JP-2026075864-A - Information processing device, assignment program, and assignment method

Abstract

[Challenge] The challenge is to optimize the allocation of workers to specific tasks. [Solution] The information processing device includes an estimation unit that estimates the future elapsed time and processing speed of a target worker by inputting the target worker's past elapsed time and processing speed into an estimation model trained on the elapsed time since the worker started work and the processing speed that indicates the amount of work per unit time, and an assignment unit that assigns the target worker to the target work based on the elapsed time and processing speed of the target worker estimated by the estimation unit and the total amount of work for the target work. [Selection Diagram] Figure 7

Inventors

• 林 伸樹
• 魚津 悠介

Assignees

• 横河電機株式会社

Dates

Publication Date

20260511

Application Date

20241023

Claims (10)

1. An estimation unit estimates the future elapsed time and processing speed of a target worker by inputting the target worker's past elapsed time and processing speed into an estimation model trained based on the elapsed time since the worker started work and the processing speed that indicates the amount of work per unit time. An information processing apparatus comprising: an assignment unit that assigns the target worker to the target work based on the elapsed time and processing speed of the target worker estimated by the estimation unit and the total workload of the target work.
2. The information processing apparatus according to claim 1, characterized in that the estimation unit estimates the future elapsed time and processing speed of multiple target workers by inputting the past elapsed time and processing speed of each of the multiple target workers.
3. The information processing apparatus according to claim 1, characterized in that the estimation unit estimates the elapsed time and processing speed of the target worker after the predetermined time by inputting the past elapsed time and processing speed of the target worker up to the predetermined time each time a predetermined time has elapsed.
4. The information processing apparatus according to claim 2, characterized in that the allocation unit assigns the multiple target workers to the target work based on the estimated elapsed time and processing speed of the multiple target workers and the total workload of the target work.
5. The information processing apparatus according to claim 2, characterized in that the allocation unit repeatedly performs a process to calculate the workload of each of the multiple target workers by integrating the relationship between the elapsed time and the processing speed of each target worker from the start time to the end time, while adjusting the end time, and further performs a process to identify the end time at which the sum of the workloads of the multiple target workers equals the total workload as the time until the target work is completed.
6. The information processing device according to claim 1, characterized in that the performance data used to train the estimation model includes the difficulty level of the task, and the estimation unit further inputs the difficulty level of the target task into the estimation model to estimate the future elapsed time and processing speed of the target worker according to the difficulty level of the target task.
7. The information processing apparatus according to claim 2, further comprising a generation unit that generates a schedule including the workload of the multiple target workers until the target work is completed, and the time required to complete the target work.
8. The information processing apparatus according to claim 4, further characterized in that the allocation unit calculates the cost for each of the multiple target workers based on the cost per unit of work set for each of the multiple target workers and the amount of work each of the multiple target workers performs, and selects a target worker to perform the target work under the condition that the sum of the costs is minimized and the time to complete the target work does not exceed a threshold.
9. On the computer, By inputting the past elapsed time and processing speed of the target worker into an estimation model trained on the elapsed time since the worker started work and the processing speed indicating the amount of work per unit time, the future elapsed time and processing speed of the target worker are estimated. An assignment program that performs a process to assign the target worker to the target work based on the estimated elapsed time and processing speed of the target worker and the total workload of the target work.
10. Computers By inputting the past elapsed time and processing speed of the target worker into an estimation model trained on the elapsed time since the worker started work and the processing speed indicating the amount of work per unit time, the future elapsed time and processing speed of the target worker are estimated. An assignment method that performs a process of assigning the target worker to the target work based on the estimated elapsed time and processing speed of the target worker and the total workload of the target work.

Description

This invention relates to an information processing device, an assignment program, and an assignment method. When a new project is ordered, workers are assigned based on the details of the project and the workers' past performance. For example, prior art related to worker assignment is disclosed in Patent Documents 1 and 2. Patent Document 1 discloses a technique that determines the work period requiring workers based on the start and end dates of a task, searches for workers with available tasks within that period using a predetermined calculation formula, and then prioritizes assigning the workers with the skills and experience best suited to the task from the searched workers. Patent Document 2 discloses a technique for selecting workers based on their skill level, work performance, and the difficulty level of the work described in the work request form. Japanese Patent Publication No. 2006-318331Japanese Patent Publication No. 2014-191377 This is a diagram illustrating the process of the training phase.This figure shows an example of training data.This is a diagram illustrating the processing of the estimation phase.This is a diagram illustrating the processing of the allocation phase.Figure (1) shows an example of schedule information.Figure (2) shows an example of schedule information.This is a functional block diagram showing the configuration of the information processing device according to this embodiment.This is a flowchart showing the processing flow of the information processing device of this embodiment.This is a diagram illustrating an example hardware configuration. The embodiments of the information processing device, assignment program, and assignment method disclosed herein will be described in detail below with reference to the drawings. However, the present invention is not limited by these embodiments. Furthermore, the same elements are denoted by the same reference numerals, redundant descriptions are omitted as appropriate, and each embodiment can be combined as appropriate within a non-contradictory scope. (First embodiment) (Explanation of the processing performed by the information processing device) The processing of the information processing device according to this embodiment will now be described. In the following description, the information processing device according to this embodiment will be referred to as "information processing device 100". For example, the information processing device 100 performs the training phase processing, the estimation phase processing, the assignment phase processing, and the schedule information review processing, respectively. (Processing during the training phase) First, an example of the training phase processing performed by the information processing device 100 will be described. Figure 1 is a diagram illustrating the training phase processing. The information processing device 100 trains the estimation model 50 using the training dataset 141. The estimated model 50 is a machine learning model such as a neural network, support vector machine, random forest, or logistic regression. In this embodiment, the estimated model 50 is described as a neural network, but it is not limited to this. The training dataset 141 contains multiple training data points. The training data represents historical data showing the relationship between the elapsed time from the start of a task and the processing speed when a particular worker has performed a single task in the past. Processing speed is the amount of work a worker can process per unit of time, and the unit is "workload/hour". For example, the training dataset 141 contains training data for all workers. Figure 2 shows an example of training data. The vertical axis of graph G1 corresponds to processing speed, and the horizontal axis corresponds to elapsed time. Elapsed time "0" represents the start time of the task in past performance. In the example shown in Figure 2, the end time of the task in past performance is set to "20," but this is not limiting. For example, training data L1 is training data generated based on the past performance of worker U1. Training data L2 is training data generated based on the past performance of worker U2. Training data L3 is training data generated based on the past performance of worker U3. Training data L4 is training data generated based on the past performance of worker U4. Training data L5 is training data generated based on the past performance of worker U5. Training data L6 is training data generated based on the past performance of worker U6. Training data L7 is training data generated based on the past performance of worker U7. In Figure 2, for the sake of explanation, only training data L1 to L7 are shown, but other training data will be registered in training dataset 141. Here, the information processing device 100 may train the estimation model 50 using any existing technology, but an example is shown below. For example, the information processing devi