Information processing apparatus, information processing method, and information processing program

Abstract

To reduce the burden of users in OJT.SOLUTION: An information processing apparatus 100 includes: an acquisition unit 121 which acquires questions from a user who receives training; a determination unit 122 which determines the presence or absence of a question that is similar to the question acquired by the acquisition unit 121; a selection unit 123 which selects, when the absence is determined by the determination unit 122, a user who answers the question based on the question; and an output unit 124 which outputs the question to the user selected by the selection unit 123 to answer the question.SELECTED DRAWING: Figure 3

Description

Technical Field

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

Background Art

[0002] Conventionally, there is a technique (for example, Patent Document 1) for appropriately grasping the situation of skill improvement of OJT (On the Job Training) trainees.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the burden on the user may not be reduced during OJT. For example, the labor may be concentrated only on the user who gives guidance to the user receiving OJT, and the burden may become excessive. Also, for example, since the content of the training for the user receiving OJT is determined by the user who gives guidance, the training cannot be standardized, and excessive labor may be required to improve the ability of the user receiving OJT to a certain level. Examples of the problems to be solved by the present invention include the above-mentioned problems.

[0005] The present invention has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program for reducing the burden on the user during OJT.

Means for Solving the Problems

[0006] In order to solve the above-described problems and achieve the object, an information processing apparatus according to the present invention includes an acquisition unit that acquires a question from a user who receives training, a determination unit that determines whether there is a question similar to the question acquired by the acquisition unit, a selection unit that selects a user who answers the question based on the question when it is determined by the determination unit that there is no such question, and an output unit that outputs the question to the user who answers the question selected by the selection unit.

Effect of the Invention

[0007] According to the present invention, the burden on the user during OJT can be reduced.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Mode for Carrying Out the Invention

[0009] Hereinafter, with reference to the drawings, embodiments of the information processing apparatus, information processing method, and information processing program according to the present application will be described in detail. Note that the present invention is not limited by this embodiment. In the description of the drawings, the same parts are denoted by the same reference numerals, and redundant explanations are omitted.

[0010] 〔1. Overview〕 First, with reference to FIGS. 1 and 2, an overview of the processing performed by the information processing apparatus 100 according to the embodiment will be described. FIG. 1 is a diagram showing the prior art. FIG. 2 is a diagram showing an overview of the processing performed by the information processing apparatus 100 according to the embodiment. Conventionally, as shown in FIG. 1, OJT is a process in which an OJT trainer (a user who conducts OJT guidance) allows an OJT trainee (a user who receives OJT) to experience actual work while providing guidance.

[0011] However, in conventional OJT, the burden on the user may not be reduced. For example, since various responses such as guidance, follow-up, and question handling for the user receiving OJT are required, the labor of the user who conducts OJT guidance may become excessive. Also, for example, since the training content for the user receiving OJT is determined by the user who conducts OJT, the training content cannot be standardized, and excessive labor may be required to improve the ability of the user receiving OJT to a certain level.

[0012] Therefore, as shown in FIG. 2, the information processing apparatus 100 enables an OJT trainee to refer to past question contents, and does not limit the response to the OJT trainee only to the OJT trainer, but allows other members of the department that has accepted the OJT trainee to perform the response as appropriate. That is, the information processing apparatus 100 acquires a question from a user who is receiving training, determines whether there is a question similar to the acquired question, and if it is determined that there is no such question, selects a user who answers the question based on the question, and outputs the question to the user who answers the selected question.

[0013] As a result, the information processing apparatus 100 determines whether there is a question similar to the question asked by the user receiving the training, and if not, selects an appropriate user who can answer the question asked by the user receiving the training and outputs the question, thereby reducing the burden on the user during OJT.

[0014] [2. Configuration of Information Processing Apparatus] Next, with reference to FIG. 3, the configuration of the information processing apparatus 100 will be described. FIG. 3 is a diagram showing an example of the configuration of the information processing apparatus 100. As shown in FIG. 3, the information processing apparatus 100 includes a communication unit 110, a control unit 120, and a storage unit 130. Note that each of these units may be held by a plurality of devices in a distributed manner. Hereinafter, the processing of each unit will be described.

[0015] The communication unit 110 is realized by a NIC (Network Interface Card) or the like, and enables communication between the control unit 120 and an external device via a telecommunication line such as a LAN (Local Area Network) or the Internet. For example, the communication unit 110 enables communication between the external device and the control unit 120.

[0016] The storage unit 130 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 130 includes a business information DB 131, a user information DB 132, and an information accumulation DB 133. Hereinafter, each unit included in the storage unit 130 will be described.

[0017] The business information DB 131 stores information related to business. For example, the business information DB 131 stores information such as a case ID, a case name, case information, a user in charge of the case, and skills related to the case as information related to business.

[0018] The user information DB 132 stores information about users. For example, the user information DB 132 stores information such as user ID, user name, user attributes, held qualifications, held skills, and assigned projects as information about users.

[0019] The information storage DB 133 stores information about questions. For example, the information storage DB 133 stores information such as question ID, question, answer to the question, user who asked the question, and user who gave the answer as information about questions.

[0020] Subsequently, the control unit 120 is realized by using a CPU (Central Processing Unit), NP (Network Processor), FPGA (Field Programmable Gate Array), etc., and executes a processing program stored in the memory. As shown in FIG. 3, the control unit 120 includes an acquisition unit 121, a determination unit 122, a selection unit 123, and an output unit 124. Hereinafter, each unit included in the control unit 120 will be described.

[0021] The acquisition unit 121 acquires a question from a user receiving training. For example, the acquisition unit 121 acquires free text input by the user receiving training to the user terminal. More specifically, the acquisition unit 121 acquires from the user terminal the free text "Please tell me the difference between the ○○ technology and the ×× technology of the infrastructure" input by the user receiving training to the user terminal. Although an example of a question related to skills has been given as the question acquired by the acquisition unit 121, the questions acquired by the acquisition unit 121 include, in addition to skills related to a specific field, questions related to projects, in-house rules, human relationships, etc., and are not particularly limited as long as they are questions that can be asked by the user receiving training.

[0022] The determination unit 122 determines whether there is a question similar to the question acquired by the acquisition unit 121. For example, the determination unit 122 determines whether there is a question similar to the question acquired by the acquisition unit 121 by clustering.

[0023] More specifically, the determination unit 122 vectorizes the question acquired by the acquisition unit 121 and the past questions stored in the information storage DB 133, and when the probability of belonging to a predetermined group exceeds a predetermined threshold as a result of clustering being performed on the question acquired and vectorized by the acquisition unit 121, it determines that there are similar questions. The detailed processing of the determination unit 122 will be described later in [3. Determination Processing].

[0024] When it is determined by the determination unit 122 that there is no such user, the selection unit 123 selects a user who answers the question based on the question. For example, the selection unit 123 selects, as the user who answers the question, a user who holds information corresponding to the question. More specifically, the selection unit 123 selects, as the user who answers the question, a user who holds the skill "infrastructure" corresponding to the question "I want to know the difference between the ○○ technology and the ×× technology of the infrastructure". Although an example of selection based on the correspondence between the question and the held skill has been given above, for example, the selection unit 123 can select information according to the purpose, such as user attributes, held skills, held qualifications, and assigned cases, as the information corresponding to the question.

[0025] For example, the selection unit 123 selects the user who answers the question using a model that has learned the relationship between the question and the user who answers the question. More specifically, the selection unit 123 inputs the question into a learning model that has learned the relationship between the question and the user who answers the question and outputs the user who answers the question when the question is input, and selects the output user as the user who answers the question. Note that the user selected as the user who answers the question may be one person or multiple persons.

[0026] The output unit 124 outputs the question to the user selected by the selection unit 123 to answer the question. For example, the output unit 124 notifies the user selected by the selection unit 123 to answer the question of the question acquired by the acquisition unit 121 by a predetermined notification method. Here, as an example of the predetermined notification method, SNS (Social Networking Service), email, etc. can be mentioned.

[0027] Also, when it is determined by the determination unit 122 that there is a similar question, the output unit 124 outputs an answer to the similar question to the user receiving the training. For example, when it is determined by the determination unit 122 that there is a similar question, the output unit 124 notifies the user receiving the training by a predetermined notification method of an answer to a past question "Please tell me the advantages and disadvantages of ○○ technology and ×× technology" that is similar to the question "Please tell me the difference between ○○ technology and ×× technology of the infrastructure" stored in the information storage DB 133 and acquired by the acquisition unit 121.

[0028] 〔3. Determination process〕 Next, with reference to FIG. 4, the determination process by the information processing apparatus 100 according to the embodiment will be described. FIG. 4 is a diagram showing an example of the determination process by the information processing apparatus 100 according to the embodiment. The determination unit 122 determines whether there is a question similar to the question acquired by the acquisition unit 121. For example, first, the determination unit 122 vectorizes the question acquired by the acquisition unit 121 and the questions stored in the information storage DB 133 using the frequency of appearance or the distributed representation of the words included in the questions, and classifies the vectorized questions into a plurality of groups by clustering.

[0029] Here, as a method of vectorizing using the frequency of appearance of words included in a question, TF-IDF (Term Frequency-Inverse Document Frequency) can be cited as an example. Also, as a method of vectorizing using the distributed representation of words included in a question, Word2Vec (Word to Vector) and BERT (Bidirectional Encoder Representations from Transformers) can be cited as examples.

[0030] Subsequently, the determination unit 122 performs dimensionality reduction on the vectorized questions. The dimensionality reduction is performed by methods such as PCA (Principal Component Analysis), t-SNE (t-Distributed Stochastic Neighbor Embedding), or UMAP (Uniform Manifold Approximation and Projection). Examples of the clustering algorithms that can be used include the K-Means method and HDBSCAN (Hierarchical Density Based Spatial Clustering of Applications with Noise).

[0031] For example, the determination unit 122 vectorizes the questions acquired by the acquisition unit 121 and the past questions stored in the information storage DB 133 using Word2Vec. Subsequently, the determination unit 122 performs dimensionality reduction on the vectorized questions using t-SNE, and then clusters them using the K-Means method and classifies them into multiple groups. For example, as shown in FIG. 4, the determination unit 122 classifies the questions into four groups and calculates the probability that the questions acquired by the acquisition unit 121 belong to each group.

[0032] Note that the determination unit 122 can accept inputs from the user or an external device and perform labeling of each group. For example, when the user interprets the classification result by the determination unit 122 and accepts the input of the correspondence between the group names and labels such as "Group A: Infrastructure", "Group B: Database", "Group C: Management Technology", "Group D: Claim Handling", the determination unit 122 labels each group. Note that the vectorization method, dimensionality reduction method, and clustering method are not limited to the above, and known methods can be combined and used according to the characteristics and purposes of the data.

[0033] Then, for questions where the probability of belonging to a predetermined group is equal to or greater than a predetermined threshold, the determination unit 122 determines that there are similar questions. For example, as shown in FIG. 4, when the probabilities of belonging to each group are 40% for group A, 72% for group B, 20% for group C, and 15% for group D as a result of clustering the question "XXXXXX" obtained by the acquisition unit 121 and vectorized, since the threshold value of 70% is exceeded for group B, the determination unit 122 determines that there are similar questions for the question "XXXXXX".

[0034] Also, for example, as shown in FIG. 4, when the probabilities of belonging to each group are 15% for group A, 25% for group B, 30% for group C, and 13% for group D as a result of clustering the question "YYYYYY" obtained by the acquisition unit 121 and vectorized, since none of the groups exceed the threshold value of 70%, the determination unit 122 determines that there are no similar questions for the question "YYYYYY".

[0035] 〔4. Selection process〕 Next, the selection process by the information processing apparatus 100 according to the embodiment will be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of the selection process by the information processing apparatus 100 according to the embodiment. When the determination unit 122 determines that there are no similar questions, the selection unit 123 selects, as the user who answers the question, the user who holds the information corresponding to the question.

[0036] For example, first, the selection unit 123 determines whether the question and the information held by the user (user attributes, held qualifications, held skills, assigned cases, etc.) correspond to each other from the relationship between the vectorized question and the information held by the user. For example, the selection unit 123 vectorizes the question and the information held by the user by an existing method such as TF-IDF or Word2Vec, and determines whether the question and the information held by the user correspond to each other by comparing the cosine similarity.

[0037] More specifically, when the cosine similarity between the question “I want to know the difference between the ○○ technology and the ×× technology of the infrastructure” input by the user receiving the training and the information “Owned skill: Infrastructure” possessed by the user is equal to or greater than a predetermined threshold value, the selection unit 123 determines that the question input by the user receiving the training corresponds to the information possessed by the user.

[0038] Then, as shown in FIG. 5, the selection unit 123 selects the user “User AAA” who possesses the information “Owned skill: Infrastructure” corresponding to the question “I want to know the difference between the ○○ technology and the ×× technology of the infrastructure” input by the user receiving the training as the user who answers the question. As another example, the selection unit 123 sorts the information possessed by the user in descending order of the cosine similarity with the question, and selects the user associated with the information possessed by the top predetermined number of users as the user who answers the question.

[0039] Note that, in the above example, the correspondence between the owned skill and the question is determined to select a user. However, the selection unit 123 can appropriately select information for determining whether it corresponds according to the question acquired by the acquisition unit 121. For example, for the question “What parts should be paid attention to in the ○○ project?”, the correspondence is determined for the information on the projects in charge of the user.

[0040] 〔5. Output process〕 Next, the output process by the information processing apparatus 100 according to the embodiment will be described with reference to FIGS. 6 and 7. FIGS. 6 and 7 are diagrams showing an example of the output process by the information processing apparatus 100 according to the embodiment. When the determination unit 122 determines that there is no similar question, the output unit 124 outputs the question to the user who answers the question selected by the selection unit 123.

[0041] For example, as shown in FIG. 6, the selection unit 123 notifies the user AAA selected by the selection unit 123 on the SNS of the question "I want to know the difference between the ○○ technology and the ×× technology of the infrastructure" of the user who receives the training acquired by the acquisition unit 121. Note that the answer given by the user AAA selected by the selection unit 123 to the question is stored in the information storage DB 133.

[0042] In this way, when there is no question similar to the question from the user who receives the training, the information processing apparatus 100 can reduce the burden on the user during OJT by selecting a user suitable for the answer from the content of the question and displaying the question.

[0043] As another example, when it is determined by the determination unit 122 that there is a similar question, the output unit 124 refers to the information storage DB 133 and outputs the answer to the similar question to the user who receives the training. For example, as shown in FIG. 7, the output unit 124 notifies the user who receives the training on the SNS of the answer "The advantages of the ○○ technology are ~~~ The disadvantages are ~~~ The advantages of the ×× technology are ~~~ The disadvantages are ~~~" to the question "I want to know the difference between the ○○ technology and the ×× technology" similar to the question of the user who receives the training. At this time, the output unit 124 may also output information such as the user who asked the similar question, the user who answered the similar question, and the date and time of the question and the answer together.

[0044] In this way, when there is a question similar to the question from the user who receives the training, the information processing apparatus 100 can reduce the burden on the user during OJT by displaying and answering the answer to the similar question.

[0045] 〔6. Flowchart〕 Next, the processing flow by the information processing apparatus 100 will be described with reference to FIG. 8. Note that each of the following steps can also be executed in a different order, and there may be processes that are omitted.

[0046] The acquisition unit 121 acquires a question from a user undergoing training (step S101). For example, the acquisition unit 121 acquires a free text input by the user undergoing training into the user terminal. Subsequently, the determination unit 122 analyzes the question acquired by the acquisition unit 121 (step S102). For example, the determination unit 122 analyzes the question acquired by the acquisition unit 121 by clustering.

[0047] Subsequently, the determination unit 122 determines whether there is a question similar to the question acquired by the acquisition unit 121 (step S103). For example, the determination unit 122 determines whether there is a similar question based on whether the probability that the question acquired by the acquisition unit 121 belongs to a predetermined group exceeds a predetermined threshold as a result of clustering.

[0048] Here, when it is determined by the determination unit 122 that there is no similar question (step S103: No), the selection unit 123 selects a user who answers the question based on the question acquired by the acquisition unit 121 (step S104). For example, the selection unit 123 selects, as the user who answers the question, a user who holds information corresponding to the question acquired by the acquisition unit 121.

[0049] Subsequently, the output unit 124 outputs the question to the user who answers the question selected by the selection unit 123 (step S105). For example, the output unit 124 notifies the user who answers the question selected by the selection unit 123 of the question acquired by the acquisition unit 121.

[0050] On the other hand, when it is determined by the determination unit 122 that there is a similar question (step S103: Yes), the output unit 124 outputs the answer to the similar question to the user undergoing training (step S106). The output unit 124 notifies the user undergoing training of the answer to the similar question.

[0051] 〔7. Effect〕 The information processing apparatus 100 according to the embodiment includes an acquisition unit 121 that acquires questions from a user receiving training, a determination unit 122 that determines whether there are questions similar to the questions acquired by the acquisition unit 121, and a selection unit 123 that selects a user who answers the questions based on the questions when the determination unit 122 determines that there are no such questions, and an output unit 124 that outputs the questions to the user selected by the selection unit 123 to answer the questions.

[0052] Thereby, when there are no questions similar to the questions from the user receiving training, the information processing apparatus 100 can reduce the burden on the user during OJT by selecting a user suitable for answering from the content of the questions and notifying the questions.

[0053] The determination unit 122 of the information processing apparatus 100 according to the embodiment determines whether there are questions similar to the questions acquired by the acquisition unit 121 by clustering. Thereby, the information processing apparatus 100 determines whether there are questions similar to the questions from the user receiving training from the result of clustering, and when there are no such questions, can reduce the burden on the user during OJT by selecting a user suitable for answering from the content of the questions and notifying the questions.

[0054] The selection unit 123 of the information processing apparatus 100 according to the embodiment selects, as the user who answers the questions, a user who holds information corresponding to the questions. Thereby, when there are no questions similar to the questions from the user receiving training, the information processing apparatus 100 can reduce the burden on the user during OJT by selecting a user who holds information corresponding to the questions and notifying the questions.

[0055] The selection unit 123 of the information processing apparatus 100 according to the embodiment selects a user who answers a question by using a model that has learned the relationship between the question and the user who answers the question. Thereby, when there is no question similar to the question from the user receiving the training, the information processing apparatus 100 selects a user who answers the question from the question by using the learning model and notifies the question, so that the burden on the user during OJT can be reduced.

[0056] When it is determined by the determination unit 122 that there is an answer, the output unit 124 of the information processing apparatus 100 according to the embodiment outputs the answer to the similar question to the user receiving the training. Thereby, when there is a question similar to the question from the user receiving the training, the information processing apparatus 100 can reduce the burden on the user during OJT by notifying the answer to the similar question.

[0057] 〔8. Hardware Configuration〕 The information processing apparatus 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. 9. FIG. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing apparatus 100. The computer 1000 has a form in which a CPU 1100, a RAM 1200, a ROM 1300, an auxiliary storage device 1400, a communication I / F (interface) 1500, and an input / output I / F (interface) 1600 are connected by a bus 1800.

[0058] The CPU 1100 operates based on a program stored in the ROM 1300 or the auxiliary storage device 1400 and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000, and the like.

[0059] The auxiliary storage device 1400 stores programs executed by the CPU 1100, data used by such programs, and the like. The communication I / F 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and sends the data generated by the CPU 1100 to other devices via a predetermined communication network.

[0060] The CPU 1100 controls output devices such as displays and printers, and input / output devices 1700 such as keyboards and mice via the input / output I / F 1600. The CPU 1100 acquires data from the input / output devices 1700 via the input / output I / F 1600. Also, the CPU 1100 outputs the generated data to the input / output devices 1700 via the input / output I / F 1600.

[0061] For example, when the computer 1000 functions as the information processing apparatus 100 according to the present embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 120 by executing the program loaded on the RAM 1200.

[0062] 〔9. Others〕 Although various embodiments have been described in detail in this specification with reference to the drawings, these multiple embodiments are examples and are not intended to limit the present invention to these multiple embodiments. The features described in this specification can be realized by various methods including various modifications and improvements based on the knowledge of those skilled in the art.

[0063] Also, the above-mentioned "parts (module, -er suffix, -or suffix)" can be read as units, means, circuits, etc. For example, the communication part (communication module), the control part (control module), and the storage part (storage module) can be read as a communication unit, a control unit, and a storage unit, respectively.

Explanation of Reference Numerals

[0064] 100 Information Processing Apparatus 110 Communication Unit 120 Control Unit 121 Acquisition Unit 122 Judgment Unit 123 Selection Unit 124 Output Unit 130 Memory Unit 131 Business Information DB 132 User Information DB 133 Information Storage DB

Claims

1. An acquisition unit that acquires questions from users undergoing training; A determination unit that determines whether there are questions similar to the questions acquired by the acquisition unit; A selection unit that, when the determination unit determines that there are none, selects a user who answers the question based on the question; An output unit that outputs the question to the user who answers the question selected by the selection unit An information processing apparatus characterized by comprising the above.

2. The information processing apparatus according to claim 1, wherein the determination unit determines whether there are questions similar to the questions acquired by the acquisition unit by clustering.

3. The information processing apparatus according to claim 1, wherein the selection unit selects, as the user who answers the question, a user who holds information corresponding to the question.

4. The information processing apparatus according to claim 1, wherein the selection unit selects a user who answers the question using a model that has learned the relationship between the question and the user who answers the question.

5. The information processing apparatus according to claim 1, wherein the output unit outputs, to the user undergoing training, an answer to the similar question when the determination unit determines that there is one.

6. A method executed by an information processing apparatus, comprising: An acquisition step of acquiring questions from users undergoing training; A determination step of determining whether there are questions similar to the questions acquired in the acquisition step; A selection step of selecting, when the determination step determines that there are none, a user who answers the question based on the question; An output step of outputting the question to the user who answers the question selected in the selection step An information processing method characterized by including the above.

7. An acquisition step of acquiring questions from users undergoing training; A determination step of determining whether there are questions similar to the questions acquired in the acquisition step; A selection step of selecting, when the determination step determines that there are none, a user who answers the question based on the question; An output step of outputting the question to the user who answers the question selected in the selection step An information processing program characterized by causing a computer to execute the above.

Images