Method and apparatus for generating XAI for human resource operations explaining prediction result in natural language

Abstract

Disclosed is a method, performed by a processor, for generating an XAI for human resource operations, which explains a prediction result in a natural language. The method for generating an XAI for human resource operations comprises the steps of: defining a specific issue related to human resource operations; and collecting data related to the specific issue; and applying the data to an explainable artificial intelligence model to output a prediction result in a natural language.

Description

Method and device for generating XAI for human resources work that explains prediction results in natural language

[0001] The present invention relates to explainable artificial intelligence, and more particularly, to a method and device for generating XAI for human resources that explains prediction results in natural language.

[0002] Explainable AI (XAI) refers to systems in which the output of an AI model can be explained in a human-friendly manner. In explainable AI, the output of an AI model is expressed in natural language. The introduction of explainable AI is also necessary in human resources processes such as hiring, assignment, transfer, performance evaluations, promotions, leave of absences, and dismissals.

[0003] The technical problem to be achieved by the present invention is to provide a method and device for generating XAI for human resources work that explains prediction results in natural language.

[0004] A method for generating XAI for human resources work that explains prediction results in natural language, performed by a processor according to an embodiment of the present invention, includes a step of defining a specific issue related to human resources work, a step of collecting data related to the specific issue, and a step of applying the data to an explainable artificial intelligence model to output a prediction result in natural language.

[0005] The above method for generating XAI for human resources work may further include a step of learning the artificial intelligence model using training data.

[0006] A method and device for generating XAI for human resources work that explains prediction results in natural language according to an embodiment of the present invention defines specific issues related to human resources work, applies data related to the specific issues to explainable artificial intelligence (XAI), and outputs prediction results in natural language, thereby enabling a user to more naturally accept the prediction results.

[0007] In order to more fully understand the drawings cited in the detailed description of the present invention, a detailed description of each drawing is provided.

[0008] FIG. 1 shows a block diagram of an XAI generation system for human resources work that explains prediction results in natural language according to an embodiment of the present invention.

[0009] Figure 2 shows a block diagram of the application module illustrated in Figure 1.

[0010] Figure 3 shows another block diagram of the application module illustrated in Figure 1.

[0011] Figure 4 shows a block diagram of the data management module illustrated in Figure 1.

[0012] Figure 5 shows a block diagram of the XAI / LLM model management module illustrated in Figure 1.

[0013] Figure 6 shows a block diagram of the prediction execution module illustrated in Figure 1.

[0014] FIG. 7 shows a flowchart of a method for generating XAI for human resources work that explains prediction results in natural language according to an embodiment of the present invention.

[0015] Specific structural or functional descriptions of embodiments according to the concept of the present invention disclosed in this specification are merely illustrative for the purpose of explaining embodiments according to the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and are not limited to the embodiments described in this specification.

[0016] Embodiments according to the concept of the present invention may have various modifications and take various forms, and thus, embodiments are illustrated in the drawings and described in detail in this specification. However, this is not intended to limit embodiments according to the concept of the present invention to specific disclosed forms, but rather includes all modifications, equivalents, or alternatives falling within the spirit and technical scope of the present invention.

[0017] While terms such as "first" or "second" may be used to describe various components, these components should not be limited by these terms. These terms are intended solely to distinguish one component from another. For example, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component, without departing from the scope of the invention.

[0018] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. Conversely, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions that describe the relationship between components, such as "between" and "directly between" or "adjacent to" and "directly adjacent to", should be interpreted similarly.

[0019] The terminology used herein is for the purpose of describing specific embodiments only and is not intended to limit the present invention. The singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, it should be understood that the terms "comprises" or "has" indicate the presence of a described feature, number, step, operation, component, part, or combination thereof, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0020] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

[0021] Hereinafter, the present invention will be described in detail by describing a preferred embodiment of the present invention with reference to the attached drawings.

[0022] FIG. 1 shows a block diagram of an XAI generation system for human resources work that explains prediction results in natural language according to an embodiment of the present invention.

[0023] Referring to Fig. 1, the XAI generation system for human resources work that explains prediction results in natural language includes an application module (1), a data management module (2), an XAI / LLM model management module (3), and a prediction execution module (4). The XAI generation system for human resources work that explains prediction results in natural language may be referred to as a device.

[0024] Figure 2 shows a block diagram of the application module illustrated in Figure 1.

[0025] Referring to FIGS. 1 and 2, the application module (1) includes a dataset management user interface, an XAI / LLM model management user interface, and a prediction execution user interface.

[0026] Figure 3 shows another block diagram of the application module illustrated in Figure 1.

[0027] Referring to FIGS. 1 and 3, the application module (1) illustrated in FIG. 3 further includes a user management user interface and a login interface, unlike FIG. 2.

[0028] Figure 4 shows a block diagram of the data management module illustrated in Figure 1.

[0029] Referring to FIGS. 1 and 4, the data management module (2) further includes a dataset input section, a dataset verification section, a dataset operation section, and a dataset query section.

[0030] Figure 5 shows a block diagram of the XAI / LLM model management module illustrated in Figure 1.

[0031] Referring to FIGS. 1 and 5, the XAI / LLM model management module (3) is divided into an XAI model management module and an LLM model management module. The XAI model management module includes an XAI model learning module. The XAI model learning module includes new model learning and model addition learning. New model learning and model addition learning can utilize a dataset.

[0032] The XAI model management module may additionally include additional pre-trained models. The XAI model management module may further include an XAI model query module.

[0033] The LLM Model Management module includes the LLM Model Training module, which further includes the Fine Tuning module.

[0034] The LLM model management module may further include pre-trained models. The LLM model management module may further include an LLM service connection module and an LLM model query module.

[0035] Figure 6 shows a block diagram of the prediction execution module illustrated in Figure 1.

[0036] Referring to Figures 1 and 6, the prediction execution module (4) processes a prediction request, outputs a prediction result, and stores the output result. To express the prediction result in a natural explanation, it processes a sentence generation request, generates a sentence, and stores the generated sentence.

[0037] The prediction execution module (4) integrates the generated sentences and output results to generate natural language expressed as a natural explanation.

[0038] A flowchart of a method for generating XAI for human resources work that explains prediction results in natural language according to an embodiment of the present invention is shown.

[0039] Referring to Fig. 7, the device defines a specific issue related to personnel work and collects data related to the specific issue (S10).

[0040] The device trains an explainable artificial intelligence model using training data (S20).

[0041] The device applies the above data to an explainable artificial intelligence model and outputs a prediction result (S30).

[0042] The device generates prediction results in natural language expressed as a natural explanation (S40).

[0043] While the present invention has been described with reference to the embodiments illustrated in the drawings, these are merely exemplary, and those skilled in the art will appreciate that various modifications and equivalent alternative embodiments are possible. Therefore, the true scope of technical protection of the present invention should be determined by the technical spirit of the appended claims.

Claims

1. A method for generating XAI for human resources work that explains prediction results in natural language performed by a processor, Steps to define specific issues related to human resources affairs; A step of collecting data related to the above specific issue; and A method for generating XAI for human resources that explains the prediction result in natural language, comprising the step of applying the above data to an explainable artificial intelligence model and outputting the prediction result in natural language.

2. In the first paragraph, the method for generating XAI for personnel work is as follows: A method for generating XAI for human resources work, wherein the artificial intelligence model further includes a step of learning using training data, and explains the prediction results in natural language.

Images