Task allocation device

Abstract

A task allocation device according to one embodiment comprises: a collection unit that collects samples of a first evaluation point related to personality that is the individuality of a person, and samples of a second evaluation point related to the goodness-of-fit of the person for completing prescribed types of tasks; a conversion unit that performs a conversion on the samples of the second evaluation point collected by the collection unit, said conversion minimizing a difference due to differences between people, and setting the variance in differences due to differences between tasks to be the same value for each sample; a generation unit that, on the basis of the first evaluation point collected by the collection unit and the second evaluation point after conversion by the conversion unit, generates a model that uses the personality to find a goodness-of-fit predicted value; and an allocation processing unit that finds an allocation, to the person, of tasks to be completed by the person, said allocation having a maximized goodness-of-fit predicted value generated by using the evaluation point related to personality in the model generated by the generation unit.

Description

Task Allocation Device

[0001] TECHNICAL FIELD An embodiment of the present invention relates to a task allocation device.

[0002] It is believed that the total degree of suitability of personnel within an organization to tasks can be maximized by assigning tasks according to the suitability for performing various tasks, which differs for each person, in this case, employee. In a conventional technology using a career interest scale (see, for example, Non-Patent Document 1), the suitability of an employee for performing a predetermined type of task (sometimes referred to as suitability for the task) is quantitatively expressed by responses to a scale that describes the content of the task, and matching between employees and tasks that maximizes suitability is realized.

[0003] The scale describing the task content is a verbal description, such as, for example, an R-type task is a job content such as a mechanic, a C-type task is a job content such as an office work, and an I-type task is a job content such as research or investigation. By having employees respond to the degree to which they are suited to these scales, the suitability for the task can be calculated.

[0004] By using this compatibility as an index and matching employees with tasks so that this index is maximized, task allocation can be achieved that increases the total compatibility of organizational personnel with tasks.

[0005] Nye, CD, Su, R., Rounds, J., & Drasgow, F. (2012). Vocational interests and performance: A quantitative summary of over 60 years of research., Perspectives on Psychological Science,7(4), 384-403.

[0006] It is desirable to predict the suitability of employees to tasks based on measures related to their individual personalities (sometimes simply referred to as "personalities") and assign tasks that maximize the total suitability of personnel within an organization, but no such method has been established. Personality refers to, for example, the Big Five personality, i.e., a person's character traits, such as openness to new experiences or social extroversion.

[0007] Unlike descriptions of job content, descriptions of personality are more general linguistic descriptions that broadly reflect behavioral patterns in everyday life, not just occupational situations.

[0008] In other words, personality may reflect individual differences in employees' behavioral patterns across a broader range of situations. This contrasts with fit scores obtained by directly assessing task suitability, which reflect only an employee's behavioral patterns specific to a particular occupational situation. For example, a person's fit for a particular task may be enhanced because they have recently been assigned a certain task more frequently in their professional life. On the other hand, predictions of an employee's fit for a task based on measures of their personality may be consistent with their everyday, long-term behavioral patterns, such as their thinking or emotional habits, and may be considered more intrinsic predictions of fit.

[0009] However, there is no method for calculating the degree of suitability of an employee to a task in accordance with their personality, and therefore no established method for assigning tasks using such suitability has been established.

[0010] This invention has been made in light of the above circumstances, and its purpose is to provide a task allocation device that makes it possible to appropriately allocate tasks to be performed by individuals using the individual's suitability for performing the tasks.

[0011] A task allocation device according to one aspect of the present invention includes a collection unit that collects samples of first rating points related to a person's personality, which is their individuality, and samples of second rating points related to the person's suitability for performing a predetermined type of task; a conversion unit that converts the second rating point samples collected by the collection unit to minimize differences due to differences between the people and to make the variance of differences due to differences in the tasks the same for each sample; a generation unit that generates a model to obtain a predicted value of the suitability from the personality based on the first rating points collected by the collection unit and the second rating points after conversion by the conversion unit; and an allocation processing unit that determines the allocation of tasks to be performed by the person, such that the predicted value of the suitability generated by applying the rating points related to the personality to the model generated by the generation unit is maximized.

[0012] According to the present invention, tasks to be performed by a person can be appropriately assigned using the person's suitability for performing the task.

[0013] Fig. 1 is a diagram showing an example of an application of a task allocation device according to an embodiment of the present invention. Fig. 2 is a flowchart showing an example of a procedure for processing operations by the task allocation device. Fig. 3 is a diagram explaining an example of calculation of suitability for a task. Fig. 4 is a block diagram showing an example of the hardware configuration of a task allocation device according to an embodiment of the present invention.

[0014] An embodiment of the present invention will be described below. In this embodiment, a model is constructed, and the suitability of an employee for a task is calculated using the model, and a match between the employee and the task that maximizes the suitability is derived.

[0015] In the model construction stage, first, responses regarding the personality and suitability of employees to tasks are collected from a sample of employees who are workers, and second, the raw data of responses regarding suitability of employees to tasks is transformed to minimize inter-sample differences and equalize the variance of intra-sample differences for each employee sample.

[0016] Third, the relationship between an employee's personality and the tasks for which they feel suited is modeled.

[0017] In the stage of calculating the degree of compatibility, the personality of the employee to be matched is input into the model, and a predicted value of the degree of compatibility for each task is calculated.

[0018] In the matching deriving stage, the predicted value of the suitability for the task is used as an index, and matching between employees and tasks is performed to maximize this index.

[0019] 1 is a diagram illustrating an application example of a task allocation device according to an embodiment of the present invention. As shown in FIG. 1, the task allocation device 100 according to this embodiment includes a data collection unit 10, a conversion processing unit 20, a model generation unit 30, a calculation processing unit 40, and an allocation processing unit 50.

[0020] 2 is a flowchart showing an example of the procedure of the processing operation by the task allocation device. First, an online survey is conducted on survey subjects, which are several thousand employees, asking them to respond to the survey about the personalities of the employees and the suitability of the employees for the tasks, and the data collection unit 10 collects the responses to this survey (S10).

[0021] In the questionnaire, for example, the subjects are asked to respond to questions such as "Are you open to new experiences?" or "Are you a socially outgoing person?" on a 1-7 scale to indicate how much they agree with the questions.

[0022] In addition, the questionnaire may ask respondents to answer questions such as, "Do you feel that you would be suited to a job driving a motorbike or truck and transporting luggage?" or "Do you feel that you would be suited to a job in interpersonal service, such as a tour guide or salesperson?" on a 1-7 scale to indicate how much they agree with the questions.

[0023] Next, the conversion processing unit 20 performs a conversion on the raw data of the answers regarding the suitability to the task collected in S10 so as to minimize the differences between samples and make the variance of the differences within samples the same value for each sample (S20).

[0024] The variance of the raw data is composed of two components: the within-sample difference and the between-sample difference. A sample refers to an individual respondent, in this case an employee. Therefore, the within-sample difference is the difference associated with differences in tasks within an individual respondent. On the other hand, the between-sample difference is the difference associated with differences between respondents. Therefore, in S20, the conversion processing unit 20 performs the above conversion by converting the average value for each sample to 0 and calculating the z-score, which is a score that converts the standard deviation for each sample to 1.

[0025] Let M be the number of task questions, and let b be the rating score of the kth task question in the ith sample. i,ｋ Then, the z-score of the kth task question item in the i-th sample can be calculated by the following (1).

[0026]

[0027] This transformation is based on the experimentally established rule that, when modeling the relationship between an employee's personality and task suitability, within-sample differences in raw data on task suitability answers are important, while between-sample differences are not. Specifically, in this embodiment, it is found that a specific employee's personality correlates with the level of task suitability answers for each sample, in this case the average value. This correlation should be removed when modeling differentiated suitability for various tasks, which is influenced by the employee's personality. Therefore, the above transformation is necessary.

[0028] Next, the model generation unit 30 models the relationship between the employee's personality and the tasks that the employee feels suited to by using canonical correlation analysis (CCA) (S30).

[0029] This canonical correlation analysis is a well-known technique that combines multiple variables into two composite variables and maximizes the correlation coefficient between these composite variables. In this embodiment, the model generation unit 30 uses the canonical correlation analysis technique to generate several linear combination values ​​that are composite variables of employee personality ratings and linear combination values ​​that are composite variables of employee suitability for tasks, i.e., suitability ratings, and derives weighting coefficients for calculating each linear combination value that maximize the correlation between the two. In other words, weights for calculating the linear combination values ​​for each personality rating and weights for calculating the linear combination values ​​for each task rating are derived when the correlation between the two is maximized.

[0030] The output from the model is used to match employees with tasks. First, responses to a personality questionnaire for each employee are input into the model (S31).

[0031] Next, the calculation processing unit 40 calculates the linear combination value for each employee using the weights derived for the model as coefficients. Next, the calculation processing unit 40 compares this linear combination value with the weighting coefficients for suitability or unsuitability for the task in the model to calculate the distance from each task, and obtains this calculated distance as a predicted value of suitability for each task (S40).

[0032] Finally, the allocation processing unit 50 uses the predicted value obtained in S40 as an index and derives a matching between employees and tasks that maximizes this index value (S50). In this embodiment, in the simplest case, the calculation processing unit 40 calculates the above-mentioned index values ​​for all combinations of employees and tasks, and the allocation processing unit 50 derives a matching that maximizes the total amount of these index values. Alternatively, a solver that quickly solves optimization problems may be used for this derivation.

[0033] Next, a specific example of calculating the suitability for each task will be described. FIG. 3 is a diagram illustrating an example of calculating the suitability for a task. The arrows in FIG. 3 represent the coordinates of the weights used to calculate two linear combination values ​​of employee personalities as the first variable, i.e., the first linear combination value and the second linear combination value. In the example shown in FIG. 3, the weight for extraversion is approximately "(0.8, 0.3)," and the weight for openness is approximately "(-0.2, 0.9)." Each individual's linear combination value is obtained by multiplying the scores for extraversion and openness indicated by the questionnaire responses by the weights for extraversion and openness, respectively, indicated by the two arrows in FIG. 3, and then summing the results. In the example shown in FIG. 3, the coordinates of Person A's linear combination value are "(0.4, -0.7)."

[0034] On the other hand, the points of the triangle shown in Fig. 3 represent the coordinates of the weights used to calculate two linear combination values, i.e., the first linear combination value and the second linear combination value, of the second variable, here, the orientation or unorthodoxy toward the task. In the example shown in Fig. 3, the coordinates of the weights for sales jobs are approximately "(0.6, -0.7)," while the coordinates of the weights for other tasks such as clerical jobs and technical jobs are at different positions.

[0035] The closer the distance between the coordinates of the individual's linear combination value calculated as above and the coordinates of the task weight, the higher the suitability of that individual for that task is estimated to be. For example, when comparing the coordinates of Person A's linear combination value (0.4,-0.7) with the coordinates of all task weights, it is found to be closest to the weight of sales, so Person A is estimated to be the most suitable for sales.

[0036] 4 is a block diagram showing an example of the hardware configuration of a task allocation device according to an embodiment of the present invention. In the example shown in FIG. 4, the task allocation device 100 according to the embodiment is configured, for example, by a server computer or a personal computer, and has a hardware processor 111A such as a CPU (Central Processing Unit). A program memory 111B, a data memory 112, an input / output interface 113, and a communication interface 114 are connected to this hardware processor 111A via a bus 115.

[0037] The communication interface 114 includes, for example, one or more wireless communication interface units, and enables transmission and reception of information to and from a communication network. As the wireless interface, for example, an interface that adopts a low-power wireless data communication standard such as a wireless LAN (Local Area Network) is used.

[0038] An input device 500 and an output device 600, which are attached to the task assignment device 100 and used by a user or the like, are connected to the input / output interface 113. The input / output interface 113 can acquire operation data input by a user or the like through the input device 500, such as a keyboard, touch panel, touchpad, or mouse, and can output output data to an output device 600, which can include a display device using a liquid crystal or organic electroluminescence (EL) display, for display. The input device 500 and the output device 600 may be devices built into the task assignment device 100, or may be input devices and output devices of other information terminals that can communicate with the task assignment device 100 via a network.

[0039] The program memory 111B is a non-transitory tangible storage medium that is a combination of a non-volatile memory that can be written to and read from at any time, such as a hard disk drive (HDD) or a solid state drive (SSD), and a non-volatile memory such as a read only memory (ROM), and can store programs necessary to execute various control processes, etc., according to one embodiment.

[0040] The data memory 112 is a tangible storage medium that is, for example, a combination of the above-mentioned nonvolatile memory and a volatile memory such as RAM (Random Access Memory), and can be used to store various data or information acquired and created during various processing steps.

[0041] The task allocation device 100 according to one embodiment of the present invention can be configured as a data processing device having the units shown in FIG. 1 as software processing function units.

[0042] The information storage unit used as a work memory or the like by each unit of the task allocation device 100 may be configured using the data memory 112 shown in Fig. 4. However, these configured storage areas are not essential components within the task allocation device 100, and may be areas provided in, for example, an external storage medium such as a USB (Universal Serial Bus) memory, or a storage device such as a database server located in the cloud.

[0043] The processing function units in each of the above units can be realized by reading and executing a program stored in the program memory 111B by the hardware processor 111A. Note that some or all of these processing function units may be realized in various other forms, including integrated circuits such as an application specific integrated circuit (ASIC) or a field-programmable gate array (FPGA).

[0044] The methods described in each embodiment can be stored as a program (software means) that can be executed by a computer on a recording medium such as a magnetic disk (floppy disk, hard disk, etc.), optical disk (CD-ROM, DVD, MO, etc.), or semiconductor memory (ROM, RAM, flash memory, etc.), and can also be distributed by transmitting it via a communication medium. The program stored on the medium also includes a configuration program that configures the software means (including not only execution programs but also tables or data structures) that the computer executes. The computer that realizes this device reads the program stored on the recording medium and, in some cases, configures the software means using the configuration program, and executes the above-mentioned processing by controlling the operation of this software means. The term "recording medium" as used herein is not limited to a storage medium for distribution, but also includes a storage medium such as a magnetic disk or semiconductor memory installed inside the computer or in a device connected via a network.

[0045] The present invention is not limited to the above-described embodiments, and various modifications can be made in the implementation stage without departing from the spirit of the invention. Furthermore, the embodiments may be implemented in appropriate combinations, in which case the combined effects can be obtained. Furthermore, the above-described embodiments include various inventions, and various inventions can be extracted by combining selected elements from the disclosed elements. For example, if the problem can be solved and the desired effect can be obtained even if some elements are deleted from all elements shown in the embodiments, the configuration from which these elements are deleted can be extracted as an invention.

[0046] 100... Task allocation device 10... Data collection unit 20... Conversion processing unit 30... Model generation unit 40... Calculation processing unit 50... Allocation processing unit

Claims

1. A task allocation device comprising: a collection unit that collects samples of first rating points related to personality, which is a characteristic of a person, and samples of second rating points related to the person's suitability for performing a predetermined type of task; a conversion unit that converts the second rating point samples collected by the collection unit to minimize differences due to differences between the people and to make the variance of differences due to differences in the tasks the same for each sample; a generation unit that generates a model to obtain a predicted value of the suitability from the personality based on the first rating points collected by the collection unit and the second rating points after conversion by the conversion unit; and an allocation processing unit that determines the allocation of tasks to be performed by the person, such that the predicted value of the suitability generated by applying the rating points related to the personality to the model generated by the generation unit is maximized.

2. The task allocation device of claim 1, wherein the conversion unit performs the conversion by calculating a score in which the average value of each sample of the second rating points collected by the collection unit is set to 0 and the standard deviation of each sample is set to 1.

3. The task allocation device of claim 1, wherein the collection unit collects, as the second evaluation score, responses to a questionnaire asking the person about the degree of suitability of the person for carrying out the specified type of task.

4. The task allocation device according to claim 1, wherein the collection unit collects responses to a questionnaire that asks the person about their personality as the first rating score.

Images