JP2018005404A - Device, method, and program for estimating issues - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an issue estimation device and the like, which allow for covering a wide range to extract appropriate issues to be verified.SOLUTION: An issue estimation device 200 includes: a determination unit 10a configured to receive an input of an issue and information indicative of an object of the issue, and to determine whether the issue is specific or not on the basis of a relationship between a modifier and a modified word within the issue; and an objectification unit 10b configured to extract, as a specific issue, a character string containing the modified word and modifier modifying the modified word from a result of a search made through general information using, as search keys, the modified word contained in the issue determined to be not specific and information indicative of the object of the issue corresponding to the issue determined to be not specific.SELECTED DRAWING: Figure 7

Description

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

  Explain how to start a business related to product development and manufacturing. One business development approach is a waste of time by rapidly repeating the processes of “development of product hypotheses that customers potentially need”, “product implementation” and “product and business trajectory correction” at the development stage. We will continue to improve our products quickly while minimizing unnecessary elements, and make the business successful. In this business development method, first, a person involved in a business (hereinafter referred to as a business operator) extracts hypothesis problems related to users such as customers, verifies the problems, and produces a prototype product that is at least practical ( Manufacturing the Minimum Viable Product as quickly as possible and providing it to the user. Thereafter, the business operator restructures the initial hypothesis based on the result obtained by verifying the user's reaction to the prototype product, and corrects the trajectory of the product or business. By repeating only the minimum processes necessary to grasp the user's demand, the operator can save time and money for non-essential elements (for example, creation of specifications, approval documents, etc.) that do not lead to the success of the business. Or, wasteful labor is saved. This makes it possible to grasp the core issues without narrowing the scope of product development too much.

  In order to grasp the true demands of users in such a development method, it is important to generate hypothetical tasks quickly and properly 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, there is a problem with a group having a certain common problem (for example, a trade association that develops a business for elderly people), a predetermined business field, or a predetermined industry (hereinafter referred to as “domain” in this application). When making a hypothesis, the operator must comprehensively grasp the information of the domain and investigate the information. In addition, the business operator needs to grasp future issues of the domain and issues in the peripheral fields of the domain, and it is difficult to quickly and appropriately make a hypothesis of the issue. In the present application, the domain is also described as “information indicating the subject of the task”.

  As a technology related to the above, a technology for creating a new idea by expanding the object data object frame when developing a new product is disclosed (see Patent Document 1). Furthermore, when designing a common object in the system design process, the common object is effectively determined from multiple domains without depending on individual domains (activity areas), the common object determination cycle is repeated, and the common object is updated. The technique to do is disclosed (refer patent document 2).

  In addition, as a related technique, a technique for detecting deficiencies in specifications written in a natural language using morphological analysis or the like is disclosed (see Patent Document 3).

JP2015-184971 JP 2004-13280 A JP 2014-81680 A

  In the techniques of Patent Documents 1 to 3, it is assumed that the information processing apparatus or the like appropriately receives the problem data from the user or the like. However, when task data is input from a user or the like, the input task data may be abstract, or the term may be inappropriate or lacking. In this way, if the task data is not sufficiently specific, the search results and task extraction results will contain a lot of noise unrelated to the task, leading to an appropriate task and a sufficient number of tasks. There was a problem that it could not be extracted.

  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 extracts an appropriate problem to be verified.

In order to solve the above problem, a problem estimation apparatus according to a first aspect of the present invention includes:
A determination unit that receives input of information indicating a task and a subject of the task, and determines whether the task is specific based on a relationship between a modifier and a modified word in the task;
Of the results of searching general information using the modified word included in the task determined to be non-specific and the information indicating the subject of the task corresponding to the task determined not specific, the modified word And a specific means for extracting a character string including a modifier that modifies the modified word as a specific problem.

The problem estimation method according to the second aspect of the present invention includes:
Accept input of information indicating the assignment and subject of the assignment,
Based on the relationship between modifiers and modifiers in the assignment, determine whether the assignment is specific,
Search the general information using a search key with the modified word included in the problem determined to be not specific and the information indicating the target of the problem corresponding to the problem determined not specific,
A character string including a modified word and a modified word that modifies the modified word is extracted as a specific problem from the retrieved results.

The problem estimation program according to the third aspect of the present invention is:
Accept input of information indicating the assignment and subject of the assignment,
Based on the relationship between modifiers and modifiers in the assignment, determine whether the assignment is specific,
Search the general information using a search key with the modified word included in the problem determined to be not specific and the information indicating the target of the problem corresponding to the problem determined not specific,
The computer is made to extract the character string containing the to-be-modified word and the to-be-modified word which modifies a to-be-modified word as a specific subject out of the said search result.

  According to the present invention, it is possible to provide a problem estimation device that covers a wide range and extracts an appropriate problem to be verified.

It is a figure which shows the structural example of the task estimation apparatus in the 1st Embodiment of this invention. It is a figure which shows the structural example of the data of an important expression. It is a figure which shows the structural example of the internal data of a domain keyword memory | storage part. It is a flowchart which shows the operation example of the subject estimation apparatus in the 1st Embodiment of this invention. It is a figure which shows the structural example of the internal data of a relationship memory | storage part. It is a figure which shows the structural example of the internal data of a relationship memory | storage part. It is a figure which shows the structural example of the task estimation apparatus in the 2nd Embodiment of this invention. It is a figure which shows an example of the task list with a priority.

  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 parts are denoted by the same or similar reference numerals. However, the drawings schematically show the configuration of the embodiment of the present invention. Furthermore, the embodiment of the present invention described below is an example, and can be appropriately changed within a range in which the essence is the same.

<First Embodiment>
(Problem estimation device)
As shown in FIG. 1, a problem estimation apparatus 100 according to the first embodiment of the present invention includes a problem estimation unit 1, a priority determination unit 2, an important expression 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 task determination unit 1a, a task materialization unit 1b, a domain extension unit 1c, and a task extension unit 1d. In the present application, the task estimation means extracting candidates that can be tasks.

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

  The important expression storage unit 3 stores terms (important expression terms) that are included in sentences in general information and that are likely to be included in sentences with high importance. The important expression storage unit 3 stores, for example, “important”, “maximum”, “necessary”, “essential”, and the like shown in FIG. 2 as important expression terms.

  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, “Postal”, “Convenience Store”, “Apparel”, etc. as the domain name of the domain, “Postcard, Postal, Yucho”, “Franchise Owner, Order”, respectively, as frequent words related to these domains "," Recycle, shop clerk ", etc. are stored.

  The relationship storage unit 6 is a memory for storing, for example, a table (see FIG. 5) indicating a relationship between a task and a domain when the task estimation unit 1 expands a domain or expands a task.

  The assignment determination unit 1a receives input of an assignment and a domain, and determines whether or not the assignment is specific based on the relationship between modifiers and modified words in the assignment. Specifically, the task determination unit 1a accepts input of text information and the like indicating “task” and “domain” via an input / output interface described later from another device. Further, the task determination unit 1a determines whether the input “task” is specific. Here, the specific problem means that a modified word (object, noun) in the problem is modified by at least one modifier. For example, the task discriminating unit 1a determines whether the modified word (object, noun or noun phrase) of the input task is modified by an adjective or adjective phrase, and whether the adjective is modified by an adverb or adverb phrase, etc. Judging. The task determination unit 1a may divide a sentence into meaningful words by morphological analysis, and determine the part of speech and contents using a dictionary or the like. As a specific example, a case will be described in which the task determination unit 1a accepts a task of “reducing driver labor costs” as an input (in the following description, a specific example of a character string is enclosed in double brackets “”). Write down). In this case, since the modified term “personnel cost” is modified by the modifier “driver” (adjective phrase), the task determination unit 1a determines that the task is specific. However, when the task of “reducing labor costs” is input, the subject word “labor costs” is not qualified, and the task determination unit 1a determines that this task is not specific.

  The task determination unit 1a may receive information in which the specificity of the task is determined in advance from another device, and may determine whether the input task is specific based on this information.

  When it is determined that the input task is specific, the task determination unit 1a outputs the task to the domain extension unit 1c. When the task determination unit 1a determines that the input task is not specific, the task determination unit 1a outputs the task and the input domain to the task specification unit 1b.

  The task materialization unit 1b searches the general information storage unit 4 using the modified word included in the task determined to be not specific and the domain corresponding to the task determined to be not specific as a search key. Further, the problem materializing unit 1b takes a character string including a modified word and a modified word that modifies the modified word as a specific problem from the search results (sentences related to the modified word and the domain). Extract.

  Specifically, the task materialization unit 1b receives from the task determination unit 1a a task and a domain that are determined not to be specific, and extracts a modified word (noun, object) from the received character string of the task. For example, upon receiving the task “reducing labor costs”, the task materialization unit 1b extracts “labor costs” as a qualified word. Next, the task materializing unit 1b searches the general information storage unit 4 using the extracted modified term “personnel cost” and its domain (here, “distribution”) as a search key. At this time, instead of using all nouns included in the assignment as search keys, the user may be allowed to select some nouns.

  The task materialization unit 1b includes a search that includes a domain (for example, “distribution”) that is a search key and includes an important expression term that is stored in the important expression storage unit 3 from the search result of the general information storage unit 4. Extract the result (sentence). At this time, since the general information storage unit 4 is generally displayed in descending order of the number of search hits, the one displayed at the top is predicted to have a higher relevance. For this reason, the task materializing unit 1b may extract only an arbitrary number (for example, 10) of search results from the top.

  The task materialization unit 1b searches for a word that modifies the extracted modified word (for example, “personnel expenses”) from an arbitrary number of extracted search results, and the character that includes “qualified word” and “qualified word”. Extract columns. For example, when the modifier is “driver” and the modifier is “labor cost”, the extracted character string is “driver labor cost”. The task materialization unit 1b outputs a character string (for example, “driver's labor cost”) including the modifier and the modified word, which is the extraction result, as a materialized task. There may be a plurality of issues to be output, and the user may select a preferable one from the plurality of issues.

  The domain expansion unit 1c includes information or a keyword indicating the target of the problem stored in the keyword storage unit among the problems as a result of searching the general information storage unit 4 based on the search key including the input specific problem. The task is extracted, and information indicating the target of the task included in the extracted task is output. Specifically, when the domain expansion unit 1c receives a specific problem (hereinafter referred to as a specific problem) from the problem specification unit 1b or the problem determination unit 1a, the domain expansion unit 1c expands the specific problem to another domain. Specifically, the domain expansion unit 1 c searches the general information storage unit 4 using a specific task and the word “task” as search keys. For example, if “driver's labor cost” is an issue, the search key is “driver's labor cost issue”.

  The domain expansion unit 1c searches the sentence including the related keyword stored in the domain keyword storage unit 5 from the search result of the general information storage unit 4, and extracts the domain name corresponding to the related keyword. The domain extension unit 1 c may search for a sentence including the domain name stored in the domain keyword storage unit 5 from the search result of the general information storage unit 4. This extraction of domain names is repeated until an arbitrary number (for example, five) of different domain names are extracted. Thereafter, the domain extension unit 1c outputs the extracted domain name to the task extension unit 1d.

  The task extension unit 1d uses at least one of the results of searching the general information storage unit 4 based on a search key including information indicating the subject of the input task as a task, including a character string estimated as a task. Extract above. Specifically, the task extension unit 1d receives the domain name output from the domain extension unit 1c, and sets the general information storage unit 4 using the domain name and the word “task” as a search key (for example, “taxi task”). Search for. The task extension unit 1d extracts a sentence including an expression estimated as a task from the search result. The expression estimated as a task is a sentence including a character string indicating a task such as “ga task” or “task is”. The task extension unit 1d extracts an expression estimated as a task from the extracted sentence. For example, the task extension unit 1d extracts a character string described before “ga task” or a character string described following “task is”. The task expansion unit 1d extracts these character strings for an arbitrary number (for example, three) as expanded tasks. The task extension unit 1d outputs the extended task to the priority determination unit 2.

  Upon receiving an arbitrary number of expanded tasks output from the task expansion unit 1d, the priority determination unit 2 determines the priority of the expanded task. For example, the priority determination unit 2 searches the general information storage unit 4 for an arbitrary number using the expanded assignment as a search key, and rearranges them in the order to be verified based on the search result. The order to be verified may be, for example, the order in which the creation or update date of the web page that is the search result is new, the order in which the number of search hits is small, and the like. These are examples, and the order to be verified may be realized by other methods. The priority determination unit 2 outputs a task list with priorities to the outside via an input / output interface described later.

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

  In step S110, the task determination unit 1a of the task estimation apparatus 100 receives “task” and “domain” from another device or the like via an input / output interface described later. The task determination unit 1a temporarily stores the received “task” and “domain” in the relationship storage unit 6 (“1. input domain”, “2. input” in the table shown in FIG. 5). (See “Issues”). In the following description, as an example, a case will be described in which the task determination unit 1a is input with the task “reducing labor costs” and the domain “logistics”.

  In step S120, the task determination unit 1a determines whether the modified word (object, noun) of the input task is modified. As an example in the present embodiment, the task determination unit 1a identifies whether the modified word has a modifier, that is, an adjective or an adjective phrase, and whether the adjective or adjective phrase has an adverb or an adverb phrase. Thus, it is determined whether or not the word to be modified is modified. If it is determined that the word to be modified is not modified, the process proceeds to step S130. If it is determined that the to-be-modified word is modified, the process proceeds to step S140.

  In step S <b> 130, with respect to the problem “reducing labor costs” determined to be not specific, the problem specifying unit 1 b performs processing for specifying the problem. Specifically, the task materialization unit 1b uses the modified word (object, noun) “labor cost” and the domain “logistics” corresponding to the modified word as a search key (for example, “labor cost logistics”), The general information storage unit 4 is searched. Among the results of the search, the task materialization unit 1b extracts a sentence that includes the important expression term (see FIG. 2) stored in the important expression storage unit 3 and in which the modified word “personnel cost” is modified. To do. The extracted sentence is, for example, “The chart shows the transportation cost per month for a 4-ton car, but the driver's labor cost accounts for 46%, which is the largest. ].

  The task materialization unit 1b extracts a modifier of the modified word from the extracted sentence. Furthermore, the task materialization unit 1b takes a character string that combines the modified word and the extracted modifier as a materialized task. For example, the problem materializing section 1b indicates that the extracted sentence “The chart shows the transportation cost per vehicle of a 4-ton car per month, but the driver's labor cost accounts for 46%, which is the largest. ”To extract the“ driver ”that modifies the modified term“ personnel cost ”. Further, the problem specifying section 1b sets the “driver's labor cost”, which is a character string obtained by combining the extracted modifiers and the modifiers, as a specific subject. The problem materializing unit 1b stores the materialized problem in the relationship storage unit 6 (see “3. Materialized problem” in the table of FIG. 5), and outputs it to the domain expansion unit 1c.

  In step S140, the domain extension unit 1c uses a search key (for example, “driver labor cost task”) that combines the task “driver's labor cost” and the term “task” output by the task materializing unit 1b. The general information storage unit 4 is searched and the domain is expanded using the search result. The domain expansion unit 1c includes the related keywords stored in the domain keyword storage unit 5 (see FIG. 3) in the search result sentence in order from the top of the search results (generally arranged in ascending order of the number of search hits). And check the results. If the related keyword is included, the domain extension unit 1c determines that the domain belongs to the domain associated with the related keyword, and sets the domain as an extended domain. For example, the domain expansion unit 1c uses the domains “taxi”, “bus”, “railway”, “emergency medical care”, and “garbage collection” including the related keyword “vehicle” in the domain keyword storage unit 5 as expanded domains. Output. This step is repeated until an arbitrary number of extended domains are extracted (here, 5 cases). The domain expansion unit 1c stores the expanded domain in the relationship storage unit 6 (see “4. Expanded domain” in the table of FIG. 5), and outputs it to the problem expansion unit 1d.

  In step S150, the task extension unit 1d searches the search key (for example, “taxi task”, “bus task”, which combines the expanded domain “taxi”, “bus”, etc., output from the domain extension unit 1c with the term “task”. Etc.) to search the general information storage unit 4. The task extension unit 1d extracts a sentence including “task” from the search result. Any number may be sufficient as extraction.

  The extracted sentences are, for example, “deterioration of the surrounding environment and traffic congestion due to taxi waiting on customers at stops in front of the station and downtown areas” and “coexistence with welfare / care taxis. ”,“ Clarification of the buses necessary for the region, and the formation of a bus network that allows route buses and community buses to function in an integrated and efficient manner ”,“ After all, activation of local areas and tourism promotion It seems that measures to promote this are a challenge. ].

  The task extension unit 1d extracts a description that seems to be a task expression from the extracted sentence. For example, the task expansion unit 1d may function in a portion corresponding to the “determination of surrounding environment, traffic congestion”, “coexistence with welfare / care taxi”, “integrated and efficient functioning” “Formation of bus network” and “measures to promote tourism” are extracted, and these are expanded issues. The task expansion unit 1d stores the expanded tasks in the relationship storage unit 6 (see “5. Expanded issues” in the table of FIG. 5), and outputs them to the priority determination unit 2.

  In step S160, the priority determination unit 2 arranges each of the extended issues output by the issue extension unit 1d in the order of creation based on the creation or update date of the web page on which the issue is posted. Change.

  In step S <b> 170, the priority determination unit 2 outputs the rearranged result as a priority assignment list (see FIG. 6) to another device via an input / output interface described later.

  As described above, the problem estimation apparatus 100 according to the first embodiment can extract an appropriate problem to be verified over a wide range. This is because the task estimation unit 1 modifies the modified word and the modified word out of the result of searching the general information using the modified word included in the unspecified task and the domain of the task as a search key. This is because a character string including "and" is extracted as a specific problem.

<Second Embodiment>
A problem estimation apparatus 200 according to the second embodiment of the present invention will be described with reference to FIG.

  The task estimation device 200 includes a determination unit 10a and a materialization unit 10b.

  The determination unit 10a receives input of a task and a domain (information indicating a target of the task), and determines whether the task is specific based on the relationship between the modifier and the modified word in the task.

  The materializing unit 10b modifies the subject out of the result of searching the general information using the modified word included in the task determined to be not specific and the domain corresponding to the task determined to be not specific as a search key. A character string including a word and a modifier that modifies the modified word is extracted as a specific problem.

The problem estimation device 200 according to the second embodiment can extract an appropriate problem to be verified over a wide range. This is because the reification unit 10b modifies the modified word and the modified word out of the result of searching the general information using the modified word included in the unspecific problem and the domain of the problem as a search key. This is because a character string including the character string is extracted as a specific problem.
(Configuration of information processing device)
In each embodiment of the present invention described above, each component of the problem estimation device represents a functional unit block. Part or all of the components of the problem estimation device are realized by any combination of an information processing device 500 and a program as shown in FIG. 8, for example. The information processing apparatus 500 includes the following configuration as an example.

CPU (Central Processing Unit) 501
ROM (Read Only Memory) 502
-RAM (Random Access Memory) 503
A program 504 loaded into the RAM 503
A storage device 505 for storing the program 504
A drive device 507 for reading / writing the recording medium 506
A communication interface 508 connected to the communication network 509
An input / output interface 510 for inputting / outputting data
-Bus 511 connecting each component
Each component (each part in the task estimation unit 1 and the like) of the task estimation apparatus in each embodiment is realized by the CPU 501 acquiring and executing a program 504 that realizes these functions. The program 504 that realizes the function of each component of the problem estimation device is stored in advance in the storage device 505 or the RAM 503, for example, and is read by the CPU 501 as necessary. Note that 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 a program that are separate for each component. Moreover, the some component with which a task estimation apparatus is provided may be implement | achieved by the arbitrary combinations of the one information processing apparatus 500 and a program.

  In addition, some or all of the components of the problem estimation device are realized by other general-purpose or dedicated circuits, processors, or combinations thereof. These may be configured by a single chip or may be configured by a plurality of chips connected via a bus.

  A part or all of each component of the problem estimation device may be realized by a combination of the above-described circuit and the like and a program.

  When some or all of the components of the problem estimation device are realized by a plurality of information processing devices and circuits, the plurality of information processing devices and circuits may be centrally arranged or distributedly arranged. May be. For example, the information processing apparatus, the circuit, and the like may be realized as a form in which each is connected via a communication network, such as a client and server system and a cloud computing system.

1: task estimation unit 1a: task determination unit 1b: task materialization unit 1c: domain expansion unit 1d: task expansion unit 2: priority determination unit 3: important expression storage unit 4: general information storage unit 5: domain keyword storage unit 6: Relationship storage unit 10a: Discriminating unit 10b: Implementation unit 100: Problem estimation device 200: Problem estimation 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 (9)

A determination unit that receives input of information indicating a task and a target of the task, and determines whether or not the task is specific based on a relationship between a modifier and a modified word in the task;
Among the results of searching for general information using the modified word included in the task determined to be not specific and information indicating the target of the task corresponding to the task determined to be not specific, as a search key, A problem estimation apparatus comprising a specific unit that extracts a character string including the modified word and a modified word that modifies the modified word as a specific problem. When the specific means extracts as the specific problem, the specific means extracts, from the search result, an important expression term included in the sentence of the problem with high importance and the modifier, and the extraction A character string including the modified word included in the result and the modified word corresponding to the modified word is output as the specific problem;
The problem estimation apparatus according to claim 1. Keyword storage means for storing at least one keyword corresponding to information indicating the subject of the task;
Of the issues that are the result of searching the general information based on the input search key including the specific issue, information indicating the subject of the issue stored in the keyword storage means or an issue including the keyword is extracted. The problem estimation apparatus according to claim 1, further comprising a domain expansion unit that outputs information indicating a target of the problem included in the extracted problem. A task expansion means for extracting at least one or more items including a character string estimated as a task from among the results of searching the general information based on a search key including information indicating the input subject of the task. The problem estimation device according to any one of claims 1 to 3, further comprising: The problem estimation apparatus according to claim 1, further comprising priority determination means for determining a priority for verifying the problem acquired from the problem expansion means. Accept input of information indicating assignment and subject of the assignment,
Based on the relationship between the modifier and the modified word in the task, it is determined whether or not the task is specific,
Search the general information using the modified word included in the task determined to be not specific and the information indicating the target of the task corresponding to the task determined to be not specific as a search key,
A problem estimation method comprising: extracting, as a specific problem, a character string including the modified word and a modified word that modifies the modified word from the retrieved results. In extracting as the specific problem,
From the results of the search, extract important expression terms included in the sentence of the task with high importance and the modifiers,
A character string including the modified word included in the extraction result and a modified word corresponding to the modified word is output as the specific problem;
The problem estimation method according to claim 6. Accept input of information indicating assignment and subject of the assignment,
Based on the relationship between the modifier and the modified word in the task, it is determined whether or not the task is specific,
Search the general information using the modified word included in the task determined to be not specific and the information indicating the target of the task corresponding to the task determined to be not specific as a search key,
A problem estimation program for causing a computer to extract, as a specific problem, a character string including the modified word and a modified word that modifies the modified word from the retrieved results. In extracting as the specific problem,
From the results of the search, extract important expression terms included in the sentence of the task with high importance and the modifiers,
A character string including the modified word included in the extraction result and a modified word corresponding to the modified word is output as the specific problem;
The problem estimation program according to claim 8.

Images