Know-how management method and information processing device

Abstract

By using machine learning and other methods, we can facilitate the time-series management of know-how and increase the reliability of the accumulated know-how. [Solution] The method includes acquiring know-how information, identifying the technical field of the know-how information, and independently performing version control for each identified technical field of multiple pieces of know-how information.

Description

Technical Field

[0001] This disclosure relates to a know-how management method and an information processing apparatus.

Background Art

[0002] Patent Document 1 discloses a technique for generating a dialogue bot specialized in a given technical field by using a large language model based on the given technical field.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a dialogue system, it is conceivable to obtain and display one or more know-how information items that can be answers to an input question from a database. However, in Patent Document 1, a method for managing know-how information in chronological order has not been sufficiently studied.

[0005] An object of this disclosure is to facilitate chronological management of know-how and improve the reliability of accumulated know-how by using machine learning or the like.

Means for Solving the Problems

[0006] A know-how management method according to an embodiment of this disclosure includes: when obtaining know-how information, specifying the technical field of the know-how information; and performing version management of a plurality of know-how information items independently for each specified technical field. and

Effects of the Invention

[0007] According to this disclosure, by using machine learning and other means, it is possible to facilitate the time-series management of know-how and increase the reliability of the accumulated know-how. [Brief explanation of the drawing]

[0008] [Figure 1] This is a block diagram showing the configuration of an information processing device according to one embodiment of the present disclosure. [Figure 2] This flowchart shows an example of operation of an information processing device according to one embodiment of the present disclosure. [Modes for carrying out the invention]

[0009] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings. In each drawing, parts having the same configuration or function are denoted by the same reference numerals. In the description of this embodiment, redundant descriptions of the same parts may be omitted or simplified as appropriate.

[0010] Referring to Figure 1, the configuration of the information processing device 1 according to one embodiment of this disclosure will be described.

[0011] The information processing device 1 comprises a control unit 10, a storage unit 20, an input unit 30, and an output unit 40.

[0012] The control unit 10 includes one or more processors, one or more dedicated circuits, or a combination thereof, and executes predetermined processing. The processor is a general-purpose processor such as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit), or a dedicated processor specialized for a specific processing. The dedicated circuit is, for example, an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). The control unit 10 executes various processing related to the operation of the information processing device 1 and controls each part of the information processing device 1.

[0013] The storage unit 20 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or at least two combinations thereof. The storage unit 20 stores data used for the operation of the information processing device 1 and data obtained by the operation of the information processing device 1.

[0014] The input unit 30 includes one or more input interfaces. The input interfaces are, for example, physical keys, capacitive keys, pointing devices, touchscreens integrated with a display, or microphones that accept voice input. The input unit 30 accepts operations to input information used for the operation of the information processing device 1.

[0015] The output unit 40 includes one or more output interfaces. The output interface is, for example, a connection interface to an external or built-in display or external output device that outputs information as images or videos. The display is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display. The output unit 40 outputs information obtained by the operation of the information processing device 1.

[0016] The following describes a know-how management method according to one embodiment of this disclosure.

[0017] When the control unit 10 acquires new know-how information via the input unit 30, it identifies the technical field to which the know-how information belongs. The technical field may be stored in the storage unit 20 in advance. The technical field may be, for example, "safety technology" or "methods for formulating employee rules." When acquiring new know-how information, the control unit 10 may also acquire information on the technical field to which the know-how information belongs, or it may identify the technical field to which the know-how information belongs from the title or content of the know-how information. The technical field may be identified, for example, by performing machine learning using data linking the title or content of the know-how information with the technical field to which it belongs as training data, and then identifying the technical field based on the generated trained model.

[0018] The control unit 10 performs version management of know-how information for each technical field. The control unit 10 may perform version management by setting the technical field of one or more specific know-how information as the first technical field and the other technical fields as the second technical field. That is, for know-how belonging to technical fields other than the technical field of specific know-how information, all of them may be collectively subject to version management.

[0019] When the control unit 10 newly acquires know-how information belonging to a specific technical field, it may determine whether the know-how information is appropriate. For the above judgment criteria, for example, a skill map of the know-how information provider may be used. The validity may be determined by whether the skill map of the know-how information provider is equal to or greater than a predetermined threshold. The skill map includes, but is not limited to, years of service, job position, etc. For example, for a specific technical field, when the years of service of the know-how information provider are equal to or greater than a predetermined threshold, the control unit 10 may determine that the know-how information is appropriate. On the other hand, when the years of service of the know-how information provider are less than a predetermined threshold, the determination of the validity of the know-how information may be requested from one or more predetermined numbers of experts. The experts may be, for example, those with years of service equal to or greater than a predetermined threshold.

[0020] When the control unit 10 determines that the know-how information is appropriate, it stores the know-how information as the latest version of the information. On the other hand, when the control unit 10 determines that the know-how information is not appropriate, it may not store the know-how information, or it may store the know-how information as low-reliability information.

[0021] When the control unit 10 acquires a question regarding the technical field of the accumulated know-how information, it calculates the degree of similarity with the stored know-how information. Then, based on the know-how information with a high degree of similarity, an answer to the question may be generated and output to the output unit 40. For example, when a question regarding a defect case is input, the control unit 10 may predict the occurring defect and generate an answer based on the know-how information (such as defect cases) with a high degree of similarity to the defect case. The generation of the answer may be executed using a large language model (LLM: Large Language Model) that has learned the accumulated know-how information or RAG (Retrieval Augmented Generation) that uses the accumulated know-how information as a database.

[0022] Hereinafter, with reference to FIG. 2, a know-how management method using the information processing apparatus 1 according to an embodiment of the present disclosure will be described.

[0023] In step S1, the control unit 10 acquires new know-how information via the input unit 30. When receiving the input of know-how information, the control unit 10 may display the technical field stored in the storage unit 20 on the output unit 40 and receive a selection input of the technical field to which the know-how information belongs.

[0024] In step S2, the control unit 10 identifies the technical field to which the new know-how information acquired in step S1 belongs. Although there is no particular limitation on the identification method, for example, the control unit 10 may perform machine learning using the linking data between the title or content of the know-how information and the belonging technical field as teacher data, and identify it as the technical field to which the new know-how information belongs based on the generated learned model.

[0025] Also, when receiving the input of the technical field to which the new know-how information belongs in step S1, the input technical field may be identified as the technical field to which the new know-how information belongs.

[0026] In step S3, the control unit 10 determines whether the know-how information acquired in step S1 falls under a pre-set specific technical field of know-how information. If it falls under a specific technical field of know-how information (step S3: Yes), the control unit 10 determines that the know-how information belongs to the first technical field (step S4) and proceeds to step S6.

[0027] If the specific know-how information does not fall under a technical field (Step S3: No), the control unit 10 determines that the know-how information belongs to a second technical field (Step S5) and proceeds to Step S10.

[0028] In step S6, the control unit 10 determines the validity of the know-how information that was determined to belong to the first technical field in step S3. Specifically, the control unit 10 determines the validity of the know-how information based on the length of service of the know-how information provider. If the length of service of the know-how information provider is greater than or equal to a predetermined threshold (step S6: Yes), the know-how information is determined to be valid (step S7), and the process proceeds to step S10. If the length of service of the know-how information provider is less than the predetermined threshold (step S6: No), the control unit 10 requests one or more predetermined number of experts to determine the validity of the know-how information.

[0029] In step S8, the control unit 10 receives input from the expert regarding the validity of the know-how information. If the control unit 10 receives input from the expert indicating that the know-how information is valid (step S8: Yes), it determines that the know-how information is valid (step S7) and proceeds to step S10. If the control unit 10 receives input from the expert indicating that the know-how information is not valid (step S8: No), it determines that the know-how information is not valid (step S9) and terminates the process without storing the know-how information.

[0030] In step S10, the control unit 10 stores the know-how information as the latest version of the information in the technical field to which the know-how information belongs, and terminates the process.

[0031] By adopting the above method, it becomes possible to manage the version of know-how information for each technical field, making it easier to manage know-how chronologically. Furthermore, for technical fields where caution is required when updating know-how information, such as safety measures information, updates can be performed using only highly reliable know-how information.

[0032] This disclosure is not limited to the embodiments described above. For example, multiple blocks described in the block diagram may be combined, or a single block may be divided. Instead of executing multiple steps described in the flowchart in chronological order as described, they may be executed in parallel or in a different order, depending on the processing capacity of the device performing each step, or as necessary. Other modifications are possible without departing from the spirit of this disclosure. [Explanation of Symbols]

[0033] 1. Information Processing Device 10 Control Unit 20 Memory section 30 Input section 40 Output section

Claims

1. A method for managing know-how that is executed by an information processing device, Upon acquiring know-how information, the technical field of the said know-how information is identified, Version control of multiple know-how information items is performed independently for each specified technical field, A method for managing know-how, including the following.

2. Identifying the aforementioned technical field involves identifying the aforementioned technical field of the know-how information based on a trained model generated by machine learning. The know-how management method described in claim 1.

3. When new know-how information is acquired in a specific technical field, it is necessary to determine whether or not such know-how information is valid. If the know-how information is deemed valid, it will be stored as the latest version of the information; if the know-how information is deemed invalid, it will not be stored. The know-how management method according to claim 1, further comprising:

4. The determination of whether or not the above is valid is made based on the skill map of the know-how information provider. The know-how management method according to claim 3, wherein the skill map includes information on the length of service of the know-how information provider.

5. An information processing device, Upon acquiring know-how information, the technical field of the said know-how information is identified, An information processing device equipped with a control unit that independently performs version control of multiple know-how information for each specified technical field.

Images