JP2017194730A - Decision Support System and Decision Support Method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technique for efficiently updating a model, about a model for estimating an event which occurs, for decision support by simulation.SOLUTION: A decision support system 101 is configured so that: a causal relation model update part 103 comprises an update information generation function 202 for generating temporary update model data for updating a causal relation model based on a causal relation model and an analysis result by a data analysis function 202, and a model update evaluation function 213 for evaluating efficiency of update by the temporary update model data; a causal relation model management part 105 has a model registration/update function 231 for updating the causal relation model by the temporary update model data, when the evaluation result by the model update evaluation function 213 is equal to or higher than a constant degree.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a decision support system and a decision support method.

  As a background art of this technical field, there is Patent Document 1. Patent Document 1 has an issue of “supporting decision making of what measures should be taken when an event that is a target of involvement of an organization or an individual occurs”. Means for evaluating what evaluation value corresponds to each evaluation axis, and means for determining whether any of the evaluation values of the participation target events evaluated on the plurality of evaluation axes is out of the allowable range; If any of the evaluation values on the multiple evaluation axes is out of the allowable range, select an important evaluation axis and extract the measures defined for the important evaluation axis. A method for inferring changes in the evaluation value on the important evaluation axis of the events to be involved by the inference model by the inference model when an arbitrary number of policies are selected and implementing the selected measures, and the targets to be involved based on the inference results Correct the event to an acceptable state It is described as comprising a means for selecting the optimal strategy. "

  Further, Patent Document 1 discloses that "a means for evaluating what evaluation values correspond to a plurality of predetermined evaluation axes on an event to be involved, and each evaluation value of a participation target event evaluated on a plurality of evaluation axes". If any of the evaluation values on the multiple evaluation axes is out of the allowable range, the important evaluation axis is selected and the important evaluation axis is determined. Change of evaluation value on the important evaluation axis of the event concerned when selecting any number of measures from the extracted measures and implementing the selected measures A decision support simulation system is described, which includes means for inferring each policy by an inference model and means for selecting an optimal policy for correcting the event to be involved into an allowable state based on the inference result. This decision support simulation system supports the decision making of what measures should be taken by inferring and evaluating a policy using an inference model when an event that is an object of involvement of an organization or an individual occurs.

Japanese Patent Laid-Open No. 2004-110469

  However, in Patent Document 1, the model that estimates the event that occurs by decision making uses the model that the user first assembled, and there is no method for updating the model in response to the actual situation that changes sequentially, There was a problem that it became a model deviating from the reality, making decision support difficult. Especially when the situation, information, knowledge and know-how change from moment to moment, the model tends to deviate from reality.

  In addition, when updating a model based on the situation and information that changes sequentially, if there are many additions / updates that have little impact on decision support (small meaning and effect), There is a problem that the performance (speed, accuracy) of the prediction simulation decreases. In addition, the wider the range of events to be predicted, the larger the number of information sources for updating, causing a problem that the updating speed decreases.

  Therefore, in order to solve the above problems, an object of the present invention is to provide a technique for effectively updating a model for estimating an event that occurs for decision support by simulation.

  To achieve the above object, a decision support system of the present invention is a decision support system comprising a causal relationship model management unit, a data collection / analysis unit, a causal relationship model update unit, and a causal relationship model management unit. The causal relationship model management unit stores, as a causal relationship model, a plurality of events that occur in society or nature, and the relationship between occurrences of events, and the data collection / analysis unit stores the events A data acquisition function for acquiring information related to the data, and a data analysis function for analyzing information related to the acquired event, wherein the causal relationship model update unit includes the causal relationship model and an analysis result of the data analysis function Based on the above, an update information generation function for generating update data for updating the causal relationship model, and the validity of the update by the update data are evaluated A model update / update function that updates the causal relationship model with the update data when the evaluation result by the model update evaluation function is greater than or equal to a certain level. Have.

  In addition, the decision support method of the present invention acquires information on an event that occurs in society or nature, analyzes the acquired information on the event, a plurality of events that occur in society or nature, and between events Based on the causal relationship model constituted by the occurrence relationship and the analysis result by the data analysis function, update data for updating the causal relationship model is generated, and the effectiveness of the update by the update data is evaluated. When the evaluation result by the model update evaluation function is a certain level or higher, the causal relationship model is updated with the update data.

  ADVANTAGE OF THE INVENTION According to this invention, the technique which updates a model effectively about the model which estimates the event which generate | occur | produces for the decision support by simulation can be provided.

It is a figure which shows an example of the whole block diagram of a decision support system. It is a figure which shows an example of the function block diagram of a decision support system. It is a figure which shows an example of a decision support sequence. It is a figure which shows an example of causal relationship model DB. It is a figure which shows an example of reaction prediction result DB. It is a figure which shows an example of a decision support screen (initial event setting, prediction result display). It is a figure which shows an example of a decision support screen (occurrence event change, prediction result display). It is a figure which shows an example of an interest event registration sequence. It is a figure which shows an example of interest event management DB. It is a flowchart which shows an example of the process sequence (interest event setting with respect to a model) of an interest event registration function. It is a flowchart which shows an example of the process sequence (interest event setting with respect to a prediction result) of an interest event registration function. It is a figure which shows an example of an interest event registration screen (interest event setting with respect to a model). It is a figure which shows an example of an interest event registration screen (interest event setting with respect to a prediction result). It is a figure which shows an example of a causal relationship model update sequence. It is a figure which shows an example of acquisition / analysis management DB. It is a figure which shows an example of acquisition information DB. It is a flowchart which shows an example of the process sequence of a data acquisition function. It is a figure which shows an example of (a) analysis result management DB and (b) occurrence event management DB. It is a flowchart which shows an example of the process sequence of a data analysis function. It is a figure which shows an example of temporary update model DB. It is a flowchart which shows an example of the process sequence of an update information generation function. It is a figure which shows an example of model update management DB. It is a flowchart which shows an example of the process sequence of a model update evaluation function and a model registration / update function. It is a flowchart which shows an example of the process sequence of an update log registration function and an update log analysis function. It is a figure which shows an example of the causal relationship model update sequence in case a user intervenes. It is a figure which shows an example of a causal relationship model update screen.

  Hereinafter, a decision support system 101 and a decision support method according to an embodiment of the present invention will be described with reference to the drawings. In the present embodiment, an explanation will be given of an example of support for decision making in a national strategy for predicting the actions of a country and an organization and considering measures, but the present embodiment can also be applied to other fields.

  In this embodiment, a decision maker who makes a decision on a national strategy, or a person who supports decision-making, before or when an event that affects the strategy (for example, military action in another country) occurs, Alternatively, the decision support method and the decision support system 101 that provide information for supporting the decision when determining the response of the own organization will be described.

  This system 101 can be used to identify social events such as natural disasters and stock price crashes, and relationships such as the actions of each country / organization including its own country / organization (which event occurs when an event occurs). Is used as a causal relationship model, and by using the causal relationship model, the next event that occurs as a result of the occurrence of a certain event and the response to it is predicted by simulation. Present to decision supporters). In addition, the causal relationship model is information such as information from information sources that the system 101 sequentially acquires, for example, public information such as social media and news information, and survey report information and countermeasure information held by the user of the system 101. Since it is sequentially updated according to the analysis result of public internal information, it is possible to always present a prediction of an event along the latest information. This system 101 is used to examine or determine the response of the home country or the organization before or at the time of occurrence of events (for example, military actions of other countries) that are executed at any time and affect the strategy. Alternatively, it may be used for graphic training such as considering what kind of response should be taken by inputting and executing this system assuming that an event that has not occurred has occurred.

  FIG. 1 is a diagram illustrating an example of the entire configuration of a decision support method and system according to the present embodiment.

  As shown in FIG. 1, a decision support system 101 according to the present embodiment includes a data collection / analysis unit 102, a causal relationship model update unit 103, an update evaluation management unit 104, a causal relationship model management unit 105, The reaction prediction unit 106 includes a user management unit 107 and an interface unit 108.

  The data acquisition / analysis unit 102 collects the information source 109 via the network 110 such as the Internet or a local network, analyzes the collected information, and generates information for updating the causal relationship model. The information source 109 includes public information such as social media and news information, and non-public internal information such as survey report information and countermeasure information held by the user of the system 101.

  The causal relationship model updating unit 103 uses the information generated by the data acquisition / analysis unit 102 to update the causal relationship model managed by the causal relationship model management unit 105, and the validity of the update (for the user). Evaluate whether a meaningful update has occurred.

  The update evaluation management unit 104 manages the contents of the update performed by the causal relationship model update unit 103 and the evaluation result.

  The causal relationship model management unit 105 is responsible for social events such as natural disasters and stock price crashes, and relationships such as the actions of each country / organization including its own country / own organization (which event occurs when an event occurs). Information that indicates whether it affects the occurrence of occurrence) as a causal relationship model.

  The reaction predicting unit 106 uses the causal relationship model managed by the causal relationship model managing unit 105 to predict the occurrence of a certain event and the next event as a result of the response by simulation.

  The user management unit 107 manages users who use the decision support system 101. For example, the user (model administrator) 111 and the user (decision determiner) 112 perform access authentication when using the system 101. . A user (model manager) 111 is a user who is responsible for updating and evaluating the causal relationship model, and a user (decision maker) 112 is a user who uses this system 101 to predict an event that will occur in the future. is there.

The interface unit 108 receives input of information from terminals used by the user (model administrator) 111 and the user (decision maker) 112, and processes each unit of the decision support system 101 for the terminal used by the user. The result is output. Here, the decision support system 101 and the terminal of each user may be directly connected, or may be connected via a network such as a local network or the Internet.

  FIG. 2 is a diagram illustrating an example of a functional configuration diagram of the decision support system 101 according to the present embodiment.

  As shown in FIG. 2, in the decision support system 101 according to this embodiment, the data collection / analysis unit 102 provides a data acquisition function 201 and a data analysis function 202.

  The data acquisition function 201 is owned by the user of the system 101 based on public information such as social media and news information based on data (acquisition source data) related to information sources and search conditions registered in the data acquisition / analysis management DB 204. To obtain information such as investigation report information and countermeasure information to be disclosed, and register the acquired information in the acquisition information DB 203.

  The data analysis function 202 performs natural language analysis processing, co-occurrence analysis processing, and the like on the data registered in the acquisition information DB 203 to generate information for updating the causal relationship model and registers it in the analysis result management DB 205 To do.

  Note that the data acquisition function 201 registers information input to the system 101 on the occurrence event management DB 206 on the assumption that an event that has not currently occurred by the user has occurred. Further, the data analysis function 202 registers the information registered in the analysis result management DB 205 in the occurrence event management DB 206 as the latest information that is currently generated.

  The causal relationship model update unit 103 provides an interest event registration function 211, an update information generation function 212, a model update evaluation function 213, a prediction result evaluation function 214, and an update information correction function 215.

  The interest event registration function 211 acquires an event of interest to the user (acquired via an interest event setting screen 262 described later), and registers it in the interest event management DB (interest event storage unit) 217.

  The update information generation function 212 uses the data registered in the analysis result management DB 205 to generate events (nodes) and inter-event (inter-node) relationships newly registered in the causal relationship model and register them. Then, the updated causal relationship model is registered in the temporary update model DB 216 as a temporary update model.

  The model update evaluation function 213 has a relationship between an interest event (node) registered in the interest event management DB 217 and an update method (for example, a relationship between events not registered in the existing causal relationship model (inter-node)). Evaluate the updated content based on new additions.

  The prediction result evaluation function 214 acquires simulation results using the models before and after the update (existing causal relationship model and temporary update model) (acquired via a reaction prediction generation function 241 described later), and outputs it to the user (described later). Presented via the model update screen 263).

  The update information correction function 215 acquires correction contents for the model update contents from the user (acquired via a model update screen 263 described later), and corrects information registered in the temporary update model DB 216.

  The update result management unit 104 provides an update log registration function 222 and an update log analysis function 221.

  The update log registration function 222 registers the update content generated by the causal relationship model update unit 103 in the model update management DB 223.

  The update log analysis function 221 extracts the importance of the information source and the information to be searched from the data regarding the update contents registered in the model update management DB 223 and the events related to the user registered in the event management DB 217, Data related to information sources and search conditions registered in the data acquisition / management DB 204 is updated.

  The causal relationship model management unit 105 provides a model registration / update function 231 and a model acquisition function 232.

  The model registration / update function 231 uses the data registered in the causality model DB 233 as a past model based on the evaluation result of the model update evaluation function 213 (effectiveness of model update) in the case of an evaluation above a certain level. Data stored in the model management DB 234 and registered in the temporary update model DB 216 is registered in the causal relationship model DB 233 (updates the causal relationship model).

  The model acquisition function 232 acquires data registered in the causal relationship model DB 233 and the past model management DB 234 and outputs it to other functions.

  The reaction prediction unit 106 provides a reaction prediction generation function 241 and a reaction prediction adjustment function 242.

  The reaction prediction generation function 241 uses the data (causal relationship model) registered in the causal relationship model DB 233, the past model management DB 234, and the temporary update model DB 216 to generate a certain event and the result of the response, The occurring event is predicted by simulation, and the result is registered in the reaction prediction result DB 243.

  The reaction prediction adjustment function 242 acquires a correction content for the response prediction result from the user (acquired via a model update screen 263 described later), and an event registered in the temporary update model DB 216 so that the correction content becomes a prediction result. Correct the relationship between nodes (between nodes).

  The user management unit 107 provides a user registration / authentication function 251.

  The user registration / authentication function 251 registers information (user name, password, etc.) on the user who uses the decision support system 101 in the user management DB 252 and is responsible for updating and evaluating the causal relationship model (model administrator). 111 and a user (decision maker) 112 who predicts an event that will occur in the future using the system 101 performs access authentication when using the system 101.

  The interface unit 108 provides a menu selection screen 261, an interest event setting screen 262, a model update screen 263, and a decision support screen 264 to a terminal used by the user.

  The menu selection screen 261 is a screen for selecting a function to be used from functions provided by the decision support system 101 for the user (model administrator) 111 and the user (decision maker) 112, for example.

  The interest event setting screen 262 is a screen for each user to input an event of interest.

  The model update screen 263 is presented in the presentation of information registered in the acquired information DB 203, the input of information from the user, the presentation of analysis results registered in the analysis result management DB 205, the causal relationship model DB 233 and the temporary update model DB 216. It is a screen for performing presentation of a causal relationship model and correction input from a user, presentation of a prediction result registered in the reaction prediction result DB 243, correction input from a user, and the like.

  The decision support screen 264 is a screen for selecting a causal relationship model to be used for prediction and executing a simulation, inputting correspondence contents from a user, and presenting a prediction result.

  FIG. 3 is a diagram illustrating an example of a decision support sequence according to the present embodiment.

  This sequence uses a causal relationship model in the decision support system 101 to predict the occurrence of a certain event and the response to it as a result of the next event by simulation. It is a basic process for presenting.

  When the user (decision maker) 112 logs into the decision support system 101 with a user ID and password registered in advance in the user management DB 252, a menu selection screen 261 is displayed. On the menu selection screen 261, it is possible to select interest event setting, model update, and decision support. Here, when the user 112 selects decision support, a decision support screen 264 is displayed (details of the screen will be described later with reference to FIG. 6).

  Further, the user ID of the user 112 is passed as a model list acquisition request to the model acquisition function 232, and the model acquisition function 232 is based on the user ID, and the causal relationship model in the causal relationship model DB 233 (details will be described later with reference to FIG. 4). The management table 410 is searched, a record (model ID, model name, update time) corresponding to the user ID is acquired as causal relationship model management data, and is output to the decision support screen 264 as a model name list.

  When the user 112 selects a model to be used for the current decision support from the model name list (causal model management data) output to the decision support screen 264, the model ID of the selected model is the model acquisition function 232. Passed to. The model acquisition function 232 records based on the passed model ID from the causal relationship model table 400 of the causal relationship model DB 233 or the past model management DB 234 in which the past causal relationship model is stored, and the record corresponding to the passed model ID. (Model ID, node ID, node name, subject, update time, link destination node, relationship degree, relationship update time) are acquired as causal relationship model data and output to the decision support screen 264.

  In the decision support screen 264, when the user 112 selects the event (initial event) that occurs in step 0 from the causal relationship model data and executes the prediction start, the node ID of the initial event is input to the reaction prediction generation function 241. Passed. The reaction prediction generation function 241 uses the causal relationship model data acquired by the model acquisition function 232 as an event that occurs in step 0 as the selected initial event, and predicts an event that occurs after step 1 through simulation, The prediction result (subject, generation step, node ID, node name, probability) is output to the decision support screen 264 as prediction result data.

  The output prediction result data and the initial event are registered as a scenario in the reaction prediction result DB 243 in association with the causal relationship model data used for the simulation. Note that when the user 112 executes a prediction start without selecting an initial event, the reaction prediction generation function 241 generates the latest event (subject, node name) registered in the generated event management DB 206 in step 0. Using the causal relationship model data acquired by the model acquisition function 232 as an event, an event occurring after step 1 is predicted by simulation.

  In the decision support screen 264, when the user 112 changes an event (node) occurring at a certain step from the prediction result data to another event, the step number and the node ID of the event (node) before and after the change are changed. The change event data is passed to the reaction prediction generation function 241. The reaction prediction generation function 241 replaces the portion corresponding to the event (node) before the change of the changed event data in the output prediction result data with the event (node) after the change, and simulates the event occurring after that step number The decision result support screen 264 uses the prediction result (subject, generation step, node ID, node name, probability) including the prediction result data and the initial event before the re-predicted step number as prediction result data. Output to.

  Further, the prediction result data is registered as a scenario in the reaction prediction result DB 243 in association with the causal relationship model data used for the simulation. By repeatedly executing the event change by the user 112 and the re-prediction by the reaction prediction generation function 241, what will happen next is predicted while changing the pattern in which various events occur, thereby supporting the user's decision making. Information can be provided. In addition, as a countermeasure against an event (prediction result) that occurs at a certain step, the user selects which event (action) to select at the next step, and presents the event that occurs thereafter, thereby making a decision You can also do training.

  FIG. 4 is a diagram illustrating an example of the causal relationship model DB 233 according to the present embodiment.

  The causal relationship model DB 233 includes a causal relationship model table 400 and a causal relationship model management table 410.

  The causal relationship model table 400 includes a model ID 401, a node ID 402, a node name 403, a subject 404, an update time 405, a link destination node 406, a degree of relationship 407, and a relationship update time 408. .

  A model ID 401 is for identifying a model. The node ID 402 is for identifying an event (node). The node name 403 indicates the content of the event. The subject 404 indicates the subject (subject) of the event. The update time 405 indicates the time when the contents of the record are updated. The link destination node 406 is for registering the node ID of a node related to the node of the record (a node that may occur next). The relation degree 407 indicates the strength of the relation (high possibility of occurring next). The relationship update time 408 indicates the time when the related node and the strength of the relationship are updated.

  Thereafter, when there are a plurality of related nodes, contents equivalent to the link destination node 406, the relation degree 407, and the relationship update time 408 are registered in the link destination node (2) 409 and the subsequent pages. For example, in the record 420, when an event (node) that “Country C regulates trade” occurs, there is a possibility that an event (node) that “Country B acts militaryly” of the node ID “4” may occur. The relationship is shown.

  The causal relationship model management table 410 includes a model ID 411, a model name 412, an update time 413, a user ID 414, and a storage location 415.

  The model ID 411 is for identifying a model. The update time 413 indicates the time when the model is updated (newly added). The user ID 414 is for identifying the owner of the model. The storage location 415 indicates a location (local path, URL, etc.) where the model corresponding to the record is stored. When the storage location 415 is not registered, it is registered in the causal relationship model table 400 as the latest model.

  FIG. 5 is a diagram illustrating an example of the reaction prediction result DB 243 according to the present embodiment.

  The reaction prediction result DB 243 has a reaction prediction result table 500 and a reaction prediction result management table 510.

  The reaction prediction result table 500 includes a scenario ID 501, a subject 502, an occurrence step 503, a node ID 504, a node name 505, and an occurrence probability 506.

  The scenario ID 501 is for identifying a prediction result (scenario). The subject 502 indicates the subject (subject) of the event (node) that occurs. The generation step 503 indicates the timing of the event that occurs. The node ID 504 is for identifying an event (node) that occurs. The node name 505 indicates the content of the event. The occurrence probability 506 represents the probability that the event will occur. For example, the record 520 indicates that the event (node) that “Country A protests” occurs at the timing of step 2 with a probability of 30%.

  The reaction prediction result management table 510 includes a scenario ID 511, a scenario name 512, a prediction time 513, a user ID 514, and a model ID 515.

  This is for identifying the scenario ID 511 prediction result (scenario). Prediction time 513 Indicates the time when the scenario of the record is generated (predicted). User ID 514 is for identifying the owner of the causal relationship model used in the prediction of the record. Model ID 515 is for identifying the causal relationship model.

  FIG. 6 is a diagram showing an example of a decision support screen (initial event setting, prediction result display) 264 according to the present embodiment.

  The decision support screen 264 includes a scenario name display unit 601, a scenario name change button 602, a reaction prediction result display unit 603, a model name display unit 604, a model read button 605, and a prediction start button 606. .

  When the user 112 presses the model name display unit 604, the model name list output by the model acquisition function 232 is displayed. When the user 112 selects a model to be used for the current decision support from the displayed list and presses the model reading button 605, the causal relationship model data of the model selected by the model acquisition function 232 is determined. Output on the support screen. Next, when the user 112 selects the event (initial event) that occurs in step 0 and presses the prediction start button 606, the prediction result output by the reaction prediction generation function 241 described above is displayed as the reaction prediction result display unit 603. Is displayed. For example, when the user 112 presses down the event (action) 610 of country B in step 0 as an initial event, selectable events of country B are displayed on the display unit 611, and “country A” is displayed from the displayed events. When “military invasion” is selected and the prediction start button 606 is pressed, a prediction result is displayed on the reaction prediction result display unit 603. As shown in the reaction prediction result 621, events that occur at each step of each subject are displayed with probability. For example, the occurrence event 622 in the response prediction result indicates that the probability that country A protests in step 1 is 70%.

  In addition, a scenario name (automatically generated by the decision support system) for identifying the reaction prediction result is displayed on the scenario name display unit 601. The scenario name can be freely changed by the user 112, and the scenario name can be changed by pressing a scenario name change button 602.

  FIG. 7 is a diagram showing an example of a decision support screen (change of occurrence event, prediction result display) 264 according to the present embodiment.

  When the user 112 selects an event to be changed from the reaction prediction result 621 displayed on the reaction prediction result display unit 603 and presses the prediction start button 606, the prediction result output by the reaction prediction generation function 241 described above is displayed. Is displayed on the reaction prediction result display unit 603. For example, when the event (action) 710 in country A in step 1 is pressed, selectable events in country A (other events that may occur in step 1) are displayed on the display unit 711. When the “ship dispatch” is selected and the prediction start button 606 is pressed, a prediction result re-predicted from step 2 is displayed.

  FIG. 8 is a diagram illustrating an example of an interest event registration sequence according to the present embodiment.

  As shown in FIG. 8, in the interest event registration sequence, the causal relationship model and the response prediction result based on the causal relationship model are presented to the user, and the event (node) of interest is selected from the information presented by the user. Then, an interest value for each node of the causal relationship model is set and registered in the interest event management DB 217.

  When the user (model administrator) 111 logs in to the decision support system 101 with the user ID and password registered in the user management DB 252 in advance, a menu selection screen 261 is displayed. On the menu selection screen 261, it is possible to select interest event setting, model update, and decision support. Here, when the user 111 selects the event of interest setting, an event of interest setting screen 262 is displayed (details of the screen will be described later with reference to FIGS. 12 and 13).

  Next, the user ID of the user 111 is passed to the model acquisition function 232, and the model acquisition function 232 searches the causal relationship model management table 410 of the causal relationship model DB 233 based on the user ID and records (models) corresponding to the user ID. ID, model name, update time) are acquired as causal relationship model management data and output to the event of interest setting screen 262.

  When the user 111 selects a model to be used for the current interest event setting from the causal relationship model management data output to the interest event setting screen 262, the model ID of the selected model is passed to the model acquisition function 232. Based on the model ID, the model acquisition function 232 reads a record (model ID, node ID) corresponding to the model ID from the causal relationship model table 400 of the causal relationship model DB 233 or the past model management DB 234 in which past causal relationship models are stored. , Node name, subject, update time, link destination node, relationship level, relationship update time) are acquired as causal relationship model data and output to the interest event setting screen 262. At this time, the node name and subject whose interest value is already registered in the interest event management DB 217 may be output together with the causal relationship model data.

  From the causal relationship model data output to the interest event setting screen 262, the user 111 selects a node for which an interest value is set as an event of interest, and inputs the interest value (interest event setting for the model). Interest values may be input to a plurality of nodes.

  Here, the user 111 can also register an interest value for the prediction result. The user 111 selects a means for registering an interest value for the prediction result, and selects an initial event (an event that occurs in step 0). As a result, the reaction prediction generation function 241 uses the causal relationship model data acquired by the model acquisition function 232 and the initial event (the latest event registered in the occurrence event management DB 206 if there is no input from the user). (Subject, node name)) is used to predict an event occurring after step 1 by simulation, and the prediction result (scenario ID, subject, generation step, node ID, node name, probability) is predicted result data To the event-of-interest setting screen 262. The prediction result data is also registered in the reaction prediction result DB 243.

  From the prediction result data output to the interest event setting screen 262, the user 111 selects an event (node) for which an interest value is to be set as an event of interest, and inputs an interest value (interest event setting for the prediction result). ). Interest values may be input to a plurality of nodes.

  When the user 111 executes the interest event registration on the interest event setting screen 262, the interest event setting data (model ID, node ID, interest value) input in the interest event setting for the model described above, and the interest event setting for the prediction result The interest event setting data (scenario ID, node ID, interest value) input in step 1 is passed to the interest event registration function 211 together with the user ID. The interest event registration function 211 registers the interest value for each node of the causal relationship model in the interest event management DB 217 in accordance with the processing described later with reference to FIGS.

  FIG. 9 is a diagram illustrating an example of the interest event management DB 217 according to the present embodiment.

  The interest event management DB 217 has an interest value management table 900. The interest value management table 900 includes a node ID 901, a node name 902, a subject 903, an update time 904, an interest value 905, a user ID 906, and a model ID 907.

  The node ID 901 is for identifying an event (node). The node name 902 indicates the content of the event. The subject 903 indicates the subject (subject) of the event. The update time 904 is the time when the contents of the record are updated. The interest value 905 is an interest value set in the node of the record. The user ID 906 is for identifying the user who has set the interest value. The model ID 907 is for identifying a model.

  FIG. 10 is a flowchart illustrating an example of a processing procedure (interest event setting for a model) of the interest event registration function 211 according to the present embodiment.

  The interest event registration function 211 receives the interest event setting data (model ID, node ID, interest value) for the model and the interest event setting data (scenario ID, node ID, interest value) for the prediction result from the interest event setting screen 262. Then, according to the following processing, the interest value for each node of the causal relationship model is registered in the interest event management DB 217.

  First, in S1001, the interest event registration function 211 confirms whether or not the interest event setting data (model ID, node ID, interest value) for the model is received. If not received, S1101 and subsequent steps in FIG. 11 are executed.

  In S1002, the interest event registration function 211 sets one interest event setting data that has not yet been processed by this processing procedure from the received interest event setting data (model ID, node ID, interest value) for one or more models. Extract.

  In S1003, the interest event registration function 211 receives the user ID received together with the model ID, node ID, interest value, and interest event setting data of one interest event setting data extracted in S1002 as interest event data (record). Are registered in the event management DB 217 together with the current time (update time) (if a record with the same node ID already exists, it is overwritten with the current data (record)).

  In S1004, the interest event registration function 211 searches the item “link destination node” (406, 409) of the causal relationship model table 400 (FIG. 4), and sets the node ID of the interest event data (record) registered in S1003. A record (factor record) possessed as the link destination node ID is extracted. For example, in FIG. 4, since the link destination node of “military exercise” with node ID “5” is “2”, “military exercise” is a factor record of “protest” with node ID “2”.

  In S1005, the event of interest registration function 211 executes S1006 and subsequent steps if a factor record is present in S1004, and executes S1010 and subsequent steps if it does not exist.

  In S1006, the interest event registration function 211 extracts the relationship level corresponding to the link destination node from the factor record extracted in S1004, and the relationship value (%) is added to the interest value registered in the interest event management DB 217 in S1003 or S1008. A value obtained by multiplying the value (rounded down by 10 or less) is calculated as an interest value. In FIG. 4, the factor record “military exercise” of “protest” with the node ID “2” has a relationship degree of 50 with “protest”. For example, the user 111 sets an interest value 50 for “protest”. In this case, the interest value of the “military exercise” is 50 × 50 (%) = 20 (rounded down to the nearest 1).

  In S1007, the event of interest registration function 211 executes S1008 and subsequent steps when there is a factor record whose interest value calculated in S1006 is other than 0, and executes S1010 and subsequent steps when there are none (when all are 0). .

  In S1008, the interest event registration function 211 uses the node ID and interest value of the node for which the interest value was calculated in S1006 (for example, the interest value “20” of the military exercise with the node ID “5”) as the interest event data (record). Are registered in the interest event management DB 217 (if the same node ID already exists, the interest value is added (upper limit 100)).

  In S1009, a factor record having the node ID of the record registered in S1008 as a link destination node is extracted from the causal relationship model table 400, and S1005 and subsequent steps are executed. By repeating S1005 to S1009, it is possible to set the interest value while going back to the causal relationship of the nodes (the interest value becomes smaller as going back).

  In S1010, in the case of interest event setting data (model ID, node ID, interest value) for the received model, if interest event setting data that has not yet been processed by this processing procedure remains, execute S1002 and subsequent steps. If it does not remain, S1101 and subsequent steps in FIG. 11 are executed.

  FIG. 11 is a flowchart illustrating an example of a processing procedure (interest event setting for a prediction result) of the interest event registration function 211 according to the present embodiment.

  When the interest event registration function 211 receives the interest event setting data (scenario ID, node ID, interest value) for the prediction result from the interest event setting screen 262, the interest event registration function 211 calculates the interest value for each node of the causal relationship model according to the following processing. And registered in the event of interest management DB 217.

  First, in S1101, the interest event registration function 211 checks whether or not interest event setting data (scenario ID, node ID, interest value) for the prediction result has been received, and if received, executes S1102 and subsequent steps. If not received, the process is terminated.

  In S1102, the interest event registration function 211 sets 1 of interest event setting data that has not yet been processed by this processing procedure from interest event setting data (scenario ID, node ID, interest value) for one or more received prediction results. Extract one.

  In S1103, the interest event registration function 211 receives the user ID received together with the scenario ID, node ID, interest value, and interest event setting data of the one interest event setting data extracted in S1102 as interest event data (record). Are registered in the event management DB 217 together with the current time (update time) (if a record with the same node ID already exists, it is overwritten with the current data (record)). As for the scenario ID, the model ID is acquired with reference to the reaction prediction result management table 510, and the model ID is registered in the interest event management DB 217.

  In S1104, the interested event registration function 211 extracts the record of the node ID in the reaction prediction result table 500 (FIG. 5) based on the scenario ID and node ID of the interested event setting data extracted in S1102.

  In S1105, the event of interest registration function 211 responds to a record having the scenario ID of the one event of interest setting data extracted in S1102 and the value of the occurrence step of the record extracted in S1104 as the value of the occurrence step. Whether it exists in the prediction result table 500 is checked. If it exists, S1106 and subsequent steps are executed, and if not, S1110 and subsequent steps are executed. For example, if the record extracted in S1104 is the “military exercise” with the node ID “5” in the reaction prediction result table 500, the generation step is “3”, and therefore the generation step is “2”. There are three records with node IDs “2”, “3”, and “4”.

  In S1106, the interest event registration function 211 extracts the node ID of the record having the generation step value −1 extracted in S1104 or S1109 as the generation step value, and registers it in the interest event management DB 217 in S1103 or S1108. The value calculated by the occurrence probability of the record extracted in the previous step (1 truncation) is calculated as the interest value. For example, if the record extracted in S1104 is the “military exercise” with the node ID “5” in the reaction prediction result table 500, the generation step is “3”, and therefore the generation step is “2”. There are three records with node IDs “2”, “3”, and “4”. In this case, since the probability of occurrence of “military exercise” is 50%, for example, the interest value of “military action” of node ID “4” is set by user 111 to “military exercise”. In this case, 90 × 1/2 × 50 (%) = 20 (1's rounded down).

  In S1107, the interest event registration function 211 executes S1108 and subsequent steps for records where the calculated interest value is other than 0 when there is a record whose interest value calculated in S1106 is other than 0. Perform the following.

  In S1108, the interest event registration function 211 uses the node ID and the interest value (for example, the interest value “20” of the military action of the node ID “4”) of the record for which the interest value is calculated in S1106, as the interest event data (record). Are registered in the interest event management DB 217 (if the same node ID already exists, the interest value is added (upper limit 100)).

  In S1109, the interested event registration function 211 extracts the record of the node ID in the reaction prediction result table 500 for the node ID of the record whose interest value was calculated in S1106, and executes S1105 and the subsequent steps. By repeating S1105 to S1109, the interest value can be set while going back the prediction result (the interest value becomes smaller as going back).

  In S1110, the interested event registration function 211 determines that the interested event setting data (scenario ID, node ID, interest value) for the received prediction result remains interested event setting data that has not yet been processed by this processing procedure. Executes S1102 and subsequent steps, and terminates the processing if there is no remaining.

  FIG. 12 is a diagram showing an example of an interest event registration screen (interest event setting for a model) 262 according to the present embodiment.

  The interest event registration screen 262 includes a menu return button 1201 for returning to the menu screen, a model name display unit 1202, a model display button 1203, a prediction result display button 1204, a search input unit 1205, and a search button 1206. , An interest event setting unit 1207 and an interest value registration button 1208.

  When the user 111 presses the model name display unit 1202, the model name list output by the model acquisition function 232 is displayed. When the user 111 selects a model to be used for current interest registration from the displayed list and presses the model display button 1203, the model acquisition function 232 described above causes the causal relationship model data of the selected model to be displayed. It is displayed on the event of interest setting unit 1207. Next, when the user 111 presses an event for setting an interest value from among the events (nodes) displayed in the event-of-interest setting unit 1207, an interest value registration unit 1209 is displayed, and the user 111 is interested in the event. A value can be entered. When the user 111 completes the input and presses the interest value registration button 1208, the interest event registration function 211 described above calculates the interest value set for each event and the interest value of each related event. Registered in the event management DB 217.

  If the model is large, an event (node) searched based on the search keyword is entered in the center of the event of interest setting unit 1207 by inputting a search keyword into the search input unit 1205 and pressing the search button 1206. You can display and enter interest values.

  FIG. 13 is a diagram showing an example of an interest event registration screen (interest event setting for a prediction result) 262 according to the present embodiment.

  When the user 111 presses the model name display unit 1202, the model name list output by the model acquisition function 232 is displayed. When the user 111 selects a model to be used for registration of the current event of interest from the displayed list and presses the prediction result display button 1204, the reaction prediction result data output by the reaction prediction generation function 241 described above is displayed. It is displayed on the event of interest setting unit 1207. Next, when the user 111 presses an event that sets an interest value from among the events (nodes) displayed in the event-of-interest setting unit 1207, an interest value registration unit 1301 is displayed, and the user 111 is interested in the event. A value can be entered. When the user 111 completes the input and presses the interest value registration button 1208, the interest value set for each event and the interest value of each event that occurred before the occurrence of the event are obtained by the above-described interest event registration function 211. Calculated and registered in the interest event management DB 217.

  For example, as shown in FIG. 13, when the “military exercise” in step 2 is designated as an event of interest (for example, an interest value of 90), an interest value of 90 is set in the node (military exercise) of the causal relationship model. Registered in the management DB 217). The prediction result “military action” in the previous step (step 1) is also set to 90 × 1/2 × 0.7 = 30 (rounded down to 1) by multiplying by 70% probability of military exercise. Is done. The node (trade regulation) of the previous step (Step 0) is also set to 30 × 1/2 × 0.8 = 10 by multiplying the probability of military action (interest value 30) by 80%. The

  FIG. 14 is a diagram illustrating an example of a causal relationship model update sequence according to the present embodiment.

  As shown in FIG. 14, in the causal relationship model update sequence, data such as news articles is acquired from an information source periodically or in response to an instruction from a user, and an event (node) for model update and between the nodes is acquired. Performs data analysis such as relationship extraction, generates update information, evaluates the effectiveness of the update information, updates the model if the effectiveness is above a certain level, and if not, updates are suspended .

  The data acquisition function 201 receives information source data (information source ID) related to an information source to be acquired from the acquisition / analysis management DB 204 periodically (for example, every 3 hours) or in response to a request from the user (model manager) 111. , URL, etc.) and search data (search ID, keyword) for information search are acquired, and information for updating the causal relationship model is acquired from the information source 109 based on these data. For the information source from which the information has been acquired, the acquisition time is registered in the corresponding record in the acquisition / analysis management DB 204. The acquired information is registered in the acquisition information DB 203.

  The data analysis function 202 performs noun extraction and subject predicate extraction by natural language analysis, extraction of the number of co-occurrence by co-occurrence analysis, etc. for the acquisition information registered in the acquisition information DB 203 and registers the analysis result in the analysis result management DB 205 To do. In addition, the subject predicate extraction result is registered in the occurrence event management DB 206 as an event currently occurring.

  The update information generation function 212 uses the analysis result registered in the analysis result management DB 205 and the acquisition time of each acquisition information registered in the acquisition information DB 203 to extract the relationship between the events (nodes). The relationship between events (nodes) targeted for update and events (between nodes) is registered in the temporary update model DB 216 as update target data. Also, the causal relationship model data to be updated this time is acquired from the causal relationship model DB 233, and updated temporary update model data is generated based on the update target data and registered in the temporary update model DB 216.

  The model update evaluation function 213 uses the update pattern of each event (node) for the temporary update model data (update data) registered in the temporary update model DB 216 (for example, between events not registered in the existing causal relationship model) The update content is evaluated based on the newly added relationship (between nodes). Further, the update contents are evaluated based on whether or not the interest event (node) registered in the interest event management DB 217 has been updated. Based on these evaluation results, the update effectiveness is calculated.

  Based on the update effectiveness calculated by the model update evaluation function 213, the model registration / update function 231 uses the data registered in the causal relationship model DB 233 as a past model when the update effectiveness is a predetermined value or more. Data stored in the model management DB 234 and registered in the temporary update model DB 216 is registered in the causal relationship model DB 233 (updates the causal relationship model).

  The update log registration function 222 registers the update contents registered in the temporary update model DB 216 in the model update management DB 223.

  The update log analysis function 221 extracts the importance of the information source and the information to be searched from the data regarding the update contents registered in the model update management DB 223 and the events related to the user registered in the interest event management DB 217, Data related to information sources and search conditions registered in the acquisition / analysis management DB 204 is updated.

    FIG. 15 is a diagram showing an example of the acquisition / analysis management DB 204 according to the present embodiment.

  The acquisition / analysis management DB 204 has an information source management table 1500 and a search management table 1510.

  The information source management table 1500 includes an information source ID 1501, an information source (URL) 1502, an update time 1503, a previous acquisition time 1504, an importance 1505, and a user ID 1506.

  The information source ID 1501 is for identifying an information source. The information source (URL) 1502 is for specifying the location of the information source. The update time 1503 indicates the time when each record is updated. The previous acquisition time 1504 indicates the time when information acquisition was performed from the information source of the record. The importance 1505 indicates the importance of each information source. The user ID 1506 is for identifying a user who uses information collection from the information source of the record. Here, in the information source (URL) 1502, a storage location on the user's local server (a folder storing articles and report documents held by the user) may be registered.

  The search management table 1510 includes a search ID 1511, a keyword 1512, an update time 1513, an importance level 1514, and a user ID 1515.

  The search ID 1511 is for identifying a search keyword. The keyword 1512 is for use in a search. The update time 1513 indicates the time when each record is updated. The importance 1514 indicates the importance of each keyword. The user ID 1515 is for identifying a user who uses information collection using the keyword of the record.

  FIG. 16 is a diagram illustrating an example of the acquisition information DB 203 according to the present embodiment.

  The acquisition information DB 203 has an acquisition information table 1600.

  The acquisition information table 1600 includes an update ID 1601, an article ID 1602, an article content 1603, an information source (URL) 1604, an acquisition time 1605, a status 1606, and a user ID 1607.

  The update ID 1601 is used to identify which information is acquired at the time of update. The article ID 1602 is for identifying each acquired information. The article content 1603 is for registering the content of the acquired information. An information source (URL) 1604 indicates an information source from which each information is acquired. An acquisition time 1605 indicates the acquisition time of each piece of information. The status 1606 indicates whether each piece of information has been processed by the data analysis function 202. The user ID 1607 is for identifying a user who uses the information of the record.

  FIG. 17 is a flowchart illustrating an example of a processing procedure of the data acquisition function 201 according to the present embodiment.

  In accordance with the following processing, the data acquisition function 201 receives data such as news articles from information sources with a certain degree of importance or more periodically (for example, every 3 hours) or in response to a request from the user (model manager) 111. get. In addition, a search on the Internet is performed using keywords with a certain degree of importance or more, and information (articles and sentences) is acquired. An ID is issued for each acquired article and registered in the acquisition information DB 203.

  When the data acquisition function 201 is activated, in S1701, an update ID for the current update is issued in order to identify the update.

  In S1702, the data acquisition function 201 determines that the importance 1505 in the information source management table 1500 of the acquisition / analysis management DB 204 (FIG. 15) is greater than or equal to a certain value (for example, 30 or more), or more than a certain time from the previous acquisition time 1504. Records of progress (for example, three months or more have elapsed) are extracted.

  In S1703, the data acquisition function 201 acquires information (article) from the Internet and the local network based on the information source (URL) 1502 for the record extracted in S1702. The data acquisition function 201 updates the previous acquisition time 1504 of the record in the information source management table 1500 to the current time for the information source (URL) for which information has been acquired.

  In S1704, the data acquisition function 201 issues an article ID for identification for each piece of information (article) acquired in S1703. The update ID issued in S1701, the content of the acquired information (article content), and the acquisition source. When managing the information source (URL), the acquisition time, and the update timing and update contents for each user, it is registered in the acquisition information table 1600 (FIG. 16) together with the user ID. Here, “unprocessed” is registered in the status 1606 of the acquisition information table 1600.

  In step S <b> 1705, the data acquisition function 201 extracts records whose importance 1514 is greater than or equal to a certain value (for example, 30 or more) from the search management table 1510 of the acquisition / analysis management DB 204.

  In S1706, the data acquisition function 201 searches the Internet and the local network for the record extracted in S1705 on the basis of the keyword 1512, and acquires information (article).

  In S1707, the data acquisition function 201 issues an article ID for identification for each information (article) acquired in S1706, indicates the update ID issued in S1701, the content of the acquired information (article content), and the acquisition source. When managing the information source (URL), acquisition time, update timing, and update contents for each user, it is registered in the acquisition information table 1600 together with the user ID. Here, “unprocessed” is registered in the status 1606 of the acquisition information table 1600.

  In S1708, the data acquisition function 201 determines whether it is an update timing (for example, whether one month has passed since the previous update (update ID issuance)). If it is the update timing, the process is terminated, and if it is not the update timing, S1702 and subsequent steps are executed after a predetermined time has elapsed (for example, after 3 hours). The update timing and the timing of returning to S1702 may be set by the user (model administrator) 111.

  For example, immediately after a series of processes of the causal relationship model update sequence is completed, when the data acquisition function 201 is activated and the update timing is set to one month and the acquisition time is set to three hours, the latest information acquisition is performed every three hours. The causal relationship model update process is performed every month (that is, the processes of S1702 to S1708 are performed 240 times during the update).

  FIG. 18 is a diagram showing an example of (a) analysis result management DB 205 and (b) occurrence event management DB 206 according to the present embodiment.

  The analysis result management DB 205 has an analysis result management table 1800 and a co-occurrence result management table 1810.

  The analysis result management table 1800 includes an update ID 1801, an article ID 1802, a noun 1803, and a subject predicate set 1804.

  The update ID 1801 is for identifying which update is the result of analysis. The article ID 1802 is for identifying each piece of information that is the source of the analysis. The noun 1803 is for registering a noun extracted from each piece of information (article). The subject predicate set 1804 is for registering a subject and predicate set extracted from each piece of information (article).

  The co-occurrence result management table 1810 includes an update ID 1811, a subject predicate set (1) 1812, a subject predicate set (2) 1813, and a co-occurrence count 1814.

The update ID 1811 is used to identify which update is the analysis result.
The subject predicate set (1) 1812 and the subject predicate set (2) 1813 are for registering a subject predicate set having a co-occurrence relationship (appearing in the same article). The co-occurrence count 1814 is for registering the co-occurrence count.

  The occurrence event management DB 206 has an occurrence event management table 1820.

  The occurrence event management table 1820 includes an article ID 1821, a subject predicate set 1822, and an acquisition time 1823.

The article ID 1821 is for identifying original information (article) in which the subject predicate set is described. The subject predicate set 1822 is for registering a subject and a set of predicates (occurring events) extracted from each piece of information (article). The acquisition time 1823 indicates the time when the original information (article) in which the subject predicate set was described was acquired.

  FIG. 19 is a flowchart illustrating an example of a processing procedure of the data analysis function 202 according to the present embodiment.

  The data analysis function 202 performs noun extraction and subject predicate extraction by natural language analysis and co-occurrence number extraction by co-occurrence analysis for the acquisition information (articles and sentences) registered in the acquisition information DB 203 (FIG. 16) according to the following processing. And so on. Further, the subject predicate extraction result is registered in the occurrence event management DB 206 (FIG. 18) as an event currently occurring.

  When the data analysis function 202 is activated, in S1901, the acquisition information table 1600 is searched, and one record whose status 1606 is “unprocessed” is extracted.

  In S1902, the data analysis function 202 acquires the article content 1603 for the record extracted in S1901.

  In S1903, the data analysis function 202 extracts a noun from the article content acquired in S1902 by natural language analysis.

  In S1904, the data analysis function 202 extracts a set of subject and predicate (for example, “Country A” “protested”) by natural language analysis for the article content acquired in S1902.

  In step S1905, the data analysis function 202 analyzes the noun and subject predicate sets extracted in steps S1903 and S1904 together with the article ID of the extracted original information (article) and the update ID indicating the current update. 18). Also, in the acquisition information table 1600, the status of the record extracted in S1901 is updated to “processed”. In addition, the registered subject predicate set is registered in the occurrence event management table 1820 of the occurrence event management DB 206 together with the article ID of the extracted original information (article) and the acquisition time as an event currently occurring.

  In step S <b> 1906, the data analysis function 202 refers to the acquisition information table 1600 and determines whether there are any records whose status 1606 is “unprocessed”. The data analysis function 202 executes the processing after S1901 if it remains, and executes the processing after S1907 if it does not remain.

  In S1907, the co-occurrence analysis is performed on all the article contents acquired in S1902, and the number of times of simultaneous appearance (number of co-occurrence) is extracted for all the subject predicate sets extracted in S1904.

  In S1908, the data analysis function 202 uses the co-occurrence information extracted in S1907 (two or more subject predicate sets (for example, (B country, military invasion) and (A country, protest)) and the number of co-occurrence). It registers in the occurrence result management table 1810. For example, the co-occurrence information to be registered may be narrowed down, for example, by registering only a set of subject predicates in which the number of co-occurrence is a certain number or more (eg, 5 times or more).

  FIG. 20 is a diagram illustrating an example of the temporary update model DB 216 according to the present embodiment.

  The temporary update model DB 216 includes an update target data table 2000 and a temporary update model data table 2010.

  The update target data table 2000 includes a temporary node ID 2001, a node name 2002, a subject 2003, an update status 2004, an article ID 2005, a link destination temporary node 2006, and a degree of relationship 2007.

  The temporary node ID 2001 is for identifying an event (node) to be updated this time. The node name 2002 indicates the content of the event. The subject 2003 indicates the subject (subject) of the event. The update status 2004 indicates whether or not to update the event (node) of the record. The article ID 2005 is for identifying each information that is the source of the event (node) of the record. The link destination temporary node 2006 is for registering a temporary node ID of a node related to the node of the record (a node that may occur next). The relationship degree 2007 indicates the strength of the relationship (high possibility of occurring next). Thereafter, when there are a plurality of related nodes, contents equivalent to the link destination temporary node 2006 and the relationship degree 2007 are registered in the link destination temporary node (2) 2008 and later.

  The temporary update model data table 2010 includes a node ID 2011, a node name 2012, a subject 2013, an update pattern 2014, a link destination node 2015, and a relationship degree 2016.

  The node ID 2011 is for identifying an event (node). The node name 2012 indicates the content of the event. The subject 2013 indicates the subject (subject) of the event. The update pattern 2014 indicates an update pattern of events (nodes) of the record (for example, a relationship between events (internodes) that is not registered in the existing causal relationship model is newly added). The link destination node 2015 is for registering the node ID of a node related to the node of the record (a node that may occur next). The relation degree 2016 indicates the strength of the relation (high possibility of occurring next). Thereafter, when there are a plurality of related nodes, the same contents as the link destination node 2015 and the relation degree 2016 are registered in the link destination node (2) 2017 and thereafter.

  FIG. 21 is a flowchart illustrating an example of a processing procedure of the update information generation function according to the present embodiment.

  The update information generation function 212 extracts a set of subjects and nodes (subject predicate set) obtained from the current information source and their relationship from the analysis result management DB 205 (FIG. 18) according to the following processing (information (article). (Extracted from the order in which they appear, the time relationship between articles, the number of co-occurrence in all articles), and the data to be updated (update target data table 2000) is generated, and the existing causal relationship model and update target Temporary update model data (temporary update model data table 2010) is generated from the data.

  When the update information generation function 212 is activated, the subject predicate set 1804 and the article ID 1802 of each record are extracted from the analysis result management table 1800 in S2101. Here, the update ID of the record whose update status 2217 of the update content management table 2210 (FIG. 22) described later is “pending” and the record of the analysis result management table 1800 corresponding to the article ID are also extracted as the analysis target. You may do it.

  In S2102, the update information generation function 212 issues temporary node IDs with the subject predicate set extracted in S2101 as the update target node (subject and node set).

  In S2103, the update information generation function 212 extracts the relationship for the subject predicate set having the same article ID in the analysis result management table 1800 for the update target node set in S2102 (for example, after the context in the article, The subject predicate set coming out of (1) is set as the link destination of the subject predicate set coming out earlier), and the temporary node ID and the link destination temporary node ID are set. For example, in the record 1805 of the article ID “1”, when “Country A, protest” comes after “Country B, military invasion”, “Country A, protest” is changed to “Country B, military Link to “Invade”.

  In S <b> 2104, the update information generation function 212 extracts a record (related record) including a certain number of the same nouns from the nouns 1803 of each record in the analysis result management table 1800. For example, the record 1805 with the article ID “1” and the record 1806 with the article ID “2” have three or more identical nouns (Z territorial water, country A, country B), and therefore are determined to be related.

  In S2105, the update information generation function 212 extracts the relationship between the subject predicate sets of the related records determined in S2104 (from the article ID of each record, referring to the acquisition time 1605 of the acquisition information table 1600, before and after the time) The relationship is extracted), and a temporary node ID and a link destination temporary node ID are set. For example, “Country C, mediate in” record 1806 of article ID “2” is the link destination of “Country A, protest” in record 1805 of article ID “1”.

  In S2106, the update information generation function 212 extracts the strength of the relationship between the subject predicate sets from the co-occurrence result management table 1810 (the relationship increases as the number of co-occurrence increases), and the temporary node ID and the link destination temporary The degree of relation of the node ID is set (for example, the number of co-occurrence times = degree of relation).

  In S2107, the update information generation function 212 updates the subject and node set (subject predicate set) extracted in S2102 to S2106, the temporary node ID, the relationship (link destination temporary node ID, degree of relationship), and article ID. Register in the data table 2000.

  In S <b> 2108, the update information generation function 212 integrates the duplicate records (the subject and the node name are the same) into one in the update target data table 2000 (if there are different link destination nodes, link (It joins after the previous node (2)). For example, since the nodes extracted from the article IDs “1” and “3” in the analysis result management table 1800 are duplicated, the nodes to be updated are combined into one (delete one) and are updated as records 2021 and 2022. Registered in the table 2000. Here, a dictionary file for determining duplicate vocabulary (a file in which rules for inferring that the vocabulary is the same) is prepared. For example, it is determined that military invasion and territorial invasion are the same, and By a similar process, the record of the node name “Ryokai invasion” may be integrated into the record of the node name “Military invasion”.

  In S <b> 2109, the update information generation function 212 sets the update status to “pending” for a record that does not have a link destination node or is not a link destination node of any record in the update target data table 2000. As a result, a node that is not connected to any node (no causal relationship) is a meaningless node that does not affect the prediction result, so it is excluded from the update target and prevents the model size after updating from becoming too large. .

In S2110, the update information generation function 212 sets the update status of the record whose update status 2004 is not “pending” to “update” for the update target data table 2000. Further, the update information generation function 212 performs the following processing in comparison with the current causal relationship model table 400 (FIG. 4, hereinafter, existing model), and registers temporary update model data.
(1) First, the contents of all records excluding the model ID 401 of the existing model are registered in the temporary update model data table 2010 as they are. For the update pattern 2014, “0” (no update) is registered.
(2) Of the set of subject and node name in the update target data table 2000, those that do not exist in the existing model issue a new node ID and register it in the temporary update model data table 2010. In this newly registered record, if the link destination node (subject, node name) does not exist in the existing model (new node ID is issued), the link destination node and the degree of relation are also added. Then, “1” is registered in the update pattern 2014. That is, if both the newly registered record and its link destination node (its main body, node name) do not exist in the existing model, “1” is registered in the update pattern 2014. On the other hand, the newly registered record does not exist in the existing model, but the link destination node (the subject, the node name) exists in the existing model, as the link destination node, the node ID of the existing model, The degree of relation extracted this time is added, and “2” is registered in the update pattern 2014. Further, the newly registered record does not have a link destination node, but the record is a link destination node of an existing model or another record of the update target data table 2000 (node name, subject only temporary update model) For those registered in the data table 2010, “3” is registered in the update pattern 2014.
(3) Of the set of subject and node name of the update target data table 2000, it also exists in the existing model (registered in the temporary update model data table 2010 in (1) above) and the link destination node (subject) , Node names) are the same (also exist in the existing model), the degree of relationship of the record in the provisional update model data table 2010 is updated (for example, the degree of relationship is +10), and the update pattern 2014 indicates “ 4 ”is registered. Of the set of subject and node name in the update target data table 2000, the existing model exists in the existing model, but the link destination node (the subject, node name) does not exist in the existing model (a new node ID is issued). ), The link destination node and the degree of relation are added, and “5” is registered in the update pattern 2014.

  FIG. 22 is a diagram illustrating an example of the model update management DB 223 according to the present embodiment.

  The model update management DB 223 has an update effectiveness management table 2200 and an update content management table 2210.

  The update validity management table 2200 includes an update ID 2201, a model ID 2202, an update time 2203, an update validity 2204, and a user ID 2205.

  The update ID 2201 is for identifying which update is the result of the evaluation of effectiveness. The model ID 2202 is for identifying the updated model. The update time 2203 indicates the time when the model is updated. The update effectiveness 2204 is for registering the effectiveness evaluation result. A user ID 2205 is for identifying the owner of the model.

  The update content management table 2210 includes an update ID 2211, a node ID 2212, a node name 2213, a subject 2214, an update pattern 2215, an article ID 2216, a link destination node 2217, and a degree of relationship 2218.

  The update ID 2211 is for identifying at which update time the update was performed. The node ID 2212 is for identifying a node. The node name 2213 indicates the content of the event. The subject 2214 indicates the subject (subject) of the event. An update pattern 2215 indicates an update pattern of the event (node) of the record. This is for identifying the article ID 2216 and each information that is the origin of the event (node) of the record. The update status 2217 indicates whether or not the event (node) of the record has been updated. The link destination node 2218 is for registering the node ID of a node related to the node of the record (a node that may occur next). The relation degree 2219 indicates the strength of the relation (high possibility of occurring next). Thereafter, when there are a plurality of related nodes, contents equivalent to the link destination node 2218 and the relation degree 2219 are registered in the link destination node (2) 2220 and the subsequent pages.

  FIG. 23 is a flowchart illustrating an example of a processing procedure of the model update evaluation function 213 and the model registration / update function 231 according to the present embodiment.

  The model update evaluation function 213 calculates the update validity for the current update content according to the following process.

  When the model update evaluation function 213 is activated, in S2301, the update pattern 2014 in the temporary update model data table 2010 of the temporary update model DB 216 (FIG. 20) described above is searched, and the record whose update pattern is other than “0” (no update). To extract.

  In S2302, the model update evaluation function 213 checks whether or not there is a record extracted in S2301, and if there is, executes the process after S2303, and if not, executes S2307 and after.

  In S2303, the model update evaluation function 213 acquires an interest value based on the node ID for each record extracted in S2301 from the interest value management table 900 of the interest event management DB 217 (FIG. 9).

  In S2304, the model update evaluation function 213 calculates the sum of the interest values of each record acquired in S2303 to calculate the update validity. For example, the sum of interest values × 0.1 is set as the update effectiveness.

  In S2305, the model update evaluation function 213 acquires an update pattern for each record extracted in S2301, and calculates the number of records corresponding to each of the update patterns 1 to 5.

  In S <b> 2306, the model update evaluation function 213 calculates the update effectiveness by weighting each update pattern based on the number calculated in S <b> 2305. For example, (number of update patterns “2” × 5 × 0.1) + (number of update patterns “5” × 3 × 0.1) + (number of update patterns “1” × 2 × 0.1) + The number of update patterns “3” × 1 × 0.1) + (the number of update patterns “4” × 0.5 × 0.1) is set as the update effectiveness. As a result, when a new causal relationship is added, it is possible to make an evaluation based on how the update is performed, such as high update effectiveness.

  In S2307, the model update evaluation function 213 adds the update effectiveness calculated in S2304 and S2306 to calculate the update effectiveness for the current update. If no record is extracted in S2301, the update validity is set to “0”. Also, the current update ID and the calculated update validity are registered in the update validity management table 2200 of the model update management DB 223 (FIG. 22).

  Next, the model registration / update function 231 updates the causal relationship model according to the following processing, based on the update effectiveness calculated by the model update evaluation function 213, when the update effectiveness is a predetermined value or more.

  In S2308, the model registration / update function 231 checks whether or not the update validity calculated in S2307 is equal to or greater than a certain value, and if it is equal to or greater than a certain value (for example, 30 or more), executes S2309 and subsequent steps. In this case, S2310 and subsequent steps are executed.

  In S2309, the model registration / update function 231 issues a new model ID, and stores the data registered in the causal relationship model table 400 of the causal relationship model DB 233 (FIG. 4) in the past model management DB 234 as a past model. Then, the data registered in the temporary update model data table 2010 of the temporary update model DB 216 (FIG. 20) is registered in the causal relationship model table 400 of the causal relationship model DB 233 (updates the causal relationship model). Also, the newly issued model ID is registered in the causal relationship model management table 410 together with the current time (update time) (the model name is arbitrarily created by the system or registered according to a naming rule defined by the user 111).

  In S2310, the model registration / update function 231 registers the model ID issued in S2309 and the update time in the record corresponding to the current update ID in the update validity management table 2200 of the model update management DB 223 (FIG. 22). . If S2309 is not executed, “NULL” is registered in the model ID 2202, and the current time is registered in the update time 2203.

  FIG. 24 is a flowchart illustrating an example of processing procedures of the update log registration function 222 and the update log analysis function 221 according to the present embodiment.

  The update log registration function 222 registers the current update content registered in the temporary update model DB 216 (FIG. 20) in the model update management DB 223 (FIG. 22) according to the following processing.

  When the update log registration function 222 is activated, records whose update pattern is other than 0 (no update) are extracted from the temporary update model data table 2010 in S2401. Further, the article ID that is the source of the update of the record is extracted from the update target data table 2000.

  In S2402, the update log registration function 222 checks whether there is a record extracted in S2401, and if there is, executes S2403 and subsequent steps, and if not, executes S2404 and subsequent steps.

  In S2403, the record extracted in S2401 is added to the update content management table 2210 together with the article ID and the current update ID.

  In step S <b> 2404, the update log registration function 222 extracts records whose update status is “pending” from the update target data table 2000.

  In S2405, the update log registration function 222 checks whether there is a record extracted in S2404, and if there is, executes S2406 and subsequent steps, and if not, executes S2407 and subsequent steps.

  In S2406, the update log registration function 222 adds the record extracted in S1204 to the update content management table 2210 together with the article ID of the record and the current update ID.

  In S2407, the update log registration function 222 confirms whether or not there is a record added to the update content management table 2210 in S2403 and S2406, and if there is, executes S2408 and subsequent steps, and if not, performs S2411 and subsequent steps. Execute.

  Next, the update log analysis function 221 extracts the importance of the information source and the information to be searched from the data related to the update contents and events that are of interest to the user according to the following processing, and obtains / analyzes management DB 204 (FIG. 15). ). In addition, the update log analysis function 221 extracts and deletes unnecessary nodes in the causal relationship model DB 233 (FIG. 4).

  In S2408, the update log analysis function 221 extracts records in which the update status of the update content management table 2210 (FIG. 22) is “update” and the update pattern is “1” or “5”. Based on the article ID of each extracted record, the importance of the information source corresponding to the article ID is incremented by one from the acquisition information table 1600 (FIG. 16) and the information source management table 1500 (FIG. 15).

  In S2409, the update log analysis function 221 determines that the record ID (record added to the update content management table 2210) extracted in S2403 is registered in the interest value management table 900 (FIG. 9). Based on the article ID, the importance level of the information source corresponding to the article ID is counted up by +10 from the acquired information table 1600 and the information source management table 1500.

  In S2410, the update log analysis function 221 newly adds the node name of the record as a keyword to the search management table 1510 (FIG. 15) for the record whose update status in the update content management table 2210 is “pending”. (If a record with the same node name is already registered, the importance of the record is incremented by one). For the record registered in the causal relationship model table 400, the node name of the record is newly added as a keyword to the search management table 1510 (the same node name is already registered in the record of the search management table 1510). In this case, the importance of the record is incremented by +1). Further, the importance of the record in the search management table 1510 that is the same as the node name of the record newly added / updated to the interest value management table 900 (FIG. 9) (record updated from the previous update time to the current update). Increase by 10.

  In S2411, the update log analysis function 221 has not updated any of the update time 405 and the relationship update time 408 for a certain period (for example, six months or more) for each record of the causal relationship model table 400, and the node ID of the record In the subject predicate set 1804 of the record having the current update ID in the analysis result management table 1800, the relation update time 408 of the record registered in the link destination node 406 has not been updated for a certain period (for example, half a year or more). If there is no match with the node name 403 and the subject 404 of the record, the record is deleted from the causal relationship model table 400, and the content of the record is stored in the update content management table 2210 with the current update ID, Register with update status “Deleted”.

  FIG. 25 is a diagram illustrating an example of a causal relationship model update sequence in the case where a user according to the present embodiment is present.

  In the causal relationship model update sequence when the user is involved, each function of the causal relationship model update sequence of FIG. 14 is activated by information and instructions from the user (model manager) 111 input via the model update screen 263. Then, obtain data such as news articles from information sources, perform data analysis such as model update events (nodes) and relationship extraction between the nodes, generate update information, and the effectiveness of the update information To evaluate. Next, along with the effectiveness, the reaction prediction results using the causal relationship model before and after the update and the causal relationship model before and after the update are presented to the user 111 via the model update screen 263, and the user corrects the update contents and causes and effects. A relation model update execution instruction is issued, and the causal relation model is updated by the model registration / update function 231 in the same procedure as the causal relation model update sequence in FIG.

  The model update screen 263 acquires the interest value of each event (node) from the temporary update model DB 216, the temporary update model data (causal relation model after update), and the interest event management DB 217. Further, the model acquisition function 232 is used to acquire the causal relationship model data (causal relationship model before update) from the causal relationship model DB 233 and present it to the user 111.

  When the user 111 corrects the presented temporary update model data (relationship between events (nodes), deletion of events (nodes), change of event (node) names, etc.), the update information correction function 215 The correction content is acquired, and the items of the corresponding record among the records registered in the temporary update model DB 216 are corrected.

  The reaction prediction generation function 241 acquires pre-update and post-update causal relationship model data from the causal relationship model DB 233 and the temporary update model DB 216, and performs the process before and after the update by the same process as the process described with reference to FIG. Reaction prediction result by simulation using the model of the cause-and-effect relationship model and the temporary update model) is generated and registered in the reaction prediction result DB 243.

  The prediction result evaluation function 214 acquires a reaction prediction result using the generated models before and after the update (existing causal relationship model and temporary update model), and outputs the result to the model update screen 263.

  When the user 111 corrects the reaction prediction result (prediction result using the temporary update model) output to the model update screen 263, the reaction prediction adjustment function 242 acquires the correction content, executes the simulation, The relationship between events (between nodes) registered in the temporary update model DB 216 is corrected so that the correction content becomes a prediction result.

  The model registration / update function 231 updates the causal relationship model based on the provisional update model DB 216 modified by the user 111 by the same process as that described with reference to FIG.

  FIG. 26 is a diagram showing an example of the model update screen 263 according to the present embodiment.

  The model update screen 263 presents information registered in the acquired information DB 203, inputs information from the user, presents analysis results registered in the analysis result management DB 205, and is registered in the causal relationship model DB 233 and the temporary update model DB 216. It provides an interface for presenting a causal relationship model and a correction input from the user, presenting a prediction result registered in the reaction prediction result DB 243, and a correction input from the user.

  The model update screen 263 includes a button 2601, a data selection unit 2602, a manual input button 2603, an automatic collection button 2604, a data collection result display unit 2605, an analysis execution button 2606, a data analysis result display unit 2607, Temporary update execution button 2608, update result display unit 2609, pre-update causal relationship model display unit 2610, post-update causal relationship model display unit 2611, update effectiveness display unit 2612, and return to uncorrected button 2613 A correction reflection button 2614, an update execution button 2615, a prediction result display unit 2616, a prediction result display unit 2617 before update, a prediction result display unit 2618 after update, and a prediction execution button 2619. .

  A button 2601 is a button for returning to the menu for returning to the menu screen. The data selection unit 2602 is a button for registering data used for model update. A manual input button 2603 is a button for registering data designated by the data selection unit 2602. An automatic collection button 2604 is a button for automatically collecting data by this system.

  When the user (model manager) 111 presses the data selection unit 2602, a list of data used for model update (a list of files stored in a specific folder in advance) is displayed. When the user (model administrator) 111 selects data and presses the manual input button 2603, the selected data is registered in the acquisition information DB 203 as data used for model update, and the content of the acquisition information DB 203 is the data. It is displayed on the collection result display unit 2605. When the automatic collection button 2604 is pressed, information is automatically collected by the data acquisition function 201 by the same process as in FIG. 17, and data registered in the acquisition information DB 203 is displayed on the data collection result display unit 2605.

  When the user 111 presses the analysis execution button 2606, the data analysis function 202 performs analysis by the same processing as in FIG. 19, and the data registered in the analysis result management DB 205 is displayed on the data analysis result display unit 2607. .

  When the user 111 presses the temporary update execution button 2608, the update information generation function 212 creates temporary update model data by the same processing as in FIG. 21, and the content of the current causal relationship model DB 233 is the causal relationship before the update. The contents of the temporary update model DB 216 are displayed on the model display unit 2610 on the updated causal relationship model display unit 2611. Also, the update effectiveness calculated by the same processing as in FIG. 23 is displayed on the update effectiveness display unit 2612 by the model update evaluation function 213.

  Here, the user 111 corrects the temporary update model data displayed in the updated causal relationship model display unit 2611 (relationship between events (nodes), deletion of events (nodes), and event (node) names. When the update reflection button 2614 is pressed, the update information correction function 215 corrects the temporary update model data registered in the temporary update model DB 216, and the content after correction is the causal relationship after the update. It is displayed on the model display unit 2611. When a return button 2613 before correction is pressed, the state after the temporary update execution button 2608 is pressed can be restored. When the update execution button 2615 is pressed, the causal relationship model is updated by the model registration / update function 231 based on the temporary update model DB 216 corrected by the user 111 by the process equivalent to the process described in FIG. .

  When the user presses the prediction execution button 2619, the reaction prediction generation function 241 acquires the causal relationship model data before and after the update from the causal relationship model DB 233 and the temporary update model DB 216, and is equivalent to the processing described in FIG. Through this process, a reaction prediction result is generated by simulation using models before and after the update (existing causal relationship model and temporary update model). A prediction result using the current causal relationship model DB 233 is displayed on the prediction result display unit 2617 before update, and a prediction result using the temporary update model DB 216 is displayed on the prediction result display unit 2618 after update. Here, when the user 111 corrects the reaction prediction result (prediction result using the temporary update model) displayed on the updated prediction result display unit 2618, the reaction prediction adjustment function 242 executes a simulation, The relationship between events (between nodes) registered in the temporary update model DB 216 is corrected so that the correction content becomes a prediction result. The corrected content is displayed on the updated causal relationship model display unit 2611.

  According to the decision support system 101 described above, the causal relationship model updating unit 103 generates temporary update model data for updating the causal relationship model based on the causal relationship model and the analysis result by the data analysis function 202. The update information generation function 202 and the model update evaluation function 213 that evaluates the validity of the update based on the temporary update model data. The causal relationship model management unit 105 has an evaluation result by the model update evaluation function 213 that exceeds a certain level. In this case, a model registration / update function 231 for updating the causal relationship model with temporary update model data is provided.

  According to such a configuration, when updating the model so as to correspond to the actual situation that changes sequentially, the causal relationship model that is meaningful to the user is updated. Therefore, the causal relationship model of the decision support system 101 Quality deterioration can be prevented.

  The event update management database 217 further stores an event of interest to the user. The model update evaluation function 213 evaluates the effectiveness of the update based on the temporary update model data and the events stored in the event management DB 217. To do.

  According to such a configuration, since the effectiveness of the update is evaluated based on an event that is of interest to the user, it is possible to prevent a causal relationship model that is meaningless to the user from being updated, so that decision support is possible. It is possible to prevent deterioration in quality and enlargement of the causal relationship model of the system 101.

  In addition, the reaction prediction unit 106 predicts a plurality of events that occur following a certain event when a certain event occurs based on the causal relationship model, displays the prediction result on the terminal, and updates the causal relationship model. The unit 103 has an interest event registration function 211 that acquires an event of interest to the user input to the terminal by the user and stores it in the interest event management DB 217.

  According to such a configuration, an event of interest to the user input to the prediction result is registered, and the effectiveness of the update is evaluated based on the registered event. The update can be prevented, and the deterioration and enlargement of the causal relationship model of the decision support system 101 can be prevented.

  The update information generation function 212 displays the updated causal relationship model based on the temporary update model data on the terminal, and the causal relationship model update unit 103 acquires a correction to the updated causal relationship model input to the terminal by the user. And an update information correction function 215 for correcting the temporary update model data.

  According to such a configuration, since the causal relationship model desired by the user is created, a causal relationship model that is meaningful to the user can be provided. Moreover, since addition to the causal relationship model which is meaningless for the user is suppressed, the enlargement of the causal relationship model can be suppressed.

  The model update evaluation function 213 causes the terminal to display an evaluation result of the validity of the update. When the model registration / update function 231 receives an instruction to update the causal relationship model input to the terminal by the user, the temporary update model data To update the causal relationship model.

  According to such a configuration, a causal relationship model that is meaningful to the user can be provided. Moreover, since addition to the causal relationship model which is meaningless for the user is suppressed, the enlargement of the causal relationship model can be suppressed.

  In addition, the reaction prediction unit 106 predicts, by simulation, a plurality of events that occur following a certain event when a certain event occurs, based on the updated causal relationship model based on the causal relationship model and the temporary update model data. Then, the reaction prediction generation function 241 for displaying the prediction result on the terminal, and the correction for the prediction result based on the updated causal relationship model input by the user input to the terminal that displays the prediction result based on the updated causal relationship model are acquired. And a reaction prediction adjustment function 242 for correcting the temporary update model data.

  According to such a configuration, since the causal relationship model desired by the user is created, a causal relationship model that is meaningful to the user can be provided. Moreover, since addition to the causal relationship model which is meaningless for the user is suppressed, the enlargement of the causal relationship model can be suppressed.

  If the same event is included in the update target data table 2000, the update information generation function 212 deletes one of the data.

  With this configuration, the causal relationship model of the decision support system 101 can be prevented from becoming enormous.

  In addition, when an event updated by the temporary update model data among a plurality of events included in the updated causal relationship model by the model registration / update function 231 is stored in the event-of-interest management DB 217, an updated event The update evaluation management unit 104 increases the importance corresponding to the data related to the information source or search condition used to acquire the information, and the data acquisition function 201 acquires information about the event based on the importance.

  According to such a configuration, since the importance of the information source or the like from which the event of interest to the user is acquired is increased, it is possible to narrow down the information source or the like. Then, by acquiring information from an information source or the like having a certain degree of importance or higher, a causal relationship model that is meaningful to the user can be updated, and deterioration in update performance can be prevented.

  In addition, the model registration / update function 231 uses the information source or search condition used to acquire the updated event for the event updated by the temporary update model data among a plurality of events included in the updated causal relationship model. The update evaluation management unit 104 increases the importance corresponding to the data related to the data, and the data acquisition function 201 acquires information related to the event based on the importance.

  According to such a configuration, it is possible to narrow down information sources and the like. Then, by acquiring information from an information source or the like having a certain degree of importance or higher, a causal relationship model that is meaningful to the user can be updated, and deterioration in update performance can be prevented.

  An update evaluation management unit 104 is provided that deletes, from a causal relationship model, an event in which a causal relationship model event has not been updated for a certain period or more and has not been updated for a certain period in relation to another event.

  With this configuration, the causal relationship model of the decision support system 101 can be prevented from becoming enormous.

  As a result of the analysis by the data analysis function 202, when there is no event that occurs after one event, or when the one event does not occur following the other events, update The information generation function 212 excludes the one event from events that update the causal relationship model. That is, for the update target data table 2000, the update status is set to “pending” for a record that does not have a link destination node or is not a link destination node of any record.

  With this configuration, the size of the updated causal relationship model can be prevented.

  In addition, this invention is not limited to an above-described Example, Various modifications are included. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described.

  For example, for the update target data table 2000, the update information generation function 212 sets the update status to “pending” for a record that does not have a link destination node or is not a link destination node of any record, Although excluded from the update target, in the temporary update model data table 2010, two records whose update patterns 2014 have a relationship of “1” and “3” may be excluded from the update target. Since such a record is a record that does not significantly affect the prediction result, it can be excluded from the update target, and the size of the updated causal relationship model can be prevented.

  In addition, each configuration, function, processing unit, processing unit, and the like of the above-described embodiment may be realized by hardware by designing a part or all of them with, for example, an integrated circuit. Each of the above-described configurations, functions, and the like may be realized by software by interpreting and executing a program that realizes each function by the processor. Information such as programs, tables, and files for realizing each function can be stored in a recording device such as a memory, a hard disk, or an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

  Further, the control lines and information lines are those that are considered necessary for the explanation, and not all the control lines and information lines on the product are necessarily shown. Actually, it may be considered that almost all the components are connected to each other.

DESCRIPTION OF SYMBOLS 101 Decision support system 102 Data collection / analysis part 103 Causal relationship model update part 104 Update evaluation management part 105 Causal relation model management part 106 Reaction prediction part 201 Data acquisition function 202 Data analysis function 204 Acquisition / analysis management DB
211 Interest Event Registration Function 212 Update Information Generation Function 213 Model Update Evaluation Function 215 Update Information Correction Function 217 Interest Event Management DB
231 Model registration / update function 241 Reaction prediction generation function 242 Reaction prediction adjustment function

Claims (12)

A decision support system comprising a causal relationship model management unit, a data collection / analysis unit, a causal relationship model update unit, and a causal relationship model management unit,
The causal relationship model management unit stores, as a causal relationship model, a plurality of events that occur in society or nature, and the relationship of occurrence between events,
The data collection / analysis unit
A data acquisition function for acquiring information about the event;
A data analysis function for analyzing information about the acquired event,
The causal relationship model update unit
An update information generation function for generating update data for updating the causal relationship model based on the causal relationship model and the analysis result by the data analysis function;
A model update evaluation function for evaluating the effectiveness of the update by the update data, and
The causal relationship model management unit has a model registration / update function for updating the causal relationship model with the update data when the evaluation result by the model update evaluation function is a certain value or more,
A decision support system characterized by An event storage unit for storing events of interest to the user;
The model update evaluation function evaluates the validity of the update based on the update data and the event stored in the event of interest storage unit,
The decision support system according to claim 1, wherein: Based on the causal relationship model, further includes a reaction prediction unit that predicts a plurality of events that occur following the certain event when a certain event occurs by simulation, and displays a prediction result on the terminal,
The causal relationship model update unit has an interest event registration function for acquiring an event of interest to the user input to the prediction result of the terminal by the user and storing the event in the interest event storage unit;
The decision support system according to claim 2, wherein: The update information generation function displays the updated causal relationship model based on the update data on the terminal,
The causal relationship model update unit has an update information correction function for acquiring corrections to the updated causal relationship model input to the terminal by a user and correcting the update data.
The decision support system according to claim 1 or 2, characterized by the above. The model update evaluation function causes the terminal to display an evaluation result of the effectiveness of the update,
When the model registration / update function acquires an instruction to update the causal relationship model input to the terminal by a user, the causal relationship model is updated with the update data.
The decision support system according to claim 4, wherein: Based on the causal relationship model and the updated causal relationship model based on the update data, a plurality of events that occur following the certain event when a certain event occurs are predicted by simulation, and the prediction result is sent to the terminal. Reaction prediction generation function to be displayed,
Reaction prediction adjustment that acquires corrections to the prediction results based on the updated causal relationship model by a user input to the terminal that displays the prediction results based on the updated causal relationship model, and corrects the updated data Function and
Further comprising a reaction prediction unit having
The decision support system according to claim 1 or 2, characterized by the above. The update information generation function deletes one data when the same event is included in the update data,
The decision support system according to any one of claims 1 to 6, wherein: The data collection / analysis unit stores a plurality of acquisition source data set in advance for the data acquisition function to acquire information on the event and an importance level indicating the importance of each acquisition source data. Having an analysis storage unit,
An event of interest storage for storing events of interest to the user;
When the event updated by the update data among the plurality of events included in the causal relationship model is stored in the event-of-interest storage unit by the model registration / update function, acquisition of the updated event An update evaluation management unit that increases the importance corresponding to the acquisition source data used in
The data acquisition function acquires information on the event based on the importance;
The decision support system according to any one of claims 1 to 7, characterized by: The data collection / analysis unit stores a plurality of acquisition source data set in advance for the data acquisition function to acquire information on the event and an importance level indicating the importance of each acquisition source data. Having an analysis storage unit,
With respect to the event updated by the update data among the plurality of events included in the causal relationship model by the model registration / update function, the model corresponding to the acquisition source data used for acquiring the updated event An update evaluation management unit that increases the importance is further provided,
The data acquisition function acquires information on the event based on the importance;
The decision support system according to any one of claims 1 to 7, characterized by: About the event of the causal relationship model, further comprising an update evaluation management unit that deletes from the causal relationship model an event that has not been updated for a certain period of time and has not been updated for a certain period of time in relation to other events,
10. The decision support system according to any one of claims 1 to 9, wherein: As a result of analysis by the data analysis function, for one event, when there is no event that occurs after the one event, or when the one event does not occur after the other other events, The update information generation function excludes the one event from an event of updating the causal relationship model,
The decision support system according to any one of claims 1 to 10, wherein: Obtain information about events that occur in society or nature,
Analyzing information about the acquired event,
Update data for updating the causal relationship model based on a causal relationship model composed of a plurality of events that occur in society or nature, and the relationship between occurrences of the events, and the analysis result by the data analysis function Produces
Evaluate the effectiveness of the update with the update data,
Updating the causal relationship model with the update data when the evaluation result by the model update evaluation function is a certain value or more;
Decision support method characterized by

Images