Business classification device, business classification method, and business classification program

Abstract

In a task classification device (10), an acquisition unit (15a) acquires a history of involvement of a worker in each task to be processed. A derivation unit (15b) uses the acquired history to derive the frequency of involvement of each worker in each task. A calculation unit (15c) uses the derived frequency to calculate distances each between pieces of information each relating to the frequency of the involvement of each worker in each task. A classification unit (15d) classifies the tasks according to the calculated distances.

Description

Technical Field

[0001] The present invention relates to a business classification device, a business classification method, and a business classification program.

Background Art

[0002] In the countermeasure work immediately after a disaster occurs, it is required that the work be completed within a certain allowable time. Conventionally, a technique has been disclosed for allocating a plurality of processes included in work to workers so that the work is completed within a certain time (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, according to the prior art, it may be difficult to appropriately classify a plurality of tasks and allocate them to workers. For example, conventionally, tasks have been classified based on external characteristics or knowledge possessed by skilled workers and allocated to workers. Therefore, there is a risk that past experiences or images that have nothing to do with the essence of the task may become biases, or the similarity of skills observed between multiple tasks may be overlooked, and the tasks may not be classified appropriately. Therefore, there is a risk that the tasks cannot be allocated to appropriate workers.

[0005] The present invention has been made in view of the above, and an object thereof is to easily and appropriately classify a plurality of tasks.

Means for Solving the Problems

[0006] To solve the above-mentioned problems and achieve the objective, the business classification device according to the present invention is characterized by comprising: an acquisition unit that acquires the history of work performed by workers for each business to be processed; an acquisition unit that uses the acquired history to derive the frequency of work performed by each worker for each business; a calculation unit that uses the derived frequency to calculate the distance between the information regarding the frequency of work performed by each worker for each business; and a classification unit that classifies the business according to the calculated distance. [Effects of the Invention]

[0007] According to the present invention, it becomes possible to easily and appropriately classify multiple tasks. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is a schematic diagram illustrating the general configuration of the business classification device of this embodiment. [Figure 2] Figure 2 is a diagram illustrating the processing of the business classification device. [Figure 3] Figure 3 is a flowchart showing the business classification processing procedure. [Figure 4] Figure 4 shows an example of a computer running a business classification program. [Modes for carrying out the invention]

[0009] Hereinafter, one embodiment of the present invention will be described in detail with reference to the drawings. However, the present invention is not limited to this embodiment. Furthermore, in the drawings, the same parts are denoted by the same reference numerals.

[0010] [Overview of the business classification system] The task classification device of this embodiment assumes that each worker has tasks they are good at and tasks they are not good at, and that in the past, each worker proactively selected and handled tasks they were good at. Based on this assumption, the task classification device uses the bias of each worker's strengths and weaknesses as a characteristic of the tasks and classifies tasks using only the results of past task assignments. In this way, the task classification device clusters tasks from the perspective of the commonalities of the assigned workers, making it possible to classify tasks based on hidden commonalities such as the similarity of the required skills between the target tasks. Therefore, the task classification device can easily and appropriately classify multiple tasks. As a result, it becomes possible to assign tasks to the appropriate workers.

[0011] [Configuration of the business classification device] Figure 1 is a schematic diagram illustrating the general configuration of the business classification device of this embodiment. As illustrated in Figure 1, the business classification device 10 of this embodiment is implemented using a general-purpose computer such as a personal computer, and comprises an input unit 11, an output unit 12, a communication control unit 13, a storage unit 14, and a control unit 15.

[0012] The input unit 11 is implemented using an input device such as a keyboard or mouse, and in response to input operations by the operator, it inputs various instruction information, such as processing start, to the control unit 15. The output unit 12 is implemented using a display device such as a liquid crystal display, a printing device such as a printer, etc. For example, the output unit 12 displays the results of the business classification processing described later.

[0013] The communication control unit 13 is implemented using a NIC (Network Interface Card) or the like, and controls communication between the control unit 15 and external devices via telecommunication lines such as a LAN (Local Area Network) or the Internet. For example, the communication control unit 13 controls communication between the control unit 15 and a management device that manages various information, including business history.

[0014] The memory unit 14 is implemented using semiconductor memory elements such as RAM (Random Access Memory) or flash memory, or storage devices such as hard disks or optical discs. The memory unit 14 pre-stores processing programs for operating the business classification device 10, as well as data used during the execution of the processing programs, or temporarily stores them each time processing is performed. The memory unit 14 may also be configured to communicate with the control unit 15 via the communication control unit 13.

[0015] In this embodiment, the storage unit 14 may store the work assignment table 14a generated by the work classification process described later. The work assignment table 14a is information representing the frequency with which each worker engages in each task, as will be described later.

[0016] The control unit 15 is implemented using a CPU (Central Processing Unit), NP (Network Processor), FPGA (Field Programmable Gate Array), etc., and executes a processing program stored in memory. As a result, the control unit 15 functions as an acquisition unit 15a, a derivation unit 15b, a calculation unit 15c, and a classification unit 15d, as illustrated in Figure 1, to perform business classification processing. Note that each or part of these functional units may be implemented on different hardware. For example, the acquisition unit 15a may be implemented on a different device than the other functional units. Furthermore, the control unit 15 may also include other functional units.

[0017] The acquisition unit 15a acquires the work history of each worker for each task to be processed. Specifically, the acquisition unit 15a acquires a history including the number of times or the duration of each worker's work for each task within a predetermined period. The acquisition unit 15a acquires this information via the input unit 11 or via the communication control unit 13 from a management device that manages the history of tasks. The acquisition unit 15a may store the acquired history in the storage unit 14.

[0018] The derivation unit 15b derives the frequency of each worker's engagement in each task using the acquired history. Specifically, the derivation unit 15b derives the frequency using either the number of times or the time of each worker's engagement in each task in the history. For example, the derivation unit 15b derives the frequency of each worker's engagement in each task using the number of times or the time that each worker has engaged in each task over a predetermined period. Then, the derivation unit 15b may store in the storage unit 14 a task allocation table 14a representing the frequency of each worker's engagement in each derived task.

[0019] Here, FIG. 2 is a diagram for explaining the processing of the task classification device. For example, as illustrated in FIG. 2(a), the derivation unit 15b first totals the number of times each worker has engaged in each task using the history. In the example shown in FIG. 2(a), for example, worker 2 has engaged in tasks C and D twice each.

[0020] Next, as illustrated in FIG. 2(b), the derivation unit 15b derives the frequency for each task for each worker, normalized so that the total number of times of the tasks engaged in by each worker becomes 1. In the example shown in FIG. 2(b), for example, the frequencies of tasks C and D for worker 2 are each 0.5. The derivation unit 15b may store in the storage unit 14 the task allocation table 14a illustrated in FIG. 2(b) that has been derived. Alternatively, the derivation unit 15b may store in the storage unit 14 the aggregation information illustrated in FIG. 2(a) as the task allocation table 14a.

[0021] Then, the derivation unit 15b derives a matrix obtained by combining for each worker the frequencies for each task that have been normalized. For example, the derivation unit 15b derives a matrix having each task shown in FIG. 2(b) as rows and each worker as columns.

[0022] Returning to the description of FIG. 1, the calculation unit 15c calculates the distance (hereinafter, the distance between tasks) between information on the frequency of engagement of each task by each worker using the derived frequency of each worker's engagement in each task. Specifically, the calculation unit 15c calculates the cosine similarity between vectors for each task in the derived matrix as the distance between tasks.

[0023] For example, the calculation unit 15c calculates the cosine similarity between the vector A={0.1,0,0.2} in the row of task A and the vector B={0.2,0,0.2} in the row of task B, as the distance between task A and task B as illustrated in Figure 2(b). Here, the cosine similarity between vector a and vector b is expressed by the following equation (1).

[0024]

number

[0025] Therefore, the cosine similarity between vector A and vector B is calculated to be 0.948. In other words, the calculation unit 15c calculates the distance between task A and task B as 0.948.

[0026] Similarly, the calculation unit 15c calculates the distance between all the tasks A to E that are to be processed.

[0027] The classification unit 15d classifies tasks according to the calculated distance between them. For example, the classification unit 15d classifies tasks into three clusters, with predetermined thresholds α and β (α < β): Cluster 1, where the calculated distance is in the range from minimum to threshold α; Cluster 2, where the distance is in the range from threshold α to threshold β; and Cluster 3, where the distance is in the range from threshold β to maximum. The classification unit 15d also outputs a list of tasks for each classified cluster via the output unit 12.

[0028] Thus, according to the task classification device 10, based on the assumption that past tasks were assigned by each worker who proactively selected tasks they were good at, tasks are clustered using only past assignment results, with the bias in each worker's strengths and weaknesses as the characteristic of each task. In other words, by clustering tasks from the perspective of the commonalities of the assigned workers, it becomes possible to classify tasks based on hidden commonalities such as the similarity of the necessary skills between the target tasks. As a result, by assigning tasks to clusters, it becomes easy to assign each task to the appropriate worker.

[0029] [Business Classification Processing] Next, with reference to Figure 3, the business classification process by the business classification device 10 according to this embodiment will be described. Figure 3 is a flowchart of the business classification process procedure. The flowchart in Figure 3 starts, for example, when the user inputs an operation to instruct the process to begin.

[0030] First, the acquisition unit 15a acquires the work history of each worker for each task to be processed (step S1). Specifically, the acquisition unit 15a acquires a history including the number of times or hours each worker has worked on each task within a predetermined period.

[0031] Next, the derivation unit 15b uses the acquired history to derive the frequency of each worker's engagement with each task (step S2). For example, the derivation unit 15b derives the frequency using either the number of times or the duration of each worker's engagement with each task from the history. The derivation unit 15b also derives a matrix by combining the normalized frequencies for each task for each worker with the total number of workers.

[0032] The calculation unit 15c uses the frequency of each worker's engagement with each derived task to calculate the distance between the information regarding the frequency of each worker's engagement with each task (distance between tasks) (step S3). For example, the calculation unit 15c calculates the cosine similarity between the vectors for each task in the derived matrix as the distance between tasks.

[0033] The classification unit 15d classifies the tasks according to the calculated distance between them (step S4). The classification unit 15d also outputs a list of tasks by cluster, which is the result of the task classification process, via the output unit 12. This completes the series of task classification processes.

[0034] [effect] As described above, in the business classification device 10 of this embodiment, the acquisition unit 15a acquires the history of work performed by workers for each business to be processed. The derivation unit 15b uses the acquired history to derive the frequency of work performed by each worker for each business. The calculation unit 15c uses the derived frequencies to calculate the distance between the information regarding the frequency of work performed by each worker for each business. The classification unit 15d classifies the businesses according to the calculated distance.

[0035] Specifically, the derivation unit 15b derives the frequency using either the number of times or the duration of each worker's engagement with each task in the history.

[0036] Furthermore, the derivation unit 15b derives a matrix by combining the normalized frequencies for each task for each worker for all workers. In this case, the calculation unit 15c calculates the cosine similarity between the vectors for each task in the derived matrix as the distance between the information regarding the frequency of each worker's engagement with each task.

[0037] Thus, the task classification device 10, under the assumption that past tasks were assigned based on each worker's own strengths and abilities, clusters tasks using only past assignment results, with each worker's strengths and weaknesses as the characteristic of the task. In other words, the task classification device 10 allows for the classification of tasks based on hidden commonalities, such as the similarity of required skills, by clustering tasks based on the commonalities of the assigned workers. Therefore, the task classification device 10 can easily and appropriately classify multiple tasks. As a result, by assigning tasks to appropriate workers according to their cluster, it becomes easy to assign tasks in each cluster to the appropriate workers.

[0038] [program] It is also possible to create a program that describes the processing performed by the business classification device 10 according to the above embodiment in a language that can be executed by a computer. In one embodiment, the business classification device 10 can be implemented by installing a business classification program that performs the above business classification processing as package software or online software on a desired computer. For example, by having an information processing device execute the above business classification program, the information processing device can be made to function as the business classification device 10. The information processing device referred to here includes desktop or notebook personal computers. In addition, the category of information processing device also includes mobile communication terminals such as smartphones, mobile phones and PHS (Personal Handyphone System), and slate terminals such as PDA (Personal Digital Assistant). Furthermore, the functions of the business classification device 10 may be implemented on a cloud server.

[0039] Figure 4 shows an example of a computer running a business classification program. Computer 1000 includes, for example, memory 1010, CPU 1020, hard disk drive interface 1030, disk drive interface 1040, serial port interface 1050, video adapter 1060, and network interface 1070. These components are connected by bus 1080.

[0040] Memory 1010 includes ROM (Read Only Memory) 1011 and RAM 1012. ROM 1011 stores, for example, a boot program such as BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1031. The disk drive interface 1040 is connected to the disk drive 1041. A removable storage medium, such as a magnetic disk or optical disk, is inserted into the disk drive 1041. A serial port interface 1050 is connected to, for example, a mouse 1051 and a keyboard 1052. A video adapter 1060 is connected to, for example, a display 1061.

[0041] Here, the hard disk drive 1031 stores, for example, the OS (Operating System) 1091, the application program 1092, the program module 1093, and the program data 1094. The information described in the above embodiment is stored, for example, in the hard disk drive 1031 or the memory 1010.

[0042] Furthermore, the business classification program is stored in the hard disk drive 1031 as a program module 1093 containing instructions to be executed by the computer 1000, for example. Specifically, the program module 1093 containing instructions for each process executed by the business classification device 10 described in the above embodiment is stored in the hard disk drive 1031.

[0043] Furthermore, the data used for information processing by the business classification program is stored as program data 1094, for example, in the hard disk drive 1031. The CPU 1020 then reads the program module 1093 and program data 1094 stored in the hard disk drive 1031 into the RAM 1012 as needed and executes the procedures described above.

[0044] Furthermore, the program module 1093 and program data 1094 related to the business classification program are not limited to being stored on the hard disk drive 1031; for example, they may be stored on a removable storage medium and read by the CPU 1020 via a disk drive 1041 or the like. Alternatively, the program module 1093 and program data 1094 related to the business classification program may be stored on another computer connected via a network such as a LAN or WAN (Wide Area Network) and read by the CPU 1020 via a network interface 1070.

[0045] Although embodiments applying the invention made by the present inventors have been described above, the present invention is not limited by the descriptions and drawings that constitute part of the disclosure of the present invention in this embodiment. That is, all other embodiments, examples, and operational techniques made by those skilled in the art based on this embodiment are included in the scope of the present invention. [Explanation of symbols]

[0046] 10 Business classification device 11 Input section 12 Output section 13 Communication Control Unit 14 Storage section 14a Work Assignment Schedule 15 Control Unit 15a Acquisition part 15b Derivation part 15c Calculation part 15d Classification section

Claims

1. An acquisition unit that acquires the history of work performed by multiple workers for each task to be processed, A derivation unit that uses the acquired history to derive the frequency of each worker's engagement with each task, A calculation unit that uses the frequencies derived for multiple tasks to calculate the similarity between vectors representing information about the frequency of each worker's engagement in each task, A classification unit that classifies the business according to the calculated similarity, It has, The derivation unit derives a matrix by combining the normalized frequencies for each task for each worker with the frequencies for all workers. The business classification device is characterized in that the calculation unit calculates the cosine similarity between the vectors for each business in the derived matrix as the similarity.

2. The work classification device according to claim 1, characterized in that the derivation unit derives the frequency using either the number of times or the duration of each worker's engagement with each task from the history.

3. A business classification method performed by a business classification device, The acquisition process involves obtaining the history of work performed by multiple workers on each task being processed, Using the acquired history, a derivation step is performed to derive the frequency of each worker's engagement with each task, A calculation step of calculating the similarity between vectors representing information about the frequency of each worker's engagement in each task, using the frequencies derived for multiple tasks, A classification process that classifies the tasks according to the calculated similarity, Includes, The derivation step involves deriving a matrix by combining the normalized frequencies for each task for each worker, for all workers. The calculation step is characterized by calculating the cosine similarity between the vectors for each task in the derived matrix as the similarity.

4. The acquisition step involves obtaining the history of work performed by multiple workers on each task to be processed, Using the acquired history, a derivation step is performed to derive the frequency of each worker's engagement with each task, A calculation step of calculating the similarity between vectors representing information about the frequency of each worker's engagement in each task, using the frequencies derived for multiple tasks, A classification step in which tasks are classified according to the calculated similarity, Have the computer run it, The derivation step involves deriving a matrix by combining the normalized frequencies for each task for each worker, for all workers. The calculation step is a business classification program characterized by calculating the cosine similarity between the vectors for each business in the derived matrix as the similarity.

Images