Information processing device, information processing method and information processing program

Abstract

To grasp how a user is interested in and feels about an occurring event.SOLUTION: An information processing device has: a gathering unit which gathers contributed information that a user contributes based upon a prescribed character string; an estimation unit which estimates an event to occur based upon the contributed information gathered by the gathering unit; a specification unit which specifies an interesting matter that a user is interested in about the event estimated by the estimation unit based upon the contributed information; and a presumption unit which presumes a feeling that the user has about the interesting matter specified by the specification unit based upon the contributed information.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there are known technologies for outputting information about various events such as disasters, weather changes, etc. One example of such a technology is a technology for detecting the occurrence of a disaster and outputting a disaster notification based on regional variations in messages posted on social media. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6528532 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned techniques may not be able to grasp the interest or thoughts of users regarding an event that occurs.

[0005] For example, the conventional technology described above merely detects the occurrence of a disaster and notifies users of information indicating the occurrence of a disaster, and cannot be said to be able to grasp the user's interest or thoughts regarding the occurring event.

[0006] The present application has been made in consideration of the above, and aims to understand what interests and impressions users have regarding events that occur. [Means for solving the problem]

[0007] The information processing device according to the present application is characterized by having a collection unit that collects posted information posted by users based on a predetermined character string, an estimation unit that infers an event that will occur based on the posted information collected by the collection unit, an identification unit that identifies matters of interest in which the user is interested related to the event inferred by the estimation unit based on the posted information, and an estimation unit that infers the user's thoughts on the matters of interest identified by the identification unit based on the posted information. Effect of the Invention

[0008] According to one aspect of the embodiment, it is possible to obtain an effect of understanding what interests and thoughts a user has about an occurring event. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of the posted information database 31. As shown in FIG. [Figure 4] FIG. 4 is a diagram showing an example of the event information database 32. As shown in FIG. [Diagram 5] FIG. 5 is a flowchart illustrating an example of a procedure of information processing according to the embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. As shown in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated explanations will be omitted.

[0011] 1. Embodiment The information processing realized by the information processing device etc. of the present embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the information processing according to the embodiment. Note that in Fig. 1, the information processing etc. according to the embodiment is realized by an information processing device 10 which is an example of the information processing according to the present embodiment.

[0012] As shown in Fig. 1, an information processing system 1 according to an embodiment includes an information processing device 10 and a user terminal 100. The information processing device 10 and the user terminal 100 are connected to each other via a network N (see Fig. 2, for example) so as to be able to communicate with each other by wire or wirelessly. The network N is, for example, a Wide Area Network (WAN) such as the Internet. Note that the information processing system 1 shown in Fig. 1 may include a plurality of information processing devices 10 and a plurality of user terminals 100.

[0013] 1 is an information processing device that performs information processing, and is realized by, for example, a server device, a cloud system, etc. For example, the information processing device 10 provides a user with information on an event indicated by posted information (for example, information including text information, images, etc.) posted by a user to a social networking service (SNS) provided by the information processing device 10 itself or another external device, etc.

[0014] The information processing device 10 or other external devices may have a function as a web server that provides websites related to various services including SNS. The information processing device 10 or other external devices may be devices that deliver information to the user terminal 100 to be displayed on applications related to various services installed in the user terminal 100. The information processing device 10 or other external devices may be servers that deliver the application data itself.

[0015] Furthermore, the information processing device 10 or another external device may function as a distribution device that distributes control information to the user terminal 100. Here, the control information is described in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). Note that an application itself distributed from the information processing device 10 or another external device may be regarded as control information.

[0016] The user terminal 100 shown in Fig. 1 is an information processing device used by a user. The user terminal 100 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. The user terminal 100 displays information distributed by the information processing device 10 or the like using a web browser or an application. Note that the example shown in Fig. 1 shows a case where the user terminal 100 is a smartphone.

[0017] An example of information processing performed by information processing device 10 will be described below with reference to FIG. 1. In the following description, user terminal 100 will be referred to as user terminals 100-1 to 100-N (N is any natural number) according to the user who uses user terminal 100. For example, user terminal 100-1 is a user terminal 100 used by a user (user U1) identified by user ID "UID#1". In the following description, user terminals 100-1 to 100-N will be referred to as user terminal 100 when there is no particular distinction between them. In the following description, user terminal 100 may be regarded as the same as a user. That is, in the following description, user can also be read as user terminal 100.

[0018] In the following description, it is assumed that an application related to SNS (hereinafter, sometimes referred to as an “SNS app”) provided by the information processing device 10 or another external device is installed on the user terminal 100.

[0019] First, the information processing device 10 collects posted information posted by users via an SNS application (step S1). For example, the information processing device 10 detects, as a buzzword, a character string included in posted information that is equal to or greater than a predetermined threshold among posted information posted within a recent predetermined period (e.g., 3 days, 1 week) on the SNS. Then, the information processing device 10 collects posted information including buzzwords and posted information related to buzzwords among posted information posted within the recent predetermined period. As a specific example, the information processing device 10 collects, as posted information related to buzzwords, posted information posted by quoting posted information including buzzwords (e.g., posted information including posted information including buzzwords and a comment on the posted information), posted information that is a reply to posted information including buzzwords, posted information included in a thread (tree) related to posted information including buzzwords, and the like.

[0020] In the example of FIG. 1, it is assumed that the information processing device 10 detects buzzword #1 and collects posted information including buzzword #1 and posted information related to buzzword #1.

[0021] Next, the information processing device 10 estimates the event that has occurred based on the collected posted information (step S2). For example, the information processing device 10 estimates the event that has occurred using the collected posted information and model #1 that has been trained to generate an answer to an input question. Note that model #1 is a model trained to output an answer sentence corresponding to an input question sentence, and is a language model that performs natural language processing such as GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers). Model #1 is in the information processing device 10 and was created independently by the business entity that manages the information processing device 10. Note that it is preferable that the input information is trained so as not to be used as a new answer, thereby concealing the input information such as personal information.

[0022] Here, the information processing device 10 estimates the event that has occurred using the collected posted information and the model #1 in the procedure of steps S21 to S27. First, the information processing device 10 determines whether or not the event that has occurred can be estimated from the collected posted information (step S21). For example, the information processing device 10 inputs the collected posted information and a question indicating whether or not the event that has occurred can be estimated based on the posted information to the model #1, and when information indicating that the event that has occurred can be estimated is output from the model #1, the information processing device 10 determines that the event that has occurred can be estimated (step S21; Yes), and proceeds to the processing of step S22. On the other hand, when information indicating that the event that has occurred cannot be estimated is output from the model #1, the information processing device 10 determines that the event that has occurred cannot be estimated (step S21; No), and the information processing device 10 does not perform the processing of estimating the event that has occurred, and ends the processing.

[0023] In the example of FIG. 1, it is assumed that the information processing device 10 has determined that the event that has occurred can be estimated. In this case, the information processing device 10 estimates the event that has occurred based on the collected posted information (step S22). For example, the information processing device 10 estimates the event that has occurred by inputting the collected posted information and an instruction sentence that instructs the model #1 to output the event indicated by the posted information. Here, in the example of FIG. 1, it is assumed that the information processing device 10 has estimated event #1 as the event that has occurred.

[0024] Next, the information processing device 10 determines whether or not the name of a person related to the event #1 can be estimated from the collected posted information (step S23). For example, the information processing device 10 inputs the collected posted information and a question indicating whether or not the name of a person related to the event #1 can be estimated based on the posted information to the model #1, and when information indicating that the name of a person related to the event #1 can be estimated is output from the model #1, the information processing device 10 determines that the name of a person related to the event #1 can be estimated (step S23; Yes), and proceeds to processing of step S24. On the other hand, when information indicating that the name of a person related to the event #1 cannot be estimated is output from the model #1, the information processing device 10 determines that the name of a person related to the event #1 cannot be estimated (step S23; No), and proceeds to processing of step S25.

[0025] In the example of FIG. 1, it is assumed that the information processing device 10 has determined that it is possible to estimate a person's name related to event #1. In this case, the information processing device 10 estimates a person's name related to event #1 based on the collected posted information (step S24). For example, the information processing device 10 estimates a person's name related to event #1 by inputting the collected posted information and an instruction sentence instructing model #1 to output a person's name related to event #1. Here, in the example of FIG. 1, it is assumed that the information processing device 10 has estimated person's name #1 as a person's name related to event #1.

[0026] Here, the names of people related to event #1 are, for example, names of people affected by event #1 which is a natural disaster (e.g., typhoon, heavy rain, flood, snowfall), names of victims of incidents / man-made disasters, names of people who caused incidents / man-made disasters (perpetrators, etc.), names of organizers of event #1 which is an event, etc. Note that the names inferred by the information processing device 10 are not limited to names of people related to event #1 (in other words, specific individuals), but may also be, for example, a predetermined organization (such as a company name) related to event #1.

[0027] Next, the information processing device 10 determines whether or not the location where the event #1 occurred can be estimated from the collected post information (step S25). For example, the information processing device 10 inputs the collected post information and a question indicating whether or not the location where the event #1 occurred can be estimated based on the post information to the model #1, and when information indicating that the location where the event #1 occurred can be estimated is output from the model #1, the information processing device 10 determines that the location where the event #1 occurred can be estimated (step S25; Yes) and proceeds to processing of step S26. On the other hand, when information indicating that the location where the event #1 occurred cannot be estimated is output from the model #1, the information processing device 10 determines that the location where the event #1 occurred cannot be estimated (step S25; No) and proceeds to processing of step S27.

[0028] In the example of FIG. 1, it is assumed that the information processing device 10 has determined that it is possible to estimate the location where the event #1 occurred. In this case, the information processing device 10 estimates the location where the event #1 occurred based on the collected posted information (step S26). For example, the information processing device 10 estimates the location where the event #1 occurred by inputting the collected posted information and an instruction sentence that instructs the model #1 to output the location where the event #1 occurred to the model #1. Here, in the example of FIG. 1, it is assumed that the information processing device 10 has estimated the location #1 as the location where the event #1 occurred.

[0029] Here, the location where event #1 occurred may refer to, for example, an administrative division such as a "town," "ward," "city," or "prefecture," a facility (for example, a shopping center, concert hall, stadium, park, etc.), a natural object (for example, a river, sea, mountain, etc.), or an artificial object (for example, a bridge, road, levee, dam, tunnel, etc.).

[0030] Next, the information processing device 10 summarizes the results estimated in steps S21 to S26 (step S27). For example, the information processing device 10 generates an estimation result #1 (in other words, a fact about the event #1) summarizing the results estimated in steps S21 to S26 by inputting to the model #1 a rule indicating that the event #1, the person's name #1, and the place #1 are to be included, and an instruction sentence instructing the model #1 to output a summary (for example, a summary) of the results estimated regarding the event #1.

[0031] If it is determined in step S23 that the name of a person related to event #1 cannot be estimated, the information processing device 10 generates an estimation result that does not include the name of a person related to event #1. Also, if it is determined in step S25 that the location where event #1 occurred cannot be estimated, the information processing device 10 generates an estimation result that does not include the location where event #1 occurred.

[0032] Next, after the processing of steps S21 to S27 is completed, the information processing device 10 identifies the user's interest in event #1 based on the collected posted information (step S3). For example, the information processing device 10 inputs the collected posted information and an instruction sentence instructing the model #1 to output the user's interest in event #1, thereby identifying the user's interest in event #1. As a specific example, the information processing device 10 identifies the cause of the occurrence of event #1, the circumstances (background) of the occurrence of event #1, other events caused by event #1, the name of a person related to event #1 (person's name #1, etc.), the place where event #1 occurred, etc. as the interest.

[0033] Next, the information processing device 10 infers the user's thoughts on the interest of event #1 based on the collected posting information (step S4). For example, the information processing device 10 infers the user's thoughts on the interest of event #1 by inputting the collected posting information and an instruction sentence instructing the model #1 to output the user's thoughts on the interest of event #1. As a specific example, the information processing device 10 infers the emotions (e.g., joy, blessing, sadness, anger, disgust, fear, empathy, etc.) felt by the user regarding the interest of event #1.

[0034] Next, the information processing device 10 provides the user with content related to the event #1 that has occurred via the SNS application (step S5). For example, the information processing device 10 provides news articles related to the event #1, hashtags corresponding to the event #1, and the like, and provides information indicating the estimation result #1, matters of interest regarding the event #1, and the user's feelings regarding the matters of interest, in response to an operation of selecting these.

[0035] The information processing device 10 may input to the model #1 the information obtained by the processing of steps S2 to S4 and an instruction sentence instructing the model #1 to output a summary of the obtained information, and provide the output summary as content related to the event #1. In this case, the information processing device 10 may generate content related to the event #1 by further inputting to the model #1 a rule indicating that the information indicated by the estimation result #1 is to be included.

[0036] As described above, the information processing device 10 according to the embodiment estimates an event that has occurred based on information posted by a user, and provides content indicating the user's interests in the event, the user's thoughts on the interests, etc. This allows the information processing device 10 according to the embodiment to grasp the user's interests and thoughts on the event that has occurred.

[0037] Conventionally, in order to grasp information such as facts about a trending event on a SNS (e.g., names of people related to the event, the place where the event occurred, etc.), matters of interest such as the background of the event, and each user's feelings toward the event, it is necessary to check much of the posted information about the event. In contrast, the information processing device 10 according to the embodiment can summarize this information and provide it to the user, so that the user can easily grasp the content of the trending event and people's real feelings and reactions toward the event.

[0038] [2. Other processing examples] The above-described process is merely an example, and the information processing device 10 may perform various processes using various information. In this regard, examples are given below.

[0039] [2-1. About the incident] 1 shows an example in which the information processing device 10 estimates an event that has already occurred, but the event that the information processing device 10 estimates is not limited to this example. For example, the information processing device 10 may estimate an event that is predicted to occur. As a specific example, the information processing device 10 may predict an event such as damage caused by the occurrence of a typhoon or damage caused by heavy rain.

[0040] In the above example, the event estimated by the information processing device 10 is a disaster or an incident, but the event is not limited to such an example and may be any event. For example, the event estimated by the information processing device 10 may be a summer day, a midsummer day, a scorching hot day, a tropical night, a winter day, or a midwinter day. The event may also be the opening of the beach, the opening of a pool, cherry blossoms blooming, autumn leaves, a concert, a stage performance, a sports game, or the like. The event may also indicate something that occurred during an event, a sport, or the like (for example, something that was exciting).

[0041] [2-2. Presumption of facts of events] In the example of FIG. 1, the information processing device 10 may estimate not only the names of people related to the event and the place where the event occurred, but also various facts related to the event. For example, the information processing device 10 may estimate the date and time when the event occurred. As a specific example, the information processing device 10 inputs the collected posted information and a question sentence indicating whether the date and time when the event #1 occurred can be estimated based on the posted information to the model #1, and when information indicating that the date and time when the event #1 occurred can be estimated is output from the model #1, the information processing device 10 inputs the collected posted information and an instruction sentence instructing the model #1 to output the date and time when the event #1 occurred to estimate the date and time when the event #1 occurred.

[0042] [2-3. Collection of posted information] 1, the information processing device 10 may collect post information based on character strings included in content distributed in an SNS application, various other services, etc. For example, the information processing device 10 collects post information based on character strings included in content such as news articles, disaster information, etc. (for example, character strings included in titles, character strings indicating tags attached to content, etc.).

[0043] Furthermore, the information processing device 10 may collect posted information to which a tag (hashtag) indicating a predetermined character string set by a user, an administrator of an SNS application, an administrator of the information processing device 10, or the like is attached. For example, the information processing device 10 collects posted information to which a tag indicating a program name of a television program or an event name is attached, and estimates an event that will occur. In this way, the information processing device 10 can grasp, for example, what kind of event occurred and what was exciting from the perspective of the user (viewer) in a television program or an event such as a live performance.

[0044] [2-4. Estimation of events related to a specified event] In the example of Fig. 1, the information processing device 10 may collect posted information based on character strings included in posted information posted within a predetermined period from the time when a predetermined event occurs, and infer a related event related to the predetermined event based on the collected posted information. As a specific example, when a sudden drop in stock prices occurs for a company, the information processing device 10 collects posted information based on character strings (e.g., character strings related to the company whose stock prices have suddenly dropped) included in posted information posted within three days before and after the time when the stock price suddenly dropped, and infers a related event that caused the stock price suddenly dropped based on the collected posted information. Then, the information processing device 10 identifies matters of interest that the user is interested in regarding the related event based on the collected posted information, infers the user's thoughts on the matters of interest, and provides the user with content related to the related event.

[0045] [2-5. Collection of posted information based on character strings] In the example of FIG. 1, the information processing device 10 collects posted information including buzzword #1 and posted information related to buzzword #1. However, the information processing device 10 may collect posted information based on a combination of multiple character strings. For example, the information processing device 10 collects posted information using buzzword #2 detected in addition to buzzword #1. As a specific example, the information processing device 10 collects posted information including any of buzzwords #1 and #2 and posted information related to any of buzzwords #1 and #2. In addition, the information processing device 10 collects posted information including buzzwords #1 and #2 and posted information related to buzzwords #1 and #2 (for example, posted information posted by quoting posted information including buzzwords #1 and #2, posted information that is a reply to posted information including buzzwords #1 and #2, posted information included in a thread related to posted information including buzzwords #1 and #2).

[0046] The information processing device 10 may collect posted information based on a combination of three or more character strings.

[0047] The information processing device 10 may also identify a character string or a combination of character strings that can estimate the event that has occurred, and perform the processes of steps S2 to S4 using the posted information collected based on the identified combination. For example, it is assumed that buzzwords #1, #2, and #3 are detected, and it is determined that the event that has occurred cannot be estimated from the posted information collected based on buzzword #1, the posted information collected based on buzzword #2, and the posted information collected based on buzzword #3. In such a case, the information processing device 10 combines a plurality of buzzwords #1, #2, and #3, and determines whether the event that has occurred can be estimated from the posted information collected based on the combination. Here, when it is determined that the event that has occurred can be estimated from the posted information collected based on the combination of buzzwords #2 and #3, the information processing device 10 performs the processes of steps S2 to S4 based on the posted information collected based on the combination of buzzwords #2 and #3.

[0048] [2-6. Processing based on images included in posted information] 1, the information processing device 10 may generate text information representing an image (moving image, still image) included in the posted information by a method using any image analysis technology. The information processing device 10 may then collect posted information in which the text information generated from the image corresponds to a buzzword, and may infer an event that will occur based on the text information included in the collected posted information (in other words, the text information entered by the user) and the text information generated from the image included in the posted information, and may identify the interest of the event and infer the user's thoughts on the interest.

[0049] 3. Configuration of Information Processing Device Next, the configuration of the information processing device 10 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the information processing device 10 according to an embodiment. As shown in Fig. 2, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0050] (Regarding communication unit 20) The communication unit 20 is realized by, for example, a network interface card (NIC) etc. The communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 100 etc.

[0051] (Regarding the storage unit 30) The storage unit 30 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2, the storage unit 30 has a post information database 31, an event information database 32, and a model database 33.

[0052] (About Post Information Database 31) The posted information database 31 stores various types of information related to the posted information posted by users. An example of the information stored in the posted information database 31 will now be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the posted information database 31. In the example of Fig. 3, the posted information database 31 has items such as "posting ID", "user ID", "posting date and time", "text information", "image information", and "tag information".

[0053] "Posting ID" indicates identification information for identifying posted information. "User ID" indicates identification information for identifying a user. "Posting date and time" indicates the date and time when a user posted the posted information. "Text information" indicates text (comments) entered by a user and included in the posted information. "Image information" indicates an image captured by a user using a user terminal 100 or the like and included in the posted information. "Tag information" indicates a tag assigned to the posted information.

[0054] That is, Figure 3 shows an example in which posted information identified by a posting ID "PID#1" is identified by a user identified by a user ID "UID#1", the date and time when the posted information was posted is "posting date and time #1", the text information included in the posted information is "text information #1", the image information is "image information #1", and the assigned tag is "tag information #1".

[0055] (About Event Information Database 32) The event information database 32 stores information about events that occur. An example of information stored in the event information database 32 will now be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the event information database 32. In the example of Fig. 4, the event information database 32 has items such as "event ID", "date and time", and "content information".

[0056] "Event ID" indicates identification information for identifying an event that occurs. "Date and time" indicates the date and time when the event occurs. "Content information" indicates information about content related to the event that occurs (e.g., news articles, disaster information, etc.), and stores information such as text information and image information contained in the content, and tags attached to the content.

[0057] That is, FIG. 4 shows an example in which an event identified by an event ID "DID#1" occurs at date and time "date and time #1", and the content information relating to the event is "content information #1".

[0058] (About model database 33) The model database 33 stores models that have been trained to generate answers to input questions.

[0059] (Regarding the control unit 40) The control unit 40 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 10 using a RAM as a working area. The control unit 40 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). As shown in FIG. 2, the control unit 40 according to the embodiment has a collection unit 41, an estimation unit 42, a specification unit 43, an inference unit 44, and a provision unit 45, and realizes or executes the functions and actions of information processing described below.

[0060] (About the collection unit 41) The collection unit 41 collects posted information posted by users based on a predetermined character string. For example, in the example of FIG. 1, the collection unit 41 collects posted information including a predetermined character string and posted information related to the predetermined character string from among posted information posted within a recent predetermined period, and stores the collected information in the posted information database 31.

[0061] The collection unit 41 may also collect posted information based on character strings included in posted information that is posted within a predetermined period of time and is equal to or greater than a predetermined threshold. For example, in the example of Fig. 1, the collection unit 41 detects character strings included in posted information that is posted within a recent predetermined period of time and is equal to or greater than a predetermined threshold as buzzwords, and collects posted information that includes buzzwords and posted information related to buzzwords.

[0062] The collection unit 41 may also collect posted information based on a character string included in content indicating a predetermined event. For example, in the example of Fig. 1, the collection unit 41 refers to the event information database 32 and collects posted information based on a character string included in content such as news articles and disaster information distributed in SNS apps and various other services.

[0063] Furthermore, the collection unit 41 may collect posted information to which a tag indicating a predetermined character string has been added. For example, in the example of Fig. 1, the collection unit 41 collects posted information to which a tag indicating a predetermined character string has been added, which is set by a user, an administrator of an SNS application, an administrator of the information processing device 10, or the like.

[0064] The collection unit 41 may also collect posted information based on a character string included in posted information posted within a predetermined period from the time when a predetermined event occurred. For example, in the example of Fig. 1, when a sudden drop in the stock price of any company occurs, the collection unit 41 collects posted information based on a character string included in posted information posted within three days before and after the time when the sudden drop in the stock price occurred.

[0065] Furthermore, the collection unit 41 may collect posted information based on a combination of a plurality of predetermined character strings. For example, in the example of Fig. 1, the collection unit 41 collects posted information using the detected buzzword #2 in addition to the buzzword #1.

[0066] Furthermore, the collection unit 41 may collect posted information including an image showing a predetermined character string. For example, in the example of Fig. 1, the collection unit 41 collects posted information in which text information showing an image corresponds to a buzzword.

[0067] (Regarding the estimation unit 42) The estimation unit 42 estimates an event that will occur based on the posted information collected by the collection unit 41. For example, in the example of Fig. 1, the estimation unit 42 refers to the posted information database 31 and the model database 33 to estimate an event that will occur.

[0068] Furthermore, the estimation unit 42 may estimate a related event related to a predetermined event, based on the posted information collected by the collection unit 41. For example, in the example of Fig. 1, when a sudden drop in the stock price of any company occurs, the estimation unit 42 estimates a related event that causes the sudden drop in stock price.

[0069] The estimation unit 42 may estimate an event that occurs by inputting posted information and an instruction sentence instructing a model that has been trained to generate an answer to an input question to output the event indicated by the posted information. For example, in the example of Fig. 1, the estimation unit 42 estimates an event that occurs by inputting collected posted information and an instruction sentence instructing model #1 to output the event indicated by the posted information.

[0070] The estimation unit 42 may also input the posted information and a question indicating whether the occurring event can be estimated based on the posted information to the model, and when information indicating that the occurring event can be estimated is output from the model, input the posted information and an instruction sentence to the model, thereby estimating the occurring event. For example, in the example of FIG. 1, the estimation unit 42 inputs the collected posted information and a question indicating whether the occurring event can be estimated based on the posted information to the model #1, and when information indicating that the occurring event can be estimated is output from the model #1, inputs the collected posted information and an instruction sentence instructing to output the event indicated by the posted information, thereby estimating the occurring event.

[0071] The estimation unit 42 may further estimate a name related to an event that occurs by inputting the posted information and a question indicating whether or not a name related to an event that occurs can be estimated based on the posted information to the model, and when information indicating that a name related to an event that occurs can be estimated is output from the model, inputting the posted information and an instruction sentence instructing the model to output a name related to the event that occurs. For example, in the example of FIG. 1, the estimation unit 42 inputs the collected posted information and a question indicating whether a name related to event #1 can be estimated based on the posted information to the model #1, and when information indicating that a name related to event #1 can be estimated is output from the model #1, inputting the collected posted information and an instruction sentence instructing the model to output a name related to event #1 to estimate a name related to event #1.

[0072] The estimation unit 42 may further estimate the location of an event by inputting the posted information and a question indicating whether the location where the event occurs can be estimated based on the posted information to the model, and inputting the posted information and an instruction sentence instructing the model to output the location where the event occurs when information indicating that the location where the event occurs can be estimated is output from the model. For example, in the example of FIG. 1, the estimation unit 42 inputs the collected posted information and a question indicating whether the location where the event #1 occurs can be estimated based on the posted information to the model #1, and inputs the collected posted information and an instruction sentence instructing the model to output the location where the event #1 occurs when information indicating that the location where the event #1 occurs can be estimated is output from the model #1, thereby estimating the location where the event #1 occurs.

[0073] Furthermore, the estimation unit 42 may estimate an event that will occur based on text information generated from an image included in the posted information collected by the collection unit 41. For example, in the example of Fig. 1, the estimation unit 42 estimates an event that will occur based on text information included in the collected posted information, text information generated from an image included in the posted information, and the like.

[0074] (Regarding specific part 43) The identification unit 43 identifies, based on the posted information, an interest item in which the user is interested regarding the event estimated by the estimation unit 42. For example, in the example of Fig. 1, the identification unit 43 refers to the posted information database 31 and identifies, based on the collected posted information, an interest item in which the user is interested regarding event #1.

[0075] Furthermore, the identification unit 43 may identify matters of interest in which the user is interested regarding the related event estimated by the estimation unit 42, based on the posted information collected by the collection unit 41. For example, in the example of Fig. 1, the identification unit 43 identifies matters of interest in which the user is interested regarding the related event that causes a sudden drop in stock prices, based on the collected posted information.

[0076] The identification unit 43 may also input the posted information and an instruction sentence instructing the model, which has been trained to generate an answer to the input question, to output the interest items in which the user is interested in the event estimated by the estimation unit, thereby identifying the interest items in which the user is interested in the event. For example, in the example of Fig. 1, the identification unit 43 refers to the posted information database 31 and the model database 33, and inputs the collected posted information and an instruction sentence instructing the model #1 to output the interest items in which the user is interested in the event #1, thereby identifying the interest items in which the user is interested in the event #1.

[0077] Furthermore, the identification unit 43 may identify, based on text information, an interest of the user regarding the event estimated by the estimation unit 42. For example, in the example of FIG. 1, the identification unit 43 identifies an interest of the event that occurs based on text information included in the collected posted information (or text information generated from an image included in the posted information).

[0078] (Regarding the prediction unit 44) The inference unit 44 infers, based on the posted information, the user's thoughts on the interest item identified by the identification unit 43. For example, in the example of Fig. 1, the inference unit 44 infers the user's thoughts on the interest item of event #1, based on the collected posted information.

[0079] The estimation unit 44 may also estimate the user's thoughts on the interest identified by the identification unit by inputting the posted information and an instruction sentence instructing the model, which has been trained to generate an answer to the input question, to output the user's thoughts on the interest identified by the identification unit. For example, in the example of Fig. 1, the estimation unit 44 estimates the user's thoughts on the interest of event #1 by inputting the collected posted information and an instruction sentence instructing the model #1 to output the user's thoughts on the interest of event #1.

[0080] Furthermore, the estimation unit 44 may estimate, based on text information, the user's thoughts on the interest identified by the identification unit 43. For example, in the example of Fig. 1, the estimation unit 44 estimates the user's thoughts on the interest based on text information included in the collected posted information, text information generated from an image included in the posted information, and the like.

[0081] (About the provider 45) The providing unit 45 provides information about an event to a user. For example, in the example of Fig. 1, the providing unit 45 provides a news article about the event #1, a hashtag corresponding to the event #1, and the like, and provides information indicating the inference result #1, the interests of the event #1, and the user's feelings about the interests, etc., in response to an operation of selecting these.

[0082] [4. Information processing flow] The procedure of information processing of the information processing device 10 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of the procedure of information processing according to the embodiment.

[0083] 5, the information processing device 10 collects posted information posted by users based on a predetermined character string (step S101). Next, the information processing device 10 determines whether or not it is possible to estimate an event that will occur based on the posted information. When it is determined that it is not possible to estimate an event that will occur based on the posted information (step S102; No), the information processing device 10 ends the process.

[0084] On the other hand, when it is determined that the event to occur can be estimated based on the posted information (step S102; Yes), the information processing device 10 estimates the event to occur based on the collected posted information (step S103). Next, the information processing device 10 identifies the user's interests regarding the estimated event based on the posted information (step S104). Next, the information processing device 10 infers the user's thoughts on the identified interests based on the posted information (step S105), and ends the process.

[0085] 5. Modifications The above-described embodiment is merely an example, and various modifications and applications are possible.

[0086] [5-1. Processing mode] Among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, and conversely, all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above text and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0087] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0088] Furthermore, the above-described embodiments can be appropriately combined as long as the processing contents are not contradictory.

[0089] 6. Effects As described above, in the information processing device 10 according to the embodiment, the collection unit 41 collects posted information posted by users based on a predetermined character string. The estimation unit 42 estimates an event that will occur based on the posted information collected by the collection unit 41. The estimation unit 42 estimates an event that will occur by inputting the posted information and an instruction sentence instructing a model trained to generate an answer to an input question to output the event indicated by the posted information. The identification unit 43 identifies an interest item in which the user is interested regarding the event estimated by the estimation unit 42 based on the posted information. The identification unit 43 identifies an interest item in which the user is interested regarding the event estimated by the estimation unit 42 based on the posted information. The identification unit 43 inputs the posted information and an instruction sentence instructing a model trained to generate an answer to an input question to output the interest item in which the user is interested regarding the event estimated by the estimation unit, thereby identifying an interest item in which the user is interested regarding the event. The estimation unit 44 estimates the user's thoughts on the interest item identified by the estimation unit 43 based on the posted information. The provision unit 45 provides the user with information regarding the event that will occur. In addition, the estimation unit 44 estimates the user's thoughts on the interest identified by the identification unit by inputting the posted information and an instruction sentence that instructs the model, which has been trained to generate answers to input questions, to output the user's thoughts on the interest identified by the identification unit.

[0090] As a result, the information processing device 10 according to the embodiment can predict an event that will occur based on information posted by users and provide content indicating the user's interests in the event and the user's thoughts about the interests, and can therefore grasp the user's interests and thoughts about the event that will occur.

[0091] In the information processing device 10 according to the embodiment, for example, the collection unit 41 collects posted information based on a character string included in posted information posted within a predetermined period of time that is equal to or greater than a predetermined threshold. The collection unit 41 also collects posted information based on a character string included in content indicating a predetermined event. The collection unit 41 also collects posted information to which a tag indicating a predetermined character string has been added.

[0092] As a result, the information processing device 10 according to the embodiment can collect posted information based on character strings related to an event, thereby improving the accuracy of estimating an event that will occur.

[0093] In the information processing device 10 according to the embodiment, for example, the collection unit 41 collects posted information based on a character string included in posted information posted within a predetermined period from the time when a predetermined event occurs. Then, the estimation unit 42 estimates a related event related to the predetermined event based on the posted information collected by the collection unit 41. Then, the identification unit 43 identifies an interest item in which the user is interested regarding the related event estimated by the estimation unit 42 based on the posted information collected by the collection unit 41.

[0094] As a result, the information processing device 10 according to the embodiment can estimate events related to the event that has occurred, and therefore can grasp the background and cause of the event that has occurred.

[0095] In addition, in the information processing device 10 according to the embodiment, for example, the collection unit 41 collects posted information based on a combination of a plurality of predetermined character strings.

[0096] As a result, the information processing device 10 according to the embodiment can collect posted information based on an appropriate combination of character strings in order to estimate an event that will occur, thereby improving the accuracy of estimating an event that will occur.

[0097] Also, in the information processing device 10 according to the embodiment, for example, the collection unit 41 collects posted information including an image showing a predetermined character string. Then, the estimation unit 42 estimates an event that will occur based on text information generated from the image included in the posted information collected by the collection unit 41. Then, the identification unit 43 identifies an interest of the user in relation to the event estimated by the estimation unit 42 based on the text information. Then, the estimation unit 44 estimates the user's thoughts on the interest identified by the identification unit 43 based on the text information.

[0098] As a result, the information processing device 10 according to the embodiment can infer an event that will occur based on text information generated from an image included in the posted information, and provide content indicating the user's interests in the event and the user's thoughts on the interests, and so on, thereby making it possible to provide more information to the user.

[0099] Furthermore, in the information processing device 10 according to the embodiment, for example, the estimation unit 42 inputs to the model the posted information and a question indicating whether the occurring event can be estimated based on the posted information, and when information indicating that the occurring event can be estimated is output from the model, the estimation unit 42 inputs the posted information and the instruction sentence into the model to estimate the occurring event.

[0100] Thereby, when an event that occurs can be estimated from the collected posted information, the information processing device 10 according to the embodiment can estimate the event that occurs, and therefore can grasp accurate information.

[0101] In addition, in the information processing device 10 according to the embodiment, for example, the estimation unit 42 inputs the posted information and a question indicating whether or not a person's name related to the event that occurs can be estimated based on the posted information to the model, and when information indicating that a person's name related to the event that occurs can be estimated is output from the model, the estimation unit 42 further estimates a person's name related to the event that occurs by inputting the posted information and an instruction sentence instructing the model to output a person's name related to the event that occurs. In addition, the estimation unit 42 inputs the posted information and a question indicating whether or not a place where the event occurs can be estimated based on the posted information to the model, and when information indicating that a place where the event occurs can be estimated is output from the model, the estimation unit 42 further estimates a place where the event occurs.

[0102] As a result, the information processing device 10 according to the embodiment can infer, when it is possible to infer from the collected posted information, the names of people related to an occurring event and the location where the event will occur, thereby making it possible to grasp more facts regarding the occurring event.

[0103] [7. Hardware Configuration] Moreover, the information processing device 10 according to each of the above-described embodiments is realized, for example, by a computer 1000 configured as shown in Fig. 6. The information processing device 10 will be described below as an example. Fig. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. The computer 1000 has a CPU 1100, a ROM 1200, a RAM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0104] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1200 or the HDD 1400. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0105] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a communication network 500 (corresponding to the network N in the embodiment) and sends the data to the CPU 1100, and also transmits data generated by the CPU 1100 to other devices via the communication network 500.

[0106] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs data generated via the input / output interface 1600 to the output devices.

[0107] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1300. CPU 1100 loads the program from recording medium 1800 onto RAM 1300 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0108] For example, when the computer 1000 functions as the information processing device 10, the CPU 1100 of the computer 1000 executes a program loaded onto the RAM 1300 to realize the function of the control unit 40. In addition, the HDD 1400 stores each piece of data in the storage device of the information processing device 10. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from another device via a predetermined communication network.

[0109] [8. Other] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0110] Further, the information processing device 10 described above can flexibly change its configuration, for example, by calling an external platform or the like using an API (Application Programming Interface) or network computing to realize some functions.

[0111] Furthermore, the term "unit" in the claims can be read as "means" or "circuit," etc. For example, a collection unit can be read as collection means or collection circuit. [Explanation of symbols]

[0112] 10. Information processing device 20 Communications Department 30 Storage section 31 Posting Information Database 32 Event Information Database 33 Model Database 40 Control section 41 Collection Department 42 Estimation part 43 Specific part 44 Guessing part 45 Providing Department 100 User terminals

Claims

1. a collection unit that collects posted information posted by users based on a predetermined character string; an estimation unit that estimates an event that will occur based on the posted information collected by the collection unit; an identification unit that identifies an interest item in which a user is interested regarding the event estimated by the estimation unit based on the posted information; an inference unit that infers a user's thoughts on the interest item identified by the identification unit based on the posted information; 13. An information processing device comprising:

2. The collecting unit includes: Collecting posted information based on character strings contained in posted information that is posted within a specified period of time and that is equal to or exceeds a specified threshold 2. The information processing apparatus according to claim 1,

3. The collecting unit includes: Collecting posted information based on character strings contained in content that indicate a specific event 2. The information processing apparatus according to claim 1,

4. The collecting unit includes: Collect posted information tagged with a specific string 2. The information processing apparatus according to claim 1,

5. The collecting unit includes: Collecting posted information based on character strings contained in posted information within a specified period from the time a specified event occurs, The estimation unit is Inferring a related event related to the predetermined event based on the posted information collected by the collection unit; The identification unit is Identifying an interest of a user regarding the related event estimated by the estimation unit based on the posted information collected by the collection unit.

2. The information processing apparatus according to claim 1,

6. The collecting unit includes: Collecting posted information based on combinations of multiple predetermined strings 2. The information processing apparatus according to claim 1,

7. The estimation unit is The posted information and an instruction sentence instructing the model to output the event indicated by the posted information are input to a model that has been trained to generate an answer to an input question, and an event that will occur is estimated.

2. The information processing apparatus according to claim 1,

8. The estimation unit is The posted information and a question indicating whether or not an event that occurs can be estimated based on the posted information are input to the model, and when information indicating that the event that occurs can be estimated is output from the model, the posted information and the instruction sentence are input to the model to estimate the event that occurs.

8. The information processing apparatus according to claim 7,

9. The estimation unit is The posted information and a question sentence indicating whether or not a person's name related to the occurring event can be estimated based on the posted information are input to the model, and when information indicating that a person's name related to the occurring event can be estimated is output from the model, the posted information and an instruction sentence instructing the model to output a person's name related to the occurring event are input to the model, thereby further estimating a person's name related to the occurring event.

8. The information processing apparatus according to claim 7,

10. The estimation unit is The posted information and a question indicating whether or not the location where the event will occur can be estimated based on the posted information are input to the model, and when information indicating that the location where the event will occur can be estimated is output from the model, the posted information and an instruction sentence instructing the model to output the location where the event will occur are input to the model, thereby further estimating the location where the event will occur.

8. The information processing apparatus according to claim 7,

11. The identification unit is The posted information and an instruction sentence instructing the model to output the user's interest in the event estimated by the estimation unit are input to a model trained to generate an answer to the input question, thereby identifying the user's interest in the event.

2. The information processing apparatus according to claim 1,

12. The estimation unit is The posted information and an instruction sentence instructing the model to output the user's thoughts on the interest identified by the identification unit are input to a model trained to generate answers to input questions, thereby predicting the user's thoughts on the interest.

2. The information processing apparatus according to claim 1,

13. The collecting unit includes: Collecting posted information including images showing a predetermined character string; The estimation unit is Predicting an event that will occur based on text information generated from an image included in the posted information collected by the collection unit; The identification unit is Identifying an interest of a user regarding the event estimated by the estimation unit based on the text information; The estimation unit is A user's opinion on the subject of interest identified by the identification unit is inferred based on the text information.

2. The information processing apparatus according to claim 1,

14. 1. A computer-implemented information processing method, comprising: A collection step of collecting posted information posted by users based on a predetermined character string; an estimation step of estimating an event that will occur based on the posted information collected by the collection step; a specifying step of specifying, based on the posted information, an interest item in which the user is interested regarding the event estimated by the estimation step; a guessing step of guessing the user's thoughts on the interest item identified by the identifying step based on the posted information; 13. An information processing method comprising:

15. A collection step of collecting posted information posted by users based on a predetermined character string; an estimation step of estimating an event that will occur based on the posted information collected by the collection step; an identification step of identifying an interest of a user related to the event estimated by the estimation step based on the posted information; a guessing step of guessing a user's thoughts on the interest item identified by the identifying step based on the posted information; An information processing program for causing a computer to execute the above.

Images