JP5410557B2 - Estimation apparatus, method, and program for estimating difficulty of question and knowledge level of user in question answering service - Google Patents

Description

  The present invention relates to an estimation apparatus, method, and program for estimating a question difficulty level and a user knowledge level in a question answering service.

  In recent years, with the spread of communication networks, a service has been provided that accepts questions from users and accepts answers to these questions from any user on a Web site (see, for example, Patent Document 1). In such a service, a user who has posted a question selects an answer that is said to have solved the question from the answers posted to the question. Thereby, the user who browsed the question accepted in the past can efficiently search for an answer that the question is solved, and as a result, the service is improved.

JP 2001-273432 A

By the way, in such a service, for the purpose of improving the quality of answers, unresolved information among the accepted questions is distributed to users who answered the questions in the past, and the answers are accepted early. It has been broken.
However, depending on the difficulty level of the question, there is a possibility that the user presented with the question cannot answer the question. If the user presented with the question cannot answer the question, the unresolved state may not be resolved at an early stage, which may lead to service degradation. Therefore, it is desired to identify a user who is highly likely to solve an unresolved question, distribute the question to the user, and quickly resolve the unresolved state of the question.

  An object of this invention is to provide the estimation apparatus, method, and program which can identify the user with high possibility of solving an unresolved question.

  (1) An estimation apparatus for estimating a difficulty level of a question and a user's knowledge level in a question answering service, and storing user identification information for identifying the user and the knowledge level of the user in association with each other A question information storing means for storing the question identification information for identifying the question, the question content, and the difficulty level in association with each other, the question identification information, and an answer to the question corresponding to the question identification information Answer information storage means for associating and storing the user identification information of the user who has performed, the question identification information, and the user identification information of the user who has posted the answer selected as a solution to the question corresponding to the question identification information; Referring to the selection information storage means for storing the information in association with each other, the answer information storage means and the user information storage means, for each of the plurality of questions, The number of users who posted the information is calculated for each knowledge level, the difficulty level is estimated based on the knowledge level with the largest number of users in the total result, and the difficulty level estimation for updating the difficulty level of the question information storage means And the knowledge level of the user who posted the selected answer corresponding to the question for which the difficulty level is set with reference to the question information storage means and the selection information storage means, based on the difficulty level An estimation device comprising: knowledge level estimation means for estimating and updating the knowledge level of the user in the user information storage means.

  (2) The user information storage unit stores the user identification information, a category, and the knowledge level in association with each other, and the question information storage unit stores the question identification information, the question content, and the category. The difficulty level estimation means refers to the question information storage means, the answer information storage means and the user information storage means, and answers the question for each of a plurality of questions. The number of posted users is aggregated for each knowledge level of the user corresponding to the category to which the question belongs, and the difficulty level is estimated based on the knowledge level with the largest number of users in the aggregation result, and the question information storage means The degree of difficulty is updated, and the knowledge level estimation means refers to the question information storage means and the selection information storage means, and selects the selected times corresponding to a question. The knowledge level corresponding to the category to which the question belongs is estimated based on the level of difficulty related to the question, and the knowledge level of the user is updated in the user information storage means (1) The estimation device described.

  (3) The estimation according to (1) or (2), wherein the knowledge level estimation unit updates the knowledge level for a user who has posted the selected answer corresponding to the question whose degree of difficulty has been updated. apparatus.

  (4) The difficulty level estimation means estimates the difficulty level of each of the plurality of questions after the knowledge level is updated by the knowledge level estimation means, according to any one of (1) to (3) The estimation device described.

  (5) The difficulty level estimation means repeatedly executes the estimation of the difficulty level and the update of the estimated difficulty level, and the knowledge level estimation means performs the estimation of the knowledge level and the estimated knowledge level. The estimation device according to any one of (1) to (4), wherein update is repeatedly executed.

  (6) The difficulty level estimation unit periodically executes the estimation of the difficulty level and the update of the estimated difficulty level, and the knowledge level estimation unit includes the estimation of the knowledge level and the estimated knowledge level. The estimation apparatus according to (5), wherein level update is periodically performed.

  (7) An estimation device that is communicably connected to a storage device and estimates a difficulty level of a question and a user's knowledge level in a question answering service, the storage device including user identification information for identifying a user, User information storage means for storing the user's knowledge level in association, question identification information for identifying a question, question content, and question information storage means for storing the difficulty level in association with each other, the question identification information, Answer information storage means for associating and storing user identification information of a user who has posted an answer to the question corresponding to the question identification information, and the estimation device includes the question identification information and the question identification information Selection information storage means for storing in association with user identification information of a user who has posted an answer selected as a solution corresponding to a question corresponding to the answer, and the answer information storage For each of a plurality of questions, the number of users who have posted answers is tabulated for each knowledge level, and the difficulty level is determined based on the knowledge level with the largest number of users in the tabulation result. The selection corresponding to the question for which the difficulty level is set with reference to the difficulty level estimation means for estimating and updating the difficulty level of the question information storage means, the question information storage means and the selection information storage means An estimation apparatus comprising: a knowledge level estimating unit that estimates a knowledge level of a user who has posted a replied answer based on the difficulty level and updates the knowledge level of the user in the user information storage unit.

  (8) An estimation method for estimating a difficulty level of a question and a user's knowledge level in the question answering service, wherein the server stores user identification information for identifying the user and the knowledge level of the user in association with each other Information storage means, question identification information for identifying a question, question content, and question information storage means for storing the degree of difficulty in association with each other, the question identification information, and a question corresponding to the question identification information Answer information storage means for associating and storing the user identification information of the user who posted the answer, the user of the user who posted the answer selected as a solution to the question identification information and the question corresponding to the question identification information Selection information storage means for associating and storing identification information, and the estimation method refers to the answer information storage means and the user information storage means For each of the plurality of questions, the number of users who have posted answers is counted for each knowledge level, the difficulty level is estimated based on the knowledge level with the largest number of users in the counting result, and the question information storage means The knowledge level of the user who posted the selected answer corresponding to the question for which the difficulty level is set with reference to the difficulty level estimation step for updating the difficulty level, the question information storage means and the selection information storage means And a knowledge level estimation step of updating a knowledge level related to the user in the user information storage means.

  (9) A program for causing a computer to estimate a difficulty level of a question and a user's knowledge level in the question answering service, wherein the server associates the user identification information for identifying the user with the knowledge level of the user User information storage means for storing, question identification information for identifying a question, question content, and question information storage means for storing in association with the difficulty, the question identification information, and a question corresponding to the question identification information An answer information storage means for associating and storing user identification information of a user who posted an answer to the question, the question identification information, and an answer selected as a solution to a question corresponding to the question identification information Selection information storage means for associating and storing user identification information of a user, and the program includes the answer information storage means and the previous information storage means Refer to the user information storage means, for each of a plurality of questions, total the number of users who posted the answer for each knowledge level, based on the knowledge level with the largest number of users in the total result, estimate the difficulty, The difficulty level estimation step of updating the difficulty level of the question information storage means, the question information storage means and the selection information storage means, and the selected answer corresponding to the question for which the difficulty level is set A program for causing a computer to execute a knowledge level estimation step of estimating a knowledge level of a user who has posted a message based on the difficulty level and updating a knowledge level related to the user in the user information storage means.

  ADVANTAGE OF THE INVENTION According to this invention, it becomes possible to provide the estimation apparatus, method, and program which can identify the user with high possibility of solving an unresolved question.

It is a figure which shows a knowledge storage system. It is a block diagram which shows the function structure of a knowledge storage server. It is a figure which shows user DB. It is a figure which shows question DB. It is a figure which shows reply DB. It is a flowchart which shows the flow of the reception process of a question, an answer, and answer selection which a knowledge storage server performs. It is a flowchart which shows the flow of the difficulty level estimation process and knowledge level estimation process which a knowledge storage server performs.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[Outline of knowledge accumulation system]
FIG. 1 is a diagram showing a knowledge storage system 1 according to the present embodiment.
The knowledge storage system 1 includes a knowledge storage server 2 as an estimation device and one or a plurality of user terminals 3. The knowledge storage server 2 and one or a plurality of user terminals 3 are configured to be communicable via a communication network N such as the Internet.

  In the knowledge storage system 1, the knowledge storage server 2 accepts a question posting from a poster via the user terminal 3. The knowledge accumulation server 2 totals the knowledge level of the user who made an answer via the user terminal 3 for each posted question. The knowledge accumulation server 2 specifies the most frequent knowledge level among knowledge levels equal to or higher than a predetermined threshold. The knowledge accumulation server 2 estimates the difficulty level of the question based on the identified knowledge level. When the contributor selects the best answer via the user terminal 3 for each of the plurality of questions, the knowledge accumulation server 2 adjusts the knowledge level of the answerer who made the answer.

Next, the functional configuration of the knowledge storage server 2 will be described.
FIG. 2 is a block diagram showing a functional configuration of the knowledge storage server 2 according to the present embodiment. In FIG. 2, only one user terminal 3 is displayed, but actually, a plurality of user terminals 3 are connected to the knowledge accumulation server 2 via the network N.

[Configuration of Knowledge Storage Server 2]
The knowledge accumulation server 2 is configured by one or a plurality of general computers. A general computer includes a control unit 10 serving as a central processing unit, a storage unit 20, a communication device, an input device, a display device, and a bus line to which these devices are connected. The control unit 10 is configured by a CPU or the like. The control unit 10 includes a question reception unit 11, an answer reception unit 12, an answer selection reception unit 13, a difficulty level estimation unit 14 as a difficulty level estimation unit, a knowledge level estimation unit 15 as a knowledge level estimation unit, and the like shown in FIG. It functions as the question distribution unit 16. The storage unit 20 includes a memory (RAM, ROM), a hard disk (HDD), an optical disk (CD, DVD, etc.) and the like. The storage unit 20 functions as the user DB 21, question DB 22, and answer DB 23 shown in FIG. The communication device includes various wired and wireless LAN devices. The display device includes various displays such as a liquid crystal display and a plasma display. The input device includes a touch panel or a keyboard and a pointing device (mouse, tracking ball, etc.). In such a general computer, the control unit 10 constituted by a CPU or the like controls the knowledge storage server 2 in an integrated manner, and adjusts the difficulty level of questions and the knowledge level of the user of the user terminal 3. The various functions according to the present invention are realized by cooperating with the hardware described above by appropriately reading and executing various programs.

  FIG. 3 is a diagram showing the user DB 21 according to the present embodiment. The user DB 21 includes at least a user ID, a user name (not shown), a category, and a knowledge level of the user corresponding to the user ID in the category. In addition to the items described above, the user DB 21 may store, for example, a user's mail address corresponding to the user ID in association with the user ID. The user DB 21 stores a user ID, a user name, a category, and a knowledge level of the user in the category in association with each other. The user ID is information for identifying a user who uses the question answering service. The user name is information indicating the name of the user. The category is information for classifying questions. The knowledge level is information indicating an objective measure of the user's knowledge in the category. As shown in FIG. 3, a plurality of categories and knowledge levels are associated with one user ID. Further, the knowledge level is indicated in five stages, for example, 1, 2, 3, 4, and 5. In the present embodiment, it is assumed that 1 is the lowest knowledge level and 5 is the highest knowledge level. Note that the knowledge level is not limited to five levels and may be a plurality of levels. Further, although the knowledge level is 1 is the lowest level and 5 is the highest level, it is not limited to this. For example, the knowledge level may be 1 being the highest level and 5 being the lowest level.

  FIG. 4 is a diagram showing the question DB 22 according to the present embodiment. The question DB 22 stores a question received from a user who uses the question answering service via the user terminal 3. Specifically, the question DB 22 includes at least a question ID, a posting time, a question user ID, a question content, a category, a difficulty level, and a deadline flag. This question DB 22 stores a question ID, a posting time, a question user ID, question contents, a category, a difficulty level, and a deadline flag in association with each other. The question ID stored in the question DB 22 is information for uniquely identifying the question. The posting time is information indicating the time when the question is posted. The question user ID is the user ID of the user who posted the question. The question content is information indicating the content of the posted question. The category is information indicating the category to which the question belongs. The difficulty level is information indicating the difficulty level of the question. This difficulty level is estimated by the difficulty level estimation unit 14 described later. For this reason, the difficulty level is not set before estimation. For example, in FIG. 4, the difficulty levels of the question IDs “123” and “111” are blank.

In addition, the difficulty level is indicated by, for example, five levels of 1, 2, 3, 4, and 5, and is the same index as the knowledge level. In this embodiment, 1 is the lowest difficulty level and 5 is the highest difficulty level. The difficulty level is not limited to five levels, and may be a plurality of levels. Further, the difficulty level is 1 being the lowest difficulty level and 5 being the highest difficulty level, but is not limited thereto. For example, the difficulty level may be that 1 is the highest difficulty level and 5 is the lowest difficulty level.
The deadline flag is information for determining whether or not to accept an answer to a question. Either the Null value or 1 is stored in the deadline flag.

  FIG. 5 is a diagram showing the answer DB 23 according to the present embodiment. The answer DB 23 stores the answer received from the user who uses the question answering service for the posted question via the user terminal 3. Specifically, the answer DB 23 includes at least a question ID, an answer ID, an answer user ID, an answer content, a solution user ID, and a selection time. In addition to the items described above, the answer DB 23 may store, for example, the time when the answer is posted in association with the question ID stored in the answer DB 23. The answer DB 23 stores a question ID, an answer ID, an answer user ID, an answer content, a solution user ID, and a selection time in association with each other. The question ID stored in the answer DB 23 is information indicating the question ID of the question for which an answer has been made. The answer ID is information for uniquely identifying the answer in each question ID. The answer user ID is information indicating the user ID of the user who made the answer. The answer content is information indicating the content of the posted answer.

The solution user ID is information indicating the user ID of the user who posted the selected answer when the user who posted the question selects the answer that is said to have solved the question from the posted answer. That is, the solution user ID associates the question ID with the user ID of the user who has posted an answer to the question corresponding to the question ID.
The selection time is information indicating the time at which the user who posted the question has selected an answer that is said to have solved the question.

  The question receiving unit 11 acquires various information about the question from the user of the user terminal 3 and stores it in the question DB 22. Below, the process of the question reception part 11 and the process of the user terminal 3 are demonstrated concretely.

First, the question reception unit 11 transmits a web page for question reception to the user terminal 3 in response to receiving a request for a web page for question reception from the user terminal 3.
Subsequently, the user terminal 3 receives a web page for accepting questions from the knowledge storage server 2. Subsequently, the user terminal 3 acquires from the user via the question reception web page via the selection of the category to which the question belongs and the content of the question, and then detects the question posting request. This question posting request is made by selecting a posting button provided on a question acceptance web page. When the user terminal 3 detects the question posting request, the user terminal 3 transmits the question posting request data for requesting the question posting to the knowledge storage server 2. The question posting request data includes at least a user ID, a question category, and a question content in order to specify the user of the user terminal 3.

  When receiving the question posting request data from the user terminal 3, the question receiving unit 11 generates a question ID. Moreover, the question reception part 11 acquires the present time, and makes the said present time the posting time. The question receiving unit 11 stores the generated question ID, the posting time, and the user ID, the question content, and the category included in the question posting request data in the question DB 22 in association with each other.

  The answer receiving unit 12 acquires various information about the answer from the user of the user terminal 3 and stores the information in the answer DB 23. Below, the process of the answer reception part 12 and the process of the user terminal 3 are demonstrated concretely.

  First, the answer reception unit 12 receives a request for a web page for accepting an answer from the user terminal 3. Here, a question ID is associated with a request for a web page for receiving an answer. Subsequently, the answer reception unit 12 transmits to the user terminal 3 an answer reception web page corresponding to the question with the question ID associated with the answer reception web page request.

  Subsequently, the user terminal 3 receives a web page for accepting answers from the knowledge storage server 2. Subsequently, the user terminal 3 obtains an answer content input to the question from the user via the answer acceptance web page, and then detects an answer posting request. This answer posting request is made by selecting a posting button provided on the answer acceptance web page. This answer posting request includes a user ID for specifying the user of the user terminal 3. When the user terminal 3 detects the answer posting request, the user terminal 3 transmits answer posting request data for requesting the answer posting to the knowledge storage server 2. This answer posting request data includes at least a question ID for specifying the user of the user terminal 3 and the answer contents.

  Upon receiving the response posting request data, the response receiving unit 12 generates a response ID. The answer receiving unit 12 stores the generated answer ID in the question DB 22 in association with at least the answer contents and the question ID included in the answer posting request data.

  Note that the answer reception unit 12 refers to the deadline flag in the question DB 22, and for a question whose deadline flag value is “1”, the answer is closed when a request for a web page for accepting an answer is received. Send a web page to that effect.

  The answer selection receiving unit 13 acquires, from the user terminal 3, various types of information related to answers that are answers to the questions among the answers corresponding to the questions posted by the user. Below, the process of the answer selection reception part 13 and the process of the user terminal 3 are demonstrated concretely. Here, it is assumed that the user of the user terminal 3 selects the best answer among a plurality of questions.

  First, the answer selection receiving unit 13 receives a request for a web page for answer selection reception from the user terminal 3. Here, a question ID is associated with a request for a web page for answer selection reception. Subsequently, the answer selection receiving unit 13 transmits to the user terminal 3 an answer selection receiving web page corresponding to the question with the question ID associated with the answer selection receiving web page request.

  Subsequently, the user terminal 3 receives the answer selection reception web page from the knowledge storage server. Subsequently, the user terminal 3 transmits the question ID and the selected answer ID to the knowledge storage server 2 in response to the selection of the best answer via the answer selection reception web page. In response to receiving the question ID and the selected answer ID from the user terminal 3, the answer selection receiving unit 13 acquires the current time and determines the current time as the selected time. In addition, the answer selection receiving unit 13 refers to the answer DB 23, identifies a user ID corresponding to the received answer ID, and determines the user ID as a resolution user ID. Then, the answer selection receiving unit 13 updates the resolution user ID corresponding to the received question ID and the selection time among the question IDs stored in the answer DB 23 to the determined selection time and the resolution user ID. . In addition, the answer selection receiving unit 13 updates the value of the deadline flag related to the received question ID to 1 in the question DB 22, and closes the reception of answers.

  The difficulty level estimation unit 14 estimates the difficulty level of the question. Specifically, the difficulty level estimation unit 14 refers to the question DB 22, the user DB 21, and the answer DB 23, and for each of the plurality of questions, the knowledge level corresponding to the user who answered the question and matches the category to which the question belongs The knowledge level of the category to be specified is specified. Subsequently, the difficulty level estimation unit 14 adds up the number of users who have posted answers for each specified knowledge level. Subsequently, the difficulty level estimation unit 14 specifies the knowledge level having the largest number of users in the aggregation result for each of the plurality of questions, and estimates the difficulty level based on the knowledge level. For example, the difficulty level estimation unit 14 sets a value one higher than the value of the knowledge level with the largest number of users as the difficulty level. Subsequently, the difficulty level estimation unit 14 updates the difficulty level stored in the question DB 22 to the estimated difficulty level for each of the plurality of questions. In addition, the difficulty level estimation unit 14 passes the question ID of the question whose difficulty level is estimated and the estimated difficulty level to the knowledge level estimation unit 15.

  The process of the difficulty level estimation part 14 is demonstrated referring a figure. For example, in the question DB 22 of FIG. 4, the number of users is totaled for each knowledge level for the question with the question ID “123”. The difficulty level estimation unit 14 estimates that the difficulty level of the question corresponding to the question ID is 4 when the knowledge level with the largest number of users is 3 as a result of aggregation. Then, the difficulty level estimation unit 14 updates the difficulty level corresponding to the question ID “123” of the question DB 22 from “blank” to “4”.

Here, the difficulty level estimation unit 14 may exclude the aggregate value of the user having a low knowledge level in the aggregated result. For example, this is to exclude a case where a user who has no knowledge responds as soon as possible, or a case where the user answers without knowing.
The difficulty level estimation unit 14 repeats the estimation of the difficulty level of the question periodically (for example, once every hour).

  The knowledge level estimation unit 15 refers to the question DB 22 and the answer DB 23, and estimates the knowledge level related to the category to which the question belongs for the solution user ID corresponding to the question for which the difficulty level is set based on the difficulty level. To do. Subsequently, the knowledge level estimation unit 15 updates the knowledge level related to the category of the user ID that matches the solution user ID in the user DB 21. The knowledge level estimation unit 15 does not update the knowledge level when the estimated knowledge level is lower than the knowledge level stored in the user DB 21.

  Here, the knowledge level estimation part 15 repeats estimation of a user's knowledge level regularly (for example, once per hour). In addition, the knowledge level estimation unit 15 selects a solution user ID of a question whose selection time of the answer DB 23 is within a predetermined time (for example, within one hour) from the current time, and a solution user corresponding to the question whose degree of difficulty has been updated. To do.

  In the above description, after the difficulty level estimation unit 14 estimates and updates the difficulty level, the knowledge level estimation unit 15 estimates and updates the knowledge level using the updated difficulty level. The order of processing is not limited to this order. For example, after the knowledge level estimation unit 15 estimates and updates the knowledge level, the difficulty level estimation unit 14 may perform estimation and update of the difficulty level using the updated knowledge level.

  The question distribution unit 16 refers to the question DB 22 and extracts a question for which the difficulty level is set and the deadline flag is a null value. And the question delivery part 16 specifies user ID of the knowledge level corresponding to the difficulty level of the extracted question with reference to user DB21, and delivers the extracted question to the user of the specified user ID. . For example, the question distribution unit 16 refers to the user DB 21 and specifies a user ID of a knowledge level that is related to the category associated with the extracted question and matches the difficulty level of the question. In addition, although the question delivery part 16 decided to identify the user ID of the knowledge level relevant to the category linked | related with the extracted question, and corresponded with the difficulty of the said question, it is not restricted to this. For example, the question distribution unit 16 may specify a user who is related to the category associated with the extracted question and has a knowledge level equal to or higher than the difficulty level of the question.

  Here, the question distribution unit 16 may transmit a part of the extracted question to the identified user or distribute the extracted question to a part of the identified user. The question distribution unit 16 may refer to the user's mail address stored in advance in the storage unit 20 and distribute the question by e-mail.

[Configuration of user terminal 3]
Similar to the knowledge storage server 2, the user terminal 3 is configured by one or a plurality of general computers, and includes a control unit and a storage unit. As described above, the user terminal 3 receives the question acceptance web page and the answer acceptance web page from the knowledge storage server 2, and accepts input from the user via these web pages. When the user terminal 3 detects the posting request, the user terminal 3 transmits posting request data including information input together with the posting request to the knowledge storage server 2. The user terminal 3 that transmitted the question is different from the user terminal 3 that transmitted the answer.

[Operation]
Next, the operation of the knowledge storage system 1 will be described with reference to FIGS.

  FIG. 6 is a flowchart showing a flow of a question, answer, and answer selection reception process executed by the knowledge storage server 2. In this flowchart, a flow of processing from when one question is received until an answer is selected will be described. It is assumed that a plurality of processes are executed corresponding to a plurality of questions.

The question reception unit 11 of the knowledge storage server 2 determines whether or not a question has been acquired from the user terminal 3 (step S1). When this determination is YES, the question reception unit 11 moves the process to step S2, and when this determination is NO, the question reception unit 11 re-executes step S1.
The question receiving unit 11 of the knowledge storage server 2 stores the question acquired from the user terminal 3 in the question DB 22 (step S2).

The answer reception unit 12 of the knowledge storage server 2 determines whether an answer has been acquired from the user terminal 3 (step S3). If this determination is YES, the answer receiving unit 12 moves the process to step S4, and if this determination is NO, the answer receiving unit 12 moves the process to step S5.
The answer reception unit 12 of the knowledge storage server 2 stores the answer acquired from the user terminal 3 in the answer DB 23 (step S4).

  The answer selection receiving unit 13 of the knowledge storage server 2 determines whether or not an answer is selected from the user terminal 3, that is, whether or not the answer ID of the answer selected as the answer to the question is acquired from the user terminal 3. Is determined (step S5). If this determination is YES, the answer selection receiving unit 13 moves the process to step S6, and if this determination is NO, the answer selection receiving unit 13 moves the process to step S3.

  When the answer selection receiving unit 13 of the knowledge storage server 2 acquires the answer ID of the answer selected as the answer to the question, the answer DB 23 stores the user ID of the user who posted the answer as the solution user ID in the answer DB 23 ( Step S6).

  FIG. 7 is a flowchart showing the flow of the difficulty level estimation process and the knowledge level estimation process executed by the knowledge storage server 2.

The difficulty level estimation unit 14 of the knowledge storage server 2 estimates the difficulty level of the question. Specifically, the difficulty level estimation unit 14 refers to the question DB 22, the user DB 21, and the answer DB 23, and for each of a plurality of questions, is a knowledge level corresponding to the user who answered the question, and the category to which the question belongs Is identified, and the number of users who have posted answers is counted for each identified knowledge level (step S11).
The difficulty level estimation unit 14 of the knowledge storage server 2 identifies the knowledge level having the largest number of users in the total result for each of the plurality of questions, and estimates the difficulty level of the question based on the knowledge level (step S12). .
The difficulty level estimation unit 14 of the knowledge storage server 2 stores the estimated difficulty level in the question DB 22 (step S13).

The knowledge level estimation unit 15 of the knowledge storage server 2 refers to the question DB 22 and the answer DB 23, and determines the knowledge level related to the category to which the question belongs for the solution user ID corresponding to the question with the updated difficulty level. (Step S14).
The knowledge level estimation unit 15 of the knowledge storage server 2 updates the knowledge level related to the category of the user ID that matches the solution user ID in the user DB 21 (step S15).

The control unit 10 of the knowledge storage server 2 determines whether an end operation has been received from the administrator of the knowledge storage server 2 via the input device (step S16). When this determination is YES, the control unit 10 ends this flowchart, and when this determination is NO, the control unit 10 shifts the processing to step S16.
The control unit 10 of the knowledge storage server 2 determines whether or not a predetermined time (for example, 1 hour) has elapsed since the knowledge level was updated in step S15 (step S17). When this determination is YES, the control unit 10 moves the process to step S11, and when this determination is NO, the control unit 10 re-executes step S16.

  As described above, in the knowledge storage system 1 according to the present embodiment, the knowledge storage server 2 refers to the user DB 21 and the answer DB 23 by the difficulty level estimation unit 14, and the user who posted the answer for each of a plurality of questions. The number is counted for each knowledge level, the difficulty level is estimated based on the knowledge level with the largest number of users in the counting result, and the difficulty level of the question DB 22 is updated. In addition, the knowledge accumulation server 2 refers to the question DB 22 and the answer DB 23 by the knowledge level estimation unit 15 and determines the knowledge level of the user who has posted the selected answer corresponding to the question for which the difficulty level is set. Based on the degree, the knowledge level of the user is updated in the user DB 21.

  As described above, the knowledge storage server 2 estimates the difficulty level based on the knowledge level having the largest number of users as a result of counting the users who have posted the answers for each knowledge level. In other words, in the question answering service, users who try to answer questions are likely to try difficult questions to reveal their knowledge level. The difficulty of the question can be specified. In addition, it is considered that the user of the answer selected in this question is excellent in a plurality of answers, that is, has a high knowledge level. Thereby, the knowledge accumulation server 2 can automatically adjust the difficulty level of the question and the knowledge level of the user. Therefore, the knowledge accumulation server 2 estimates the difficulty level of the unresolved question, and identifies the user having the knowledge level corresponding to the difficulty level. Therefore, the knowledge accumulation server 2 identifies the user who is likely to solve the unresolved question. be able to.

  In addition, the knowledge storage server 2 refers to the question DB 22, the answer DB 23, and the user DB 21 by the difficulty level estimation unit 14, and for each of a plurality of questions, sets the number of users who have posted answers to the question to the category to which the question belongs. Aggregation is performed for each knowledge level of the corresponding user, the difficulty level is estimated based on the knowledge level with the largest number of users in the aggregation result, and the difficulty level of the question DB 22 is updated. In addition, the knowledge storage server 2 refers to the question DB 22 and the answer DB 23 by the knowledge level estimation unit 15, and determines the knowledge level corresponding to the category to which the question belongs of the user who has posted the selected answer corresponding to the question. Based on the difficulty level related to the question, the knowledge level of the user is updated in the user DB 21.

  As described above, the knowledge storage server 2 determines the difficulty level of the question and the knowledge level of the user for each category, so that the difficulty level and the knowledge level are estimated for each category. Estimation and knowledge level estimation can be performed with high accuracy.

  In addition, the knowledge storage server 2 updates the knowledge level of the user who has posted the selected answer corresponding to the question whose degree of difficulty is updated by the knowledge level estimation unit 15. Moreover, after the knowledge level is updated by the knowledge level estimation unit 15 by the difficulty level estimation unit 14, the knowledge storage server 2 estimates the difficulty level of each of the plurality of questions.

  As described above, the knowledge storage server 2 estimates the user's knowledge level based on the difficulty level of the question and also estimates the difficulty level of the question based on the knowledge level. be able to. Thereby, the knowledge level corresponding to the difficulty level can be selected with high accuracy.

  The knowledge storage server 2 repeatedly executes the estimation of the difficulty level and the update of the estimated difficulty level by the difficulty level estimation unit 14, and the knowledge level estimation unit 15 estimates the knowledge level. Repeat knowledge level update.

  As described above, the knowledge accumulation server 2 repeats the estimation of the difficulty level of the question and the estimation of the knowledge level of the user who has replied, thereby optimizing the knowledge level and using the optimized knowledge level, The estimation accuracy of the difficulty level can be improved.

  The knowledge storage server 2 periodically executes difficulty estimation and update of the estimated difficulty by the difficulty estimation unit 14, and knowledge level estimation and estimation by the knowledge level estimation unit 15. Periodically update the knowledge level.

  As described above, the knowledge accumulation server 2 can estimate the difficulty level of unresolved questions at an early stage by appropriately setting the interval for periodically executing the processing, and can quickly resolve the unresolved problems. Can lead to a solution.

  As mentioned above, although embodiment of this invention was described, this invention is not restricted to embodiment mentioned above. The effects described in the embodiments of the present invention are only the most preferable effects resulting from the present invention, and the effects of the present invention are limited to those described in the embodiments of the present invention. is not.

  For example, in the present embodiment, the case where the knowledge storage server 2 is realized as a single server has been described as an example. However, the functions of the knowledge storage server 2 are implemented by being distributed to a plurality of servers. It is also possible to realize the function of the knowledge storage server 2 by cooperating as a whole. For example, a server as a storage device includes a user DB 21, a question DB 22, and an answer DB 23, and the knowledge storage server 2 includes a question accepting unit 11, an answer accepting unit 12, an answer selection accepting unit 13, a difficulty level estimating unit 14, a knowledge level. You may make it provide the estimation part 15 and the question delivery part 16. FIG.

  In the present embodiment, the question DB 22 may store, for example, a deadline time for closing the reception of answers to the question in association with the user ID. In this case, the answer reception unit 12 refers to the deadline time of the question DB 22 and transmits a web page indicating that the answer is deadline when the current time is later than the deadline time. The method of closing the answer reception is not limited to this.

DESCRIPTION OF SYMBOLS 1 Knowledge storage system 2 Knowledge storage server 10 Control part 11 Question reception part 12 Answer reception part 13 Answer selection reception part 14 Difficulty level estimation part 15 Knowledge level estimation part 16 Question distribution part 20 Storage part 21 User DB
22 Question DB
23 Answer DB
3 User terminal

Claims (9)

An estimation device for estimating a difficulty level of a question and a knowledge level of a user in a question answering service,
User information storage means for storing user identification information for identifying a user and the knowledge level of the user in association with each other;
Question information storage means for storing the question identification information for identifying the question, the question content, and the difficulty level in association with each other;
Answer information storage means for storing the question identification information in association with user identification information of a user who has posted an answer to the question corresponding to the question identification information;
A selection information storage means for associating and storing the question identification information and user identification information of a user who has posted an answer selected as a solution to the question corresponding to the question identification information;
With reference to the answer information storage means and the user information storage means, for each of a plurality of questions, the number of users who have posted answers is counted for each knowledge level, and based on the knowledge level with the largest number of users in the counting result, A difficulty level estimating means for estimating the difficulty level and updating the difficulty level of the question information storage means;
With reference to the question information storage means and the selection information storage means, the knowledge level of the user who posted the selected answer corresponding to the question for which the difficulty level is set is estimated based on the difficulty level, Knowledge level estimating means for updating the knowledge level of the user in the user information storage means;
An estimation apparatus comprising: The user information storage means stores the user identification information, a category, and the knowledge level in association with each other,
The question information storage means stores the question identification information, the question content, the category, and the difficulty level in association with each other,
The difficulty level estimation means refers to the question information storage means, the answer information storage means, and the user information storage means, and for each of a plurality of questions, the number of users who have posted an answer to the question, the category to which the question belongs For each knowledge level of users corresponding to the above, based on the knowledge level with the largest number of users in the total result, estimating the difficulty level, updating the difficulty level of the question information storage means,
The knowledge level estimation means refers to the question information storage means and the selection information storage means, the knowledge level corresponding to the category to which the question belongs, of the user who posted the selected answer corresponding to the question, Estimating based on the degree of difficulty related to the question, and updating the knowledge level of the user in the user information storage means,
The estimation apparatus according to claim 1. The knowledge level estimation means updates the knowledge level for a user who has posted the selected answer corresponding to the question whose degree of difficulty has been updated.
The estimation apparatus according to claim 1 or 2. The difficulty level estimation unit estimates the difficulty level of each of the plurality of questions after the knowledge level is updated by the knowledge level estimation unit.
The estimation apparatus in any one of Claim 1 to 3. The difficulty level estimation means repeatedly executes the estimation of the difficulty level and the update of the estimated difficulty level,
The knowledge level estimation means repeatedly executes the estimation of the knowledge level and the update of the estimated knowledge level.
The estimation apparatus according to claim 1. The difficulty level estimation means periodically executes the estimation of the difficulty level and the update of the estimated difficulty level,
The knowledge level estimation means periodically performs the estimation of the knowledge level and the update of the estimated knowledge level.
The estimation apparatus according to claim 5. An estimation device that is communicably connected to a storage device and estimates a difficulty level of a question and a knowledge level of a user in a question answering service,
The storage device stores user identification information for identifying a user and a user information storage unit that associates and stores the knowledge level of the user,
Question information storage means for storing the question identification information for identifying the question, the question content, and the difficulty level in association with each other;
Answer information storage means for storing the question identification information in association with user identification information of a user who has posted an answer to the question corresponding to the question identification information,
The estimation device includes:
A selection information storage means for associating and storing the question identification information and user identification information of a user who has posted an answer selected as a solution to the question corresponding to the question identification information;
With reference to the answer information storage means and the user information storage means, for each of a plurality of questions, the number of users who have posted answers is counted for each knowledge level, and based on the knowledge level with the largest number of users in the counting result, A difficulty level estimating means for estimating the difficulty level and updating the difficulty level of the question information storage means;
With reference to the question information storage means and the selection information storage means, the knowledge level of the user who posted the selected answer corresponding to the question for which the difficulty level is set is estimated based on the difficulty level, Knowledge level estimating means for updating the knowledge level of the user in the user information storage means;
An estimation apparatus comprising: An estimation method for estimating a difficulty level of a question and a knowledge level of a user in a question answering service,
The server
User information storage means for storing user identification information for identifying a user and the knowledge level of the user in association with each other;
Question information storage means for storing the question identification information for identifying the question, the question content, and the difficulty level in association with each other;
Answer information storage means for storing the question identification information in association with user identification information of a user who has posted an answer to the question corresponding to the question identification information;
Selection information storage means for storing the question identification information in association with user identification information of a user who has posted an answer selected as a solution to the question corresponding to the question identification information,
The estimation method is:
With reference to the answer information storage means and the user information storage means, for each of a plurality of questions, the number of users who have posted answers is counted for each knowledge level, and based on the knowledge level with the largest number of users in the counting result, A difficulty level estimation step of estimating the difficulty level and updating the difficulty level of the question information storage means;
With reference to the question information storage means and the selection information storage means, the knowledge level of the user who posted the selected answer corresponding to the question for which the difficulty level is set is estimated based on the difficulty level, A knowledge level estimation step of updating a knowledge level related to the user in the user information storage means;
The estimation method that the computer executes. A program for causing a computer to execute an estimation of a difficulty level of a question and a knowledge level of a user in a question answering service,
The server
User information storage means for storing user identification information for identifying a user and the knowledge level of the user in association with each other;
Question information storage means for storing the question identification information for identifying the question, the question content, and the difficulty level in association with each other;
Answer information storage means for storing the question identification information in association with user identification information of a user who has posted an answer to the question corresponding to the question identification information;
Selection information storage means for storing the question identification information in association with user identification information of a user who has posted an answer selected as a solution to the question corresponding to the question identification information,
The program is
With reference to the answer information storage means and the user information storage means, for each of a plurality of questions, the number of users who have posted answers is counted for each knowledge level, and based on the knowledge level with the largest number of users in the counting result, A difficulty level estimation step of estimating the difficulty level and updating the difficulty level of the question information storage means;
With reference to the question information storage means and the selection information storage means, the knowledge level of the user who posted the selected answer corresponding to the question for which the difficulty level is set is estimated based on the difficulty level, A knowledge level estimation step of updating a knowledge level related to the user in the user information storage means;
A program that causes a computer to execute.

Images