information processing method is a method for providing information that is of interest to an organization or an individual.

[0112] First, the information processing device 10 acquires information expressed by people within an organization as internal text information it (step S10). For example, the information processing device 10 accesses the first database 51 to acquire the internal text information it.

[0113] Internal text information IT is information emitted by a person when multiple people communicate with each other. For example, internal text information IT is information obtained by information expressed by a person in at least one of a meeting, a chat, and an email transmission held within an organization.

[0114] Next, the information processing device 10 analyzes the internal text information it to acquire one or more internal topics tp related to the internal text information it (step S20). For example, the information processing device 10 analyzes the latent meaning of the internal text information it using topic model analysis to acquire the internal topics tp.

[0115] The information processing device 10 may analyze the internal text information it by calculating the number of times each word appears in the internal text information it, and acquire the words that appear frequently as topics. The information processing device 10 may also acquire the internal topics tp by performing sentiment analysis on the internal text information it.

[0116] Meanwhile, the information processing device 10 acquires general text information ig included in general information IG disclosed inside and outside the organization (step S30). For example, the information processing device 10 acquires the general text information ig by accessing the third database 53 and the fourth database 54.

[0117] The general text information ig is information obtained from at least one of news, papers, and patent publications. The general text information ig may also be information about in-house papers and technical reports. Step S30 may be performed before step S10 or S20.

[0118] Next, the information processing device 10 determines whether the internal topic tp matches the general text information ig (step S40). For example, the information processing device 10 derives similarities s1, s2, s3, s4, and s5 between the internal topics tp1 to tp5 and the general text information ig1, respectively, calculates a total similarity s between the internal topic tp1 and the general text information ig1 based on the respective similarities s1 to s5, and determines the matching degree MA based on the total similarity s. The information processing device 10 similarly determines the matching degrees MA for the other general text information ig2 and ig3.

[0119] Although the above example shows the case where the internal topic tp is used as is, this is not limiting. For example, the information processing device 10 may calculate the similarity between the internal topic tp and the general text information ig by multiplying the similarity between the internal topic tp and the general text information ig by the belonging probability of the internal topic tp. The information processing device 10 may also calculate the similarity for other general text information ig2 and ig3 in a similar manner.

[0120] Next, the information processing device 10 outputs general information IG including the general text information ig1 matched in step S40 (step S50). The information output unit 16 outputs the general information IG to, for example, a computer or a mobile terminal used by the user.

[0121] In this way, by acquiring an internal topic tp based on internal text information it and determining whether the internal topic tp matches general text information ig, it is possible to output general information IG that matches the internal topic tp. This information processing method makes it possible to provide information that is of interest to organizations or individuals.

[0122] (Embodiment 2) [Configuration of Information Processing System] The configuration of an information processing system according to embodiment 2 will be described with reference to Fig. 11 to Fig. 17. In embodiment 2, an example will be described in which general topics tg are extracted from general text information ig and matching determination is performed using these general topics tg.

[0123] FIG. 11 is a diagram showing a block configuration of an information processing system 1A and an information processing device 10A included in the information processing system 1A.

[0124] As shown in FIG. 11, the information processing system 1A includes an information processing device 10A and a database 50.

[0125] The information processing device 10A and the database 50 are connected to each other via a communication network. The configuration of the database 50 is the same as that in the first embodiment.

[0126] FIG. 12 is a diagram showing an outline of the processing executed in the information processing system 1A.

[0127] Fig. 12(a) shows internal text information it, which is information expressed by people during a web conference. Fig. 12(b) shows multiple internal topics tp extracted based on the internal text information it. Fig. 12(c) shows multiple general text information ig obtained from general information IG stored in the third database 53 and the fourth database 54. Fig. 12(d) shows multiple general topics tg extracted based on the general text information ig. Fig. 12(e) shows an example of a matching determination between the internal topic tp and the general topic tg.

[0128] As shown in FIG. 12, the information processing system 1A extracts internal topics tp based on internal text information it, extracts general topics tg based on general text information ig, determines whether the internal topics tp and the general topics tg match, and provides the user with general information IG related to the matched general topics tg and the general text information ig.

[0129] 11 , information processing device 10A includes an internal information acquisition unit 11, an internal topic acquisition unit 12, a general information acquisition unit 13, a general topic acquisition unit 14, a matching determination unit 15, and an information output unit 16. The internal information acquisition unit 11 and the internal topic acquisition unit 12 are the same as those in the first embodiment.

[0130] The general information acquisition unit 13 is a processing circuit that acquires general text information ig from the general information IG. The general text information ig acquired by the general information acquisition unit 13 is output to the general topic acquisition unit 14.

[0131] The general topic acquisition unit 14 is a processing circuit that acquires a general topic tg. The general topic acquisition unit 14 analyzes the general text information ig to acquire a plurality of general topics tg related to the general text information ig.

[0132] FIG. 13 is a diagram showing general text information ig1 included in general information IG and general topics tg extracted from the general text information ig1.

[0133] In the example shown in FIG. 13, "CO2 reduction" is extracted as the first general topic tg1 from general text information ig1 included in a paper, "DX" is extracted as the second general topic tg2, and "social impact" is extracted as the third general topic tg3. In this example, the topics are arranged from top to bottom in descending order of topic affiliation probability. Although three topics are shown in the figure, the number of extracted topics may be four or more. The number of topics extracted from the general text information ig may be, for example, between 1 and 20.

[0134] The general topic acquisition unit 14 analyzes the general text information ig using topic model analysis, which is an example of latent semantic analysis, to extract multiple general topics tg from the general text information ig. Note that the general topic acquisition unit 14 may acquire general topics tg by excluding topics that may not be related to research and development from the multiple general topics tg related to the general text information ig.

[0135] The information on the general topics tg1 to tg3 acquired by the general topic acquisition unit 14 is output to the matching determination unit 15.

[0136] The matching determination unit 15 is a processing circuit that determines whether an internal topic tp matches a general topic tg. The matching determination unit 15 determines whether a matching occurs by calculating the similarity between multiple internal topics tp1 to tp5 and multiple general topics tg1 to tg3 in the general text information ig1. The similarity between the internal topic tp and the general topic tg is derived using a cosine (cos) similarity method. Note that the matching determination unit 15 performs language conversion using Word2vec before calculating the similarity.

[0137] FIG. 14 is a diagram showing an example of a matching determination between an internal topic tp and a general topic tg.

[0138] The matching determination unit 15 derives similarities s1, s2, s3, s4, and s5 between multiple internal topics tp1, tp2, tp3, tp4, and tp5 and general text information ig1, respectively, and then sums these similarities s1 to s5 to determine the total similarity s between the multiple internal topics tp1 to tp5 and the general text information ig1. When determining the similarity between one internal topic tp1 and one piece of general text information ig1, the matching determination unit 15 derives the similarity between the internal topic tp1 and multiple general topics tg1, tg2, and tg3 included in the general text information ig1, and sums these similarities to determine the similarity s1 between the internal topic tp1 and the general text information ig1. The matching determination unit 15 similarly determines similarities s2 to s5 for the other internal topics tp2 to tp5.

[0139] The matching determination unit 15 determines whether or not there is a match based on the calculated total similarity s. The matching determination unit 15 determines that the higher the value of the total similarity s, the higher the matching degree MA. The matching determination unit 15 similarly calculates similarities for the other general text information ig2 and ig3, and determines whether or not there is a match.

[0140] Although the above example shows the case where the internal topic tp and the general topic tg are used as they are, the present invention is not limited to this. The matching determination unit 15 may determine the matching degree MA using the probability of the internal topic tp belonging to the internal text information it and the probability of the general topic tg belonging to the general text information ig.

[0141] FIG. 14 shows an example in which the belonging probability of general topic tg1 in general text information ig1 is 8.2%, the belonging probability of general topic tg2 is 5.8%, and the belonging probability of general topic tg3 is 2.9%.

[0142] For example, the matching determination unit 15 may calculate the matching degree MA between the internal topic tp and the general topic tg by multiplying the similarity between multiple internal topics tp and the general topic tg by the affiliation probability of the internal topic tp and the affiliation probability of the general topic tg. The higher the affiliation probability of a topic, the more important the topic is in the text information, and therefore the higher the affiliation probability, the higher the matching degree MA. The results determined by the matching determination unit 15 are output to the information output unit 16.

[0143] The information output unit 16 is a circuit that outputs general information IG. The information output unit 16 outputs general information IG related to the general topic tg and general text information ig that have been matched as determined by the matching determination unit 15. The information output unit 16 outputs general information IG including general text information ig with a high matching degree MA between the internal topic tp and the general topic tg, and does not output general information IG with a low matching degree MA.

[0144] In addition to the components of the information processing system 1 according to the first embodiment, the information processing system 1A of the present embodiment further includes a general topic acquisition unit 14 that analyzes the general text information ig to acquire one or more general topics tg related to the general text information ig. The matching determination unit 15 determines a match between the internal topic tp and a general topic tg related to the general text information ig. The information output unit 16 outputs the general topic tg matched by the matching determination unit 15 and general information IG related to the general text information ig.

[0145] In this way, by acquiring a general topic tg based on general text information ig and determining whether the general topic tg matches the general text information ig, it is possible to output general information IG in which the internal topic tp matches the general topic tg. This information processing system 1A can provide information that is of interest to organizations or individuals.

[0146] Although the above example shows that the internal topic tp is a term formed based on a plurality of words, the present invention is not limited to this.

[0147] FIG. 15 is a diagram showing another example of topic model analysis.

[0148] 15 shows that in document d1a, general topic tg1 (=word w1) appears 5 times, general topic tg2 (=word w2) appears 0 times, and general topic tg3 (=word w3) appears 20 times. The general topic acquisition unit 14 may simply analyze the general text information ig by determining the number of times each word appears in the general text information ig, and acquire one word that appears frequently as the general topic.

[0149] The general topic acquisition unit 14 may also extract general topics tg according to the organization to which the user belongs.

[0150] FIG. 16 is a diagram showing an example of extracting a general topic tg according to an organizational hierarchy.

[0151] As shown in (a) of FIG. 16, the general topic acquisition unit 14 may extract a general topic tg according to an organization called First Development Department to which the user belongs. As shown in (b) of FIG. 16, the general topic acquisition unit 14 may extract a general topic tg according to an organization called First Business Department, which is a higher level than First Development Department. In this case, since First Development Department is located in a level below First Business Department, a specialized general topic tg is extracted in (a), and a more general general topic tg is extracted in (b). Note that information about the organization to which the user belongs is acquired from the second database 52. In this way, the general topic acquisition unit 14 may extract a general topic tg according to the level of the organization to which the user belongs. Alternatively, the general topic acquisition unit 14 may extract a general topic tg based on the level of the organization selected by the user.

[0152] The general topic acquisition unit 14 may also extract general topics based on emotion information requested by the user.

[0153] FIG. 17 is a diagram showing an example of extracting a general topic tg based on sentiment analysis.

[0154] For example, if the information processing device 10A has an input unit that accepts user emotion information, the general topic acquisition unit 14 performs emotion analysis on the general text information ig based on the emotion information accepted by the input unit and extracts general topics. The matching determination unit 15 determines whether the extracted internal topics match the general topics, and the information output unit 16 outputs general information IG related to the matched general topics tg and general text information ig. The output general information IG includes information that matches the user's emotions.

[0155] The general topic acquisition unit 14 may extract general topics tg based on not only "joy, anger, sorrow, and pleasure" but also ten types of emotions: "joy, anger, excitement, sadness, like, fear, relief, disgust, surprise, and shame." The general topic acquisition unit 14 may extract general topics based on Russell's emotional circumplex model. The general topic acquisition unit 14 may extract general topics based on frequently occurring expressions related to the seven emotions "sadness, anxiety, anger, disgust, trust, surprise, and joy" in the Japanese IWC-Dictionary of Emotion Expressions.

[0156] The general topic acquisition unit 14 may also determine whether the words included in the general text information ig are based on positive information or negative information, and acquire topics based on the determination. Whether the words included in the general text information ig are based on positive information or negative information may be determined by sentiment analysis using feature transformation of character data, using a model of a transformer-based machine learning method for pre-learning of natural language processing, such as BERT.

[0157] For example, if the general text information ig contains negative information such as "social impact is meaningless," using the word "social impact" to count the number of occurrences or calculate the probability of belonging to an internal topic will result in data analysis with an intention different from that intended by the context. Therefore, if the general topic acquisition unit 14 determines that the information contained in the general text information ig is based on negative information, it is desirable that the general topic acquisition unit 14 not analyze the general text information ig based on the negative information.

[0158] [Information Processing Method] The information processing method according to the second embodiment will be described with reference to FIG.

[0159] FIG. 18 is a flowchart showing an information processing method according to the second embodiment.

[0160] First, the information processing device 10A acquires information expressed by people within an organization as internal text information it (step S10). Next, the information processing device 10A analyzes the internal text information it to acquire one or more internal topics tp related to the internal text information it (step S20).

[0161] Meanwhile, the information processing device 10A acquires general text information ig included in general information IG disclosed inside and outside the organization (step S30).

[0162] Next, the information processing device 10A analyzes the general text information ig to acquire one or more general topics tg related to the general text information ig (step S35). The information processing device 10A analyzes the general text information ig using topic model analysis, which is an example of latent semantic analysis, to extract multiple general topics tg from the general text information ig.

[0163] The information processing device 10A may analyze the general text information ig by calculating the number of times each word appears in the general text information ig, and acquire the frequently appearing words as topics. The information processing device 10A may acquire the general topics tg by performing sentiment analysis on the general text information ig. Steps S30 and S35 may be executed before step S10 or S20.

[0164] Next, the information processing device 10A determines whether the internal topic tp matches the general topic tg (step S40). For example, the information processing device 10A derives similarities s1a, s1b, and s1c between one internal topic tp1 and multiple general topics tg1 to tg3, respectively, and then calculates the similarity s1 between the internal topic tp1 and one piece of general text information ig1 by summing these similarities s1a to s1c. The information processing device 10A then similarly derives similarities s2, s3, s4, and s5 between the internal topic tp2 to tp5 and the general text information ig1. The information processing device 10A calculates the total similarity s between the internal topic tp1 and one piece of general text information ig1 by summing these similarities s1 to s5, and determines the matching degree MA based on the total similarity s.

[0165] The matching determination unit 15 similarly obtains the similarity for the other general text information ig2 and ig3, and determines the degree of matching.

[0166] Although the above describes an example in which the internal topic tp and the general topic tg are used as they are, this is not limiting. For example, the information processing device 10A may calculate the similarity between the internal topic tp and the general topic tg by multiplying the similarity between the internal topic tp and the general topic tg by the affiliation probability of the internal topic tp and the affiliation probability of the general topic tg, respectively.

[0167] Next, the information processing device 10A outputs general information IG related to the general topic tg and general text information ig matched in step S50 (step S50). The information output unit 16 outputs the general information IG to, for example, a computer or a mobile terminal used by the user.

[0168] In this way, by acquiring an internal topic tp based on the internal text information it, acquiring a general topic tg based on the general text information ig, and determining whether the internal topic tp matches the general topic tg, it is possible to output general information IG in which the internal topic tp matches the general topic tg. This information processing method makes it possible to provide information that is of interest to organizations or individuals.

[0169] (Other Embodiments) Although aspects of the information processing system etc. have been described above according to the embodiments, the aspects of the information processing system etc. are not limited to the embodiments. Modifications conceivable by those skilled in the art may be made to the embodiments, and multiple components in the embodiments may be combined in any manner.

[0170] Although the above example shows a case where a matching determination is made using the affiliation probability of the internal topic tp in the internal text information it, the present invention is not limited to this. For example, the information processing device 10 may set the importance of the internal topic tp based on the job title or role within the organization of the person who disclosed the information, and make a matching determination based on the importance of the internal topic tp.

[0171] Furthermore, for example, a process performed by a specific component in the embodiments may be performed by another component instead of the specific component. The order of multiple processes may be changed, or multiple processes may be performed in parallel. Furthermore, ordinal numbers such as "first" and "second" used in the description may be changed, removed, or newly assigned as appropriate. These ordinal numbers do not necessarily correspond to a meaningful order, and may be used to identify elements.

[0172] The information processing method may be executed by any system or device, i.e., the information processing method may be executed by the information processing system described above or by another system or device.

[0173] For example, a part or all of the information processing method may be executed by a computer including a processor, a memory, an input / output circuit, etc. In this case, the information processing method may be executed by the computer executing a program for causing the computer to execute the information processing method.

[0174] The above program may also be recorded on a non-transitory computer-readable recording medium such as a CD-ROM.

[0175] Furthermore, each component of an information processing system or the like may be configured with dedicated hardware, general-purpose hardware that executes the above-mentioned programs, or a combination of these. The general-purpose hardware may be configured with a memory in which the programs are recorded and a general-purpose processor that reads and executes the programs from the memory. Here, the memory may be a semiconductor memory or a hard disk, and the general-purpose processor may be a CPU or the like.

[0176] Furthermore, the dedicated hardware may be configured with a memory and a dedicated processor, etc. For example, the dedicated processor may refer to the memory and execute the information processing method described above.

[0177] Furthermore, each component of the information processing system may be an electric circuit. These electric circuits may form a single electric circuit as a whole, or may be separate electric circuits. Furthermore, these electric circuits may correspond to dedicated hardware, or may correspond to general-purpose hardware that executes the above-mentioned programs, etc.

[0178] The present disclosure is applicable to an information providing method for providing information that is of interest to an organization or an individual.

[0179] 1, 1A Information processing system 10, 10A Information processing device 11 Internal information acquisition unit 12 Internal topic acquisition unit 13 General information acquisition unit 14 General topic acquisition unit 15 Matching determination unit 16 Information output unit 50, 51, 52, 53, 54 Database it Internal text information ig, ig1, ig2, ig3 General text information IG General information MA Matching degree tp, tp1, tp2, tp3, tp4, tp5 Internal topics tg, tg1, tg2, tg3 General topics s, s1, s2, s3, s4, s5, s1a, s1b, s1c Similarity w1, w2, w3 Word

Claims

1. An information processing method comprising: an internal information acquisition step of acquiring information expressed by a person as internal text information; a general information acquisition step of acquiring general text information contained in disclosed general information; an internal topic acquisition step of acquiring one or more internal topics related to the internal text information by analyzing the internal text information; a matching determination step of determining a match between the internal topic and the general text information; and an output step of outputting the general information including the general text information matched in the matching determination step.

2. The information processing method according to claim 1, further comprising a general topic acquisition step of acquiring one or more general topics related to the general text information by analyzing the general text information, in which a matching determination step determines a matching between the internal topic and the general topic related to the general text information, and in which a matching determination step outputs the general information related to the general topic matched in the matching determination step.

3. The information processing method according to claim 1, wherein in said matching determination step, a similarity between said internal topic and said general text information is calculated, and said matching is determined based on said similarity.

4. The information processing method according to claim 2, wherein in said matching determination step, a similarity between said internal topic and said general topic is calculated, and said matching is determined based on said similarity.

5. The information processing method according to claim 1 or 2, wherein the internal text information is information obtained by information expressed by the person in at least one of a meeting, a chat, and an email transmission.

6. The information processing method according to claim 1 or 2, wherein the general text information is information obtained from at least one of news, papers, and patent publications.

7. The information processing method according to claim 1 or 2, wherein in said internal topic acquisition step, the latent meaning of said internal text information is analyzed using a topic model analysis to acquire said internal topic.

8. The information processing method according to claim 1 or 2, wherein in the internal topic acquisition step, the internal text information is analyzed by determining the number of occurrences of words in the internal text information, and the words that occur frequently are acquired as the internal topics.

9. The information processing method according to claim 2, wherein in said general topic acquisition step, the latent meaning of said general text information is analyzed using a topic model analysis to acquire said general topic.

10. The information processing method according to claim 2, wherein in the general topic acquisition step, the general text information is analyzed by determining the number of occurrences of words in the general text information, and the words that occur frequently are acquired as the general topics.

11. The information processing method according to claim 3, wherein the internal topic includes information regarding the affiliation probability of the internal topic in the internal text information, and in the matching determination step, the matching is determined based on the similarity and the affiliation probability of the internal topic.

12. The information processing method according to claim 4, wherein the general topic includes information regarding the probability of the general topic belonging to the general text information, and in the matching determination step, the matching is determined based on the similarity and the probability of the general topic belonging to the general text information.

13. The information processing method according to claim 1 or 2, wherein in the internal topic acquisition step, the internal topic is acquired by performing sentiment analysis on the internal text information.

14. The information processing method according to claim 2, wherein in the general topic acquisition step, the general topic is acquired by performing sentiment analysis on the general text information.

15. The information processing method according to claim 1 or 2, wherein each of the internal text information and the general text information includes text information accompanying video data.

16. An information processing system comprising: an internal information acquisition unit that acquires information expressed by a person as internal text information; a general information acquisition unit that acquires general text information contained in disclosed general information; an internal topic acquisition unit that acquires one or more internal topics related to the internal text information by analyzing the internal text information; a matching determination unit that determines a match between the internal topic and the general text information; and an information output unit that outputs the general information including the general text information matched by the matching determination unit.

17. The information processing system of claim 16, further comprising a general topic acquisition unit that acquires one or more general topics related to the general text information by analyzing the general text information, wherein the matching determination unit determines a match between the internal topic and the general topic related to the general text information, and the information output unit outputs the general information related to the general topic matched by the matching determination unit.

18. A program for causing a computer to execute the information processing method according to claim 1 or 2.

Citation Information

Patent Citations

  • Method and device for receiving and displaying electronic information

    JP2000250822A

  • Processor

    JP2018185690A

  • User interfaces for refining video group packages

    WO2022060956A1