JP6733362B2 - Task estimation device, task estimation method, and task estimation program - Google Patents

Description

The present invention relates to a technique for estimating a problem that requires verification.

Explain how to launch a business related to product development and manufacturing. One method of business development is wasteful by rapidly repeating the processes of “building a hypothesis of the product potentially needed by the customer”, “implementing the product” and “correcting the trajectory of the product and business” in the development stage. In addition, we will continue to improve products quickly while minimizing non-value elements, and lead the business to success. In this business development method, first, a person involved in the business (hereinafter referred to as a business operator) extracts a hypothetical problem related to a user such as a customer, verifies the problem, and produces a prototype product that is practically practical ( Minimum Viable Product) to be manufactured and delivered to users as quickly as possible. After that, the business operator reconstructs the problem of the original hypothesis based on the result obtained by verifying the reaction of the user to the prototype product, and corrects the trajectory of the product or business. Business owners need to spend only the minimum amount of time and money on non-essential elements (for example, creating specifications, approval documents, etc.) that do not lead to the success of the business by repeating only the minimum processes necessary to capture the demand of users. Or save waste such as labor. This makes it possible to understand the core issues without overly narrowing the scope of product development.

In order to grasp the true needs of users in such a development method, it is important to generate hypothetical tasks quickly and appropriately and obtain feedback through communication with the users. If it is determined that the hypothetical task is not appropriate, it is necessary to immediately verify the next task.

However, a group (for example, an organization that develops businesses for the elderly, etc.) having a certain common problem, a predetermined business field, or a predetermined industry (hereinafter, these are referred to as “domains” in the present application) have problems. When making a hypothesis, the business operator must comprehensively understand the information of the domain and investigate the information. In addition, the business operator needs to understand future problems of the domain and problems of fields around the domain, and it is difficult to quickly and appropriately establish a hypothesis of the problem. In addition, in the present application, the domain is also described as “information indicating the target of the problem”.

As a technique related to the above, a technique for providing a task for implementing a predetermined life improvement measure and supporting a user's life improvement measure is disclosed (see Patent Document 1).

International Publication No. 2015/125454

In the technology of Patent Document 1, the information processing device is a specific subject corresponding to a problem with respect to a predetermined life improvement measure and another problem for implementing the same life improvement measure and the reason why the predetermined life improvement measure fails. It was necessary to create in advance the data of the task correspondence table that corresponded to those with different actions.

However, the problem to be verified and its surrounding situation in a certain domain change every moment, and therefore it is not possible to sufficiently deal with the change only by creating a correspondence table in advance.

The present invention has been made to solve the above problems. The main object of the present invention is to provide a problem estimation device or the like that covers a wide range and appropriately extracts a large number of problems to be verified.

In order to solve the above problems, the problem estimation device according to the first aspect of the present invention is
Output at least one second task which is a result of specializing the superordinate concept obtained by generalizing the input first task,
Of the output second tasks, an estimation unit that extracts a task that co-occurs with the information indicating the target of the task to which the first task belongs is provided.

The problem estimation method according to the second aspect of the present invention is
Output at least one second task which is a result of specializing the superordinate concept obtained by generalizing the input first task,
Among the output second tasks, extracting a task that co-occurs with information indicating the target of the task to which the first task belongs.

The problem estimation program according to the third aspect of the present invention is
Output at least one second task which is a result of specializing the superordinate concept obtained by generalizing the input first task,
The computer is caused to execute the extraction of the co-occurrence problem from the output second problem and the information indicating the target of the problem to which the first problem belongs.

According to the present invention, it is possible to provide a problem estimation device or the like that covers a wide range and appropriately extracts a large number of problems to be verified.

It is a figure which shows the structural example of the subject estimation apparatus in the 1st Embodiment of this invention. It is a figure which shows the structural example of the data of the pattern and term used for analysis of a causal relationship and an inclusion relationship. It is a figure which shows the structural example of the internal data of a domain keyword storage part. It is a flowchart which shows the operation example of the task estimation apparatus in the 1st Embodiment of this invention. It is a figure which shows the internal data structural example of a relationship storage part. It is a figure which shows the internal data structural example of a relationship storage part. It is a figure which shows the structural example of the subject estimation apparatus in the 2nd Embodiment of this invention. It is a flowchart which shows the operation example of the task estimation apparatus in the 2nd Embodiment of this invention. It is a figure which shows the example of the tree structure in a relationship storage part. It is a figure which shows the structural example of the subject estimation apparatus in the 3rd Embodiment of this invention. It is a flowchart which shows the operation example of the task estimation apparatus in the 3rd Embodiment of this invention. It is a figure which shows the example of the data information in a general information storage part. It is a figure which shows the example of the data information in a general information storage part. It is a figure which shows the internal data structural example of a relationship storage part. It is a figure which shows the structural example of the subject estimation apparatus in the 4th Embodiment of this invention. It is a figure which shows the structural example of the information processing apparatus applicable in embodiment of this invention.

Next, an embodiment of the present invention will be described with reference to the drawings. In the following description of the drawings, the same or similar reference numerals are given to the same or similar parts. However, the drawings schematically show the configuration in the embodiment of the present invention. Furthermore, the embodiment of the present invention described below is an example, and can be appropriately modified within the scope of the same essence.

<First Embodiment>
(Problem estimation device)
As shown in FIG. 1, the task estimation device 100 according to the first embodiment of the present invention has a task estimation unit 1, a priority determination unit 2, a pattern storage unit 3, a general information storage unit 4, and a domain keyword storage unit 5. And a relationship storage unit 6. The task estimation unit 1 includes a higher-rank task search unit 1a, a task expansion unit 1b, and a selection unit 1c. Note that in the present application, task estimation refers to extraction of candidates that can be tasks.

The general information storage unit 4 stores general information including a sentence (a set of character strings) used for extracting a problem to be verified, terms and character strings described in the table. Specifically, general information is a term written in a text sentence of a magazine or a newspaper, a text sentence on a website, or a chart on a website necessary for investigating a trend of a certain domain. When a diagram is described as an image, a text sentence may be extracted using an OCR (Optical character recognition) technique.

As shown in FIG. 2, the pattern storage unit 3 stores a combination of patterns and terms used for analyzing a causal relationship and an inclusion relationship included in general information from which a task to be verified is to be extracted. The method used for analysis is not limited to this. A causal relationship refers to a relationship between two or more things that has a cause and an effect. An inclusive relationship is a relationship in which one set is included in another set.

When the task estimation unit 1 extracts a causal relationship using, for example, the pattern shown in FIG. 2, a sentence corresponding to “XXX” of a general sentence is a sub-task, and “---” is a sub-task including its sub-tasks. Extract as an issue. When the task estimation unit 1 extracts a causal relationship using, for example, the combination shown in FIG. 2, if the words “result” and “become” are included in the text of the general information, “the text is causal” It outputs the extraction result that "represents a relationship."

When the task estimation unit 1 extracts the inclusion relation using, for example, the pattern shown in FIG. 2, the sentence corresponding to “XXX” is a subordinate task, and the sentence corresponding to “---” is a superordinate task including the sentence. To extract. When the inclusion relation is extracted using the combination, the task estimation unit 1 extracts “the sentence expresses the inclusion relation” if the sentences include “for” and “do”. Output the result. In the inclusive relation, the task estimation unit 1 uses similar words (for example, “result” and “effect”, “elimination” and “solved”, etc.) as words used for the combination inside another apparatus or the task estimation apparatus 100. You may search using the dictionary etc. which were equipped for, and apply the searched similar word to the above-mentioned analysis.

The domain keyword storage unit 5 stores keywords related to a certain domain in association with each other. The domain keyword storage unit 5 includes, for example, a keyword table as shown in FIG. In the table, for example, "convenience store" and "newspaper" are stored as the domain names of the domains, and "young and old" and "marketing and articles" are stored as the frequent words corresponding to these domains.

The task estimation unit 1 outputs a hypothetical task to be verified. Specifically, the task estimation unit 1 specializes a superordinate concept which is a result of generalizing a task (first task) input via an input/output interface described later. The task estimation unit 1 outputs at least one task (second task) that is a specialized result, and then, among the output second tasks, outputs the same as the domain to which the first task belongs. Extract the issues that arise. Here, generalization refers to abstracting an existing subordinate concept (corresponding to the first problem here) to search for or create a new superordinate concept (superior problem). Specialization refers to creating a new lower-level concept (lower-level problem) linked to an existing higher-level concept (here, a higher-level problem searched or created). Co-occurrence means that a character string and another character string appear at the same time or a high frequency of appearance in a sentence or term of general information.

The relationship storage unit 6 stores information indicating the relationship between the higher level task and the lower level task, for example, a tree diagram as shown in FIGS. 5 and 6.

The upper-level task search unit 1a extracts at least one of the above-mentioned causal relationship and inclusion relationship from the text of the task included in the general information based on the patterns and combinations stored in the pattern storage unit 3. By this extraction, a higher-ranked task of the task (first task) is searched. In the present embodiment, it is assumed that the high-level assignment searched by the high-level assignment search unit 1 a is known and stored in the relationship storage unit 6.

The task extension unit 1b creates a new lower task by specializing the higher task. Therefore, the task extension unit 1b extends the range of the tasks to be verified by specialization to another lower task (second task) different from the lower task included in the first task as the basis. Specifically, the task expansion unit 1b searches for and outputs one or more other lower-level tasks that have a causal relationship or an inclusion relationship with the higher-level task searched by the higher-level task search unit 1a. This output extends the scope of the task to other subtasks that have the same superordinate task.

Based on the keyword table in the domain keyword storage unit 5, the selection unit 1c analyzes whether or not the task output from the task expansion unit 1b has relevance or affinity with the domain to which the first task belongs. As a result, a problem (co-occurrence problem) having relevance is extracted. Specifically, the selecting unit 1c stores whether a certain domain to which the input task belongs and the individual tasks out of the tasks output from the task expanding unit 1b are linked and stored in the keyword table. And, as a result of the determination, those associated with each other in the keyword table among the tasks are extracted.

The priority determination unit 2 sets the priority for verifying the problems (first and second problems) extracted by the problem estimation unit 1, that is, the order in which the verification should be started. There are various methods for setting the priority, but it is preferable that the user can freely set the priority. As a method of setting the priority, a method of increasing the likelihood that the issue is newer, a result of searching a general search website for the issues, and ascending or descending the number of hits There are a method of acquiring and a method of arranging a plurality of extracted problems in correspondence with the ranking of the search ranking at the time of extraction.

(Operation of the task estimation device)
The operation of the task estimation device 100 will be described with reference to the flowchart shown in FIG.

In step S110, the task estimation unit 1 receives the “task” and the “domain” from another device via an input/output interface described below. Specifically, the accepted “issue” is text information indicating the issue, and the accepted “domain” is text information indicating the domain (domain name shown in FIG. 3) and the like. Hereinafter, a case where "I want to reduce newspaper manufacturing cost" is accepted as a problem and "newspaper" is accepted as a domain will be described.

In step S120, the higher-level task search unit 1a of the task estimation unit 1 generalizes the accepted task (first task) into a higher-level task. Specifically, the higher-rank task search unit 1a extracts at least one of the causal relationship and the inclusion relationship in the first task based on the patterns and combinations stored in the pattern storage unit 3, and the higher-rank task that is the higher task. Search for issues. A specific example will be described with reference to the tree diagram of FIG. 5, which schematically shows the relationship between the higher-level task and the lower-level task, which is stored in the relationship storage unit 6. First, in order to generalize the input first problem "I want to reduce newspaper production cost", the higher-rank problem search unit 1a searches for an existing higher-rank problem corresponding to the first problem. Specifically, the higher-level task search unit 1a, based on the patterns and combinations stored in the pattern storage unit 3, is an existing task that is higher than the input "I want to reduce newspaper production cost", that is, "reduce cost". Search for "taitai" and insert it into the tree diagram of FIG. When a plurality of candidates for higher-ranking tasks are searched, an appropriate higher-ranking task may be extracted based on a common word (for example, “cost”). Note that, as shown in FIG. 5, the domain “newspaper” and the top-level task “I want to make a profit” are inserted in the root of the tree. The top task is a task that is common to all the top tasks.

In step S130, the task expansion unit 1b specializes the higher-level task and creates a new lower-level task. Specifically, the task expanding unit 1b searches for subordinate tasks (a plurality of) that have a causal relationship and an inclusion relationship with the higher level task, and extracts the retrieved lower level task. Specifically, the task expansion unit 1b excludes tasks that should be associated with the lower level of the task “I want to reduce cost” in the tree diagram of FIG. 5 (the task that is the basis of the search “I want to reduce the newspaper manufacturing cost”). ) From the general information storage unit 4. As a result of the search, the task expansion unit 1b stores, in the general information storage unit 4, a task that follows the expression of a causal relationship or an inclusion relationship such as "to do XXXX to reduce the cost" based on the pattern storage unit 3. Extract multiple documents. The extracted issues are, for example, “1. need to reduce sales cost”, “2. need to reduce marketing cost”, “3. need to lower R&D cost”, “4. improve efficiency of newspaper article content creation” Need to do so."

In step S140, the selection unit 1c co-occurs with a keyword related to the domain "newspaper" (or may include a similar domain "article", "paper", etc.) among the tasks extracted from the general information storage unit 4. Select an issue. As the co-occurrence task and the keyword, words stored in the keyword table in the domain keyword storage unit 5 as the domain name and the domain frequent word may be used. For example, the higher-level problem is “I want to reduce cost”, and the problem group extracted by the problem extension unit 1b is “1. Need to reduce sales cost”, “2. Need to reduce marketing cost”, “3. R&D cost”. It is necessary to lower the cost" and "4. It is necessary to improve the efficiency of newspaper article content creation." In this case, the selecting unit 1c must co-occur with the domain, that is, include the domain frequent words "marketing" and "article" corresponding to the domain name "newspaper" in the domain keyword storage unit "2. It is necessary to reduce the marketing cost". ”, “4. Need to streamline newspaper article content creation” is selected as a new issue. The selection unit 1c adds the selected task to the relationship storage unit 6 as a new subordinate task. For example, it is inserted in the tree shown in FIG. The selected subject and subordinate subjects may differ in expression. For example, in FIG. 6, “2. Need to reduce marketing cost” is a sub-problem “I want to reduce sales/marketing cost”, and “4. Need to make newspaper article contents efficient” is a sub-problem “Cost of newspaper article production”. I want to reduce."

In step S150, the priority determination part 2 sets the priority which should be verified about the subject which the selection part 1c extracted. That is, the priority determination unit 2 determines the order in which to tackle each of the subordinate tasks in the tree after the insertion shown in FIG. 6, and outputs it as list data of the tasks with priorities. There are various methods for determining the priority. For example, the priority determination unit 2 searches the general information storage unit 4 for each lower-level problem and extracts the lower-level problem as a problem to be verified in ascending order of the number of search hits. The priority determination unit 2 may extract the tasks to be verified in descending order of the number of search hits in order to obtain a new idea.

According to the problem estimation apparatus 100 of the present embodiment, a large number of problems to be verified can be appropriately generated over a wide range. This is because the task estimation unit 1 expands the basic task based on the higher-level task and extracts other tasks to be verified.

<Second Embodiment>
In the first embodiment of the present invention, the higher-level task search unit 1a of the task estimation apparatus 100 searches for a known higher-level task based on at least one of the causal relationship and the inclusion relationship in the input task. However, the higher-ranked task search unit 1a can analyze the higher-ranked task and newly derive it. Hereinafter, in the second embodiment of the present invention, a task estimation device that newly derives a higher-level task will be described.

(Problem estimation device)
The task estimation apparatus 200 according to the second embodiment of the present invention, as shown in FIG. 7, has a task estimation unit 10, a priority determination unit 2, a pattern storage unit 3, a general information storage unit 4, and a domain keyword storage unit 5. And a relationship storage unit 6. The task estimation unit 10 includes a higher-rank task derivation unit 1d, a task expansion unit 1b, and a selection unit 1c.

The higher order task derivation unit 1d searches the general information storage unit 4 based on the input domain information and task information, and derives a higher order task of the task information (lower order task). Note that the derivation may use a combination of patterns and terms for causal relationship and inclusive relationship analysis stored in the pattern storage unit 3. Others are the same as those in the first embodiment.

(Operation of the task estimation device)
The operation of the task estimation device 200 will be described with reference to the flowchart shown in FIG.

In step S110, the task estimation unit 10 accepts task information and domain information from another device via an input device described later. For example, a case where "I want to reduce the newspaper manufacturing cost" as the task information and "newspaper" as the domain information is accepted will be described below.

In step S121, the higher-level task derivation unit 1d of the task estimation unit 10 searches the general information storage unit 4 based on the input domain and task, and derives the higher-level task of the task (lower level task). The higher-level task deriving unit 1d extracts at least one of the causal relationship and the inclusion relationship in the derived higher-level task based on the patterns and combinations stored in the pattern storage unit 3, and thus the higher-level task suitable for the lower-level task. Derive. For example, it is assumed that the input problem (subordinate problem) is “I want to reduce newspaper manufacturing cost”. In this case, the higher-rank problem deriving unit 1d searches the general information storage unit 4 for a sentence including the lower-rank problem, and extracts the searched sentence based on the patterns and combinations stored in the pattern storage unit 3. For example, when the retrieved sentence is “If the newspaper manufacturing cost is reduced, the cost is reduced as a result”, the higher-rank problem deriving unit 1d determines, based on the causal relationship pattern, “I want to lower the cost”. Is derived.

The higher-level task deriving unit 1d stores the lower-level task and the derived higher-level task in the relationship storage unit 6, for example, inserts them into the tree diagram shown in FIG.

Steps S130 to S160 are the same as those in the first embodiment (FIG. 4).

According to the problem estimation device 200 of the present embodiment, a large number of problems to be verified can be appropriately extracted over a wide range. This is because the task estimation unit 10 expands the base task (lower level task) based on the higher level task and extracts other tasks to be verified. In the present embodiment, the higher level task is further derived from the general information based on the input lower level task, so that the higher level task can be extracted in a more timely manner.

<Third Embodiment>
In the first embodiment of the present invention, the task estimation device 100 estimates sub-tasks other than the input sub-task from the common high-rank tasks using causal relationships and the like. However, it is also possible to estimate parallel higher-level tasks from higher-level tasks. Hereinafter, in the third embodiment of the present invention, a task estimation device that newly derives another higher level task from a higher level task will be described.

(Problem estimation device)
The task estimation apparatus 300 according to the third embodiment of the present invention, as shown in FIG. 10, has a task estimation unit 20, a priority determination unit 2, a pattern storage unit 3, a general information storage unit 4, and a domain keyword storage unit 5. And a relationship storage unit 6. The task estimation unit 20 includes a higher-rank task search unit 1a, a task expansion unit 1b, a selection unit 1c, a higher-rank task expansion unit 1e, and a higher-rank task selection unit 1f.

The higher-rank assignment expansion unit 1e extends the higher-rank assignment searched by the higher-rank assignment search unit 1a, and derives another higher-rank assignment having a parallel relationship (coordinate) with the higher-rank assignment. For example, suppose that "I want to reduce the newspaper manufacturing cost" is input as a subordinate task, and as a result of searching by the superordinate task search unit 1a, "I want to reduce the cost" is output as this superordinate task. At this time, the synonyms of the output higher-level task may be extracted. After that, the higher-level task expansion unit 1e searches for a task that is on the same level as this higher-level task from the sentences stored in the general information storage unit 4 and the description in the table, and then searches for a new higher-level task (for example, " I want to increase"). As a method of determining the description of the same level (parallel relationship), for example, a pattern indicating a parallel relationship such as "A and B" "A and B" "A, B and C" "A, B, and C" Is stored in advance in the higher level task expansion unit 1e, and a sentence that matches the pattern of the parallel relationship is extracted as a higher level task of the same rank.

Based on the keyword table in the domain keyword storage unit 5, the higher-level task selection unit 1f analyzes whether the task extracted by the higher-level task extension unit 1e has relevance or affinity with the domain, and performs analysis. Only select issues that are relevant and relevant. Specifically, it is determined whether a certain domain and each of the extracted tasks are linked and stored in the keyword table.

Others are the same as those in the first embodiment.

(Operation of the task estimation device)
The operation of the task estimation device 300 will be described with reference to the flowchart shown in FIG.

In step S110, the task estimation unit 20 of the task estimation apparatus 300 accepts a task (for example, "want to reduce newspaper manufacturing cost") and a domain (for example, "newspaper").

In step S120, the higher-level task search unit 1a of the task estimation unit 20 extracts at least one of the causal relationship and the inclusion relationship in the task based on the patterns and combinations stored in the pattern storage unit 3, and the higher-level task (for example, Search for "I want to reduce costs").

In step S122, the higher-rank assignment expansion unit 1e extends the higher-rank assignment searched by the higher-rank assignment search unit 1a and derives another task. For example, suppose that the high-ranked task searched by the high-ranked task search unit 1a is "I want to reduce the cost" (note that even if the descriptions do not match exactly, a similar expression may be used using an external or internal post-similar dictionary). May be). The higher-level task expansion unit 1e searches for a task that is a synonym (parallel description) to this higher-level task from the sentences stored in the general information storage unit 4 or the description in the table, and extracts it as a new higher-level task.

For example, the general information storage unit 4 stores an article “A recent problem in the television industry is that it is difficult to reduce costs, new customers cannot get in, and advertising revenue does not increase” on a website as shown in FIG. It has been done. The upper-level task extension unit 1e determines that the word "cost reduction" in the upper level task "I want to lower the cost" and the word "cost down" in the article are parallel descriptions of the higher level tasks at the same level, and the word "cost down" is used in parallel in the article. The items described are extracted as candidates for a new subject (for example, “incorporation of new customers”, “increased advertising revenue”).

Furthermore, it is assumed that the general information storage unit 4 stores a correspondence table of tasks and measures as shown in FIG. The higher-rank task extension unit 1e determines that the word "high cost" in the table similar to the higher-rank task "I want to reduce cost" is a parallel description of higher-rank tasks of the same level, and in the table, "high cost". , Which are described in parallel with "," are extracted as candidates for a new subject (for example, "detachment of existing customer", "break from dependence on newspaper").

In step S123, the higher-rank task selection unit 1f selects a task that co-occurs with a keyword related to the domain "newspaper" (or a similar domain may be included) among the expanded new higher-rank tasks. As the co-occurrence task and the keyword, words stored in the keyword table in the domain keyword storage unit 5 as the domain name and the domain frequent word may be used. For example, for the domain "newspaper" and the higher-level problem "I want to reduce costs," the higher-level problem extension unit 1e extracts from the general information storage unit 4 as "1. Incorporation of new customers" and "2. Increase in advertising revenue." "3. Separation of existing customers" and "4. Elimination from dependence on newspapers". In this case, the higher-level task selection unit 1f newly creates “2. Increase in advertising revenue” including the domain frequent word “advertisement” that co-occurs with the domain, that is, corresponds to the domain name “newspaper” in the domain keyword storage unit 5. Selected as a high-ranking task. Furthermore, the higher-level task selection unit 1f may select "4. Breaking from dependency on newspaper" including the domain name "newspaper" as a new task. The selection unit 1c adds the selected task to the relationship storage unit 6 as a new higher level task. For example, it is inserted in the tree diagram shown in FIG. The selected problem and the problem to be inserted in the tree may differ in expression. For example, in FIG. 14, “2. Increasing advertising revenue” is placed in the tree as a top task “I want to increase advertising revenue”, and “4. Breaking from dependence on newspapers” is a top issue “I want to earn in a business different from newspapers”. insert. Note that the selection unit 1c may extract the highest-level task common to all the higher-level tasks and insert it into the root of the tree together with the domain.

Next, steps S130 to S140 are executed for the number of higher-level tasks, and the lower-level tasks in each higher-level task are extracted. In step S150, the verification priority of all subordinate tasks is determined. In step S160, a list of subordinate tasks with priorities is output (the operations of steps S130 to S160 are the same as in the first embodiment).

According to the problem estimation device 300 of the present embodiment, a large number of problems to be verified can be appropriately extracted over a wide range. This is because the task estimation unit 20 searches for the higher-level task based on the underlying lower-level task, expands the higher-level task up to the task in parallel with the searched higher-level task, and lowers all of the expanded higher-level tasks. This is because the problem is extracted. This makes it possible to cover a wide range and extract other problems to be verified.

<Fourth Embodiment>
FIG. 15 shows a task estimation device 400 according to the fourth embodiment of the present invention. The task estimation device 400 is the minimum configuration of the first to third embodiments. The task estimation device 400 includes a task estimation unit 30. The task estimation unit 30 outputs at least one second task that is a result of specializing a superordinate concept that generalizes the input first task, and outputs at least one second task among the second tasks that are output. A problem that co-occurs with the domain to which the first problem belongs is extracted.

According to the problem estimation device 400 of the present embodiment, a large number of problems to be verified can be appropriately extracted over a wide range. This is because the task estimation unit 30 extracts, in particular, a task in the same domain as the input task or a domain similar to the input task, out of the tasks that are the result of specializing the superordinate concept obtained by generalizing the input task.
(Configuration of information processing device)
In each of the above-described embodiments of the present invention, each component of the task estimation device represents a block of a functional unit. Some or all of the constituent elements of the task estimation device are realized by an arbitrary combination of an information processing device 500 and a program as shown in FIG. 16, for example. The information processing device 500 includes, for example, the following configuration.

-CPU (Central Processing Unit) 501
-ROM (Read Only Memory) 502
RAM (Random Access Memory) 503
-Program 504 loaded in RAM 503
-Storage device 505 that stores the program 504
-Drive device 507 for reading and writing the recording medium 506
-Communication interface 508 connected to the communication network 509
.Input/output interface 510 for inputting/outputting data
.Bus 511 for connecting each component
Each component of the task estimation device in each embodiment is realized by the CPU 501 acquiring and executing the program 504 that realizes these functions. The program 504 that realizes the function of each component of the task estimation device is stored in the storage device 505 or the RAM 503 in advance, for example, and is read by the CPU 501 as necessary. The program 504 may be supplied to the CPU 501 via the communication network 509, or may be stored in the recording medium 506 in advance and the drive device 507 may read the program and supply it to the CPU 501.

There are various modifications to the method of realizing each device. For example, the task estimation device may be realized by an arbitrary combination of the information processing device 500 and the program, which are different for each component. Further, a plurality of constituent elements included in the task estimation device may be realized by an arbitrary combination of one information processing device 500 and a program.

Further, some or all of the constituent elements of the task estimation device are realized by other general-purpose or dedicated circuits, processors, etc., or a combination thereof. These may be configured by a single chip, or may be configured by a plurality of chips connected via a bus.

Some or all of the constituent elements of the task estimation device may be realized by a combination of the above-described circuits and the like and a program.

When some or all of the constituent elements of the task estimation device are realized by a plurality of information processing devices or circuits, the plurality of information processing devices or circuits may be centrally arranged or distributed. May be. For example, the information processing device, the circuit, and the like may be realized as a form in which a client and server system, a cloud computing system, and the like are connected to each other via a communication network.

1: task estimation unit 1a: higher-level task search unit 1b: task extension unit 1c: selection unit 1d: higher-level task derivation unit 1e: higher-level task expansion unit 1f: higher-level task selection unit 2: priority determination unit 3: pattern storage unit 4 : General information storage unit 5: Domain keyword storage unit 6: Relationship storage unit 10: Assignment estimation unit 20: Assignment estimation unit 30: Assignment estimation unit 100: Assignment estimation device 200: Assignment estimation device 300: Assignment estimation device 400: Assignment Estimating device 500: Information processing device 501: CPU
503: RAM
504: Program 505: Storage device 506: Recording medium 507: Drive device 508: Communication interface 509: Communication network 510: Input/output interface 511: Bus

Claims (7)

A keyword storage unit storing at least one keyword corresponding to the information indicating the subject of the task;
And issues expansion means for the first problem is a problem that is input to search the second problem to be correlated cord to the lower-level object that is generalized from the general information, and outputs at least one or more,
Among the second problem, selecting for outputting a challenge for the co-occurrence of the problem that has the keyword which the stored in the keyword storage means, corresponding to the first object indicating the said problems of the subject belonging information And a task estimation device. During pre KiHiroshika, the first receiving the information indicating the first object and the first object of interest to acquire the general information related to the first problem has been accepted, the general information obtained On the basis of the above, a higher- rank problem search means for outputting the higher- rank problem having at least one of a causal relationship and an inclusion relation with the first problem
The task estimation device according to claim 1, further comprising: Higher-rank problem deriving means for searching the general information based on the inputted first problem and information indicating the target of the first problem and deriving the higher-rank problem which is a higher rank of the first problem.
The task estimation device according to claim 1 , further comprising: From the general information, the higher-level task expansion means for acquiring and outputting the same level of task as the higher level task based on a pattern indicating a parallel relationship ,
Based on the keywords stored in the keyword storage means, a task that co-occurs with a keyword related to the received information indicating the target of the first task is selected from the tasks output by the higher-level task expansion means. The task estimation device according to claim 2 , further comprising: upper-level task selection means . Priority determining means for determining priority for verifying the first problem and the second problem acquired from the estimating means
The task estimation device according to claim 1 , further comprising: Find the second problem first problem is a problem that has been entered should be correlated cord to the lower-level object that is generalized from the general information, and outputs at least one or more,
Among the second assignments, the keyword storage means for storing at least one keyword corresponding to the information indicating the subject of the assignment is used to correspond to the information indicating the subject of the assignment to which the first assignment belongs. A task estimation method that a computer executes to output a task having a keyword as a co-occurrence task. Find the second problem first problem is a problem that has been entered should be correlated cord to the lower-level object that is generalized from the general information, and outputs at least one or more,
Among the second assignments, the keyword storage means for storing at least one keyword corresponding to the information indicating the subject of the assignment is used to correspond to the information indicating the subject of the assignment to which the first assignment belongs. A task estimation program for causing a computer to output a task having a keyword as a co-occurring task.

Images