Information processing device, information processing method, and information processing program

Abstract

To provide an information processor that normalizes bias related to evaluation and improves evaluation fairness.SOLUTION: An information processor according to the present application includes an acquisition unit, a calculation unit, and a provision unit. The acquisition unit acquires multiple evaluation data. The calculation unit calculates, on the basis of Bayesian estimation of the multiple evaluation data acquired by the acquisition unit, a bias value that quantifies a bias related to evaluation included in the multiple evaluation data. The provision unit provides information related to an evaluation value obtained by subtracting the bias value calculated by the calculation unit from a measured value of the multiple evaluation data.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Bias can occur because the evaluation content varies depending on the evaluator. For example, in personnel evaluations, bias can occur due to the number of evaluations the evaluator has made in the past, their experience, and the relationship between the evaluator and the critic (for example, how close they are). Furthermore, bias can also occur due to the implementation conditions, such as the wording of the evaluation questions and the timing of the evaluation.

[0003] A technology called people analytics has been known as an example of a technology that utilizes various types of information accumulated in organizations such as companies to make strategic decisions and improve business efficiency. For example, a technology that supports personnel evaluation is known. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2019 / 043889 [Patent Document 2] Patent No. 6216903 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the above-mentioned conventional techniques leave room for further improvement in order to normalize biases related to evaluation and improve the fairness of evaluation.

[0006] The present application has been made in consideration of the above, and aims to normalize biases related to evaluation and improve the fairness of evaluation. [Means for solving the problem]

[0007] The information processing device of the present application is characterized by having an acquisition unit that acquires multi-faceted evaluation data, a calculation unit that calculates a bias value that quantifies a bias related to the evaluation contained in the multi-faceted evaluation data based on Bayesian estimation of the multi-faceted evaluation data acquired by the acquisition unit, and a provision unit that provides information related to the evaluation value obtained by subtracting the bias value calculated by the calculation unit from the actual value of the multi-faceted evaluation data. Effect of the Invention

[0008] According to one aspect of the embodiment, it is possible to normalize biases related to evaluation and improve the fairness of the evaluation. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of a terminal device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of a multi-faceted evaluation data storage unit according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a model storage unit according to the embodiment. [Figure 7] FIG. 7 is a flowchart illustrating an example of information processing according to the embodiment. [Figure 8] FIG. 8 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated explanations are omitted.

[0011] (Embodiment) [1. Configuration of information processing system] An information processing system 1 shown in Fig. 1 will be described. As shown in Fig. 1, the information processing system 1 includes a terminal device 10 and an information processing device 100. The terminal device 10 and the information processing device 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other by wire or wirelessly. Fig. 1 is a diagram showing an example of the configuration of the information processing system 1 according to an embodiment. Note that the information processing system 1 shown in Fig. 1 may include a plurality of terminal devices 10 and a plurality of information processing devices 100.

[0012] The terminal device 10 is an information processing device used by an evaluator. The terminal device 10 may be any device that can realize the processing in the embodiment. The terminal device 10 may be a device such as a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. In the example shown in FIG. 2, the terminal device 10 is a smartphone.

[0013] The terminal device 10 is, for example, a smart device such as a smartphone or a tablet, and is a mobile terminal device capable of communicating with any server device via a wireless communication network such as 3G (Generation) or LTE (Long Term Evolution). The terminal device 10 has a screen such as a liquid crystal display with a touch panel function, and may receive various operations on the displayed data such as content, such as tapping, sliding, scrolling, etc., performed by an evaluator using a finger or a stylus.

[0014] In the example of FIG. 2, the terminal device 101 is used by the evaluator U11, the terminal device 102 is used by the evaluator U12, and the terminal device 103 is used by the evaluator U13. The terminal devices 101, 102, and 103 access the information processing device 100 and transmit information received from each of the evaluators to the information processing device 100. In the following, when it is not necessary to distinguish between the terminal devices 101, 102, and 103, they are referred to as "terminal devices 10". In addition, when it is not necessary to distinguish between the evaluators U11, U12, and U13, they are simply referred to as "evaluators". In addition, in the following, the terminal device 10 may be referred to as the evaluator. That is, in the following, the evaluator can also be read as the terminal device 10.

[0015] The information processing device 100 is an information processing device for implementing various data collection and analysis, and is implemented, for example, by a server device or a cloud system. For example, the information processing device 100 is used to manage data within an organization such as a company. The information processing device 100 has a function of, for example, acquiring multifaceted evaluation data and providing information based on the results of quantifying bias caused by an evaluator or evaluation implementation conditions based on Bayesian Inference. The information processing device 100 is, for example, an information processing device such as a PC or a WS (Work Station), and performs processing based on information transmitted from a terminal device 10 or the like via a network N.

[0016] Although FIG. 1 illustrates a case in which the terminal device 10 and the information processing device 100 are separate devices, the terminal device 10 and the information processing device 100 may be integrated.

[0017] [2. An example of information processing] A method called multi-faceted evaluation (360-degree evaluation) is known as an example of a method for evaluating an evaluator from multiple perspectives by multiple evaluators with different positions and relationships with the evaluator, such as a superior, a colleague, and a subordinate. In the following embodiment, information processing for providing information that effectively quantifies the evaluation-related bias contained in the multi-faceted evaluation data based on Bayesian estimation of the multi-faceted evaluation data will be described. In the following embodiment, the bias of the evaluator will be used as an example of the bias related to the evaluation, but this example is not limited to this example. For example, the bias related to the evaluation may be a bias related to the conditions for performing the evaluation. In the following embodiment, the case where the evaluator performs a multi-faceted evaluation of the evaluator R11 will be described as an example. In the following embodiment, the evaluators U11, U12, and U13 and the evaluator R11 are assumed to belong to the same organization.

[0018] Fig. 2 is a diagram showing an example of information processing of the information processing system 1 according to the embodiment. The information processing device 100 acquires multi-faceted evaluation data of the evaluators U11, U12, and U13 for the assessee R11 (step S101). For convenience of explanation, Fig. 2 shows a case where the multi-faceted evaluation data from the evaluators U11, U12, and U13 are simultaneously transmitted and acquired, but it may be transmitted and acquired individually. In addition, the evaluators from which the information processing device 100 acquires multi-faceted evaluation data and the number of evaluators are not particularly limited.

[0019] The information processing device 100 performs machine learning using the multifaceted evaluation data thus acquired and collected (step S102). Specifically, the information processing device 100 generates a model using the multifaceted evaluation data as input information and using evaluation values ​​(hereinafter, appropriately referred to as "bias values") that quantify biases related to evaluations included in the multifaceted evaluation data as output information. Note that the multifaceted evaluation data input here is, for example, the answers of the evaluators or values ​​(actual measured values) based on the answers of the evaluators.

[0020] At this time, the information processing device 100 generates a model by adding predetermined attribute information to the input information together with the multi-faceted evaluation data. The predetermined attribute information is basic attribute information for appropriately quantifying the bias of the evaluator, such as attribute information of the evaluator, attribute information of the person being evaluated, and attribute information related to the multi-faceted evaluation survey.

[0021] The predetermined attribute information is, for example, attribute information of the evaluator and the evaluatee, such as the department and job title of the evaluator and the evaluatee.

[0022] The predetermined attribute information may be relative attribute information such as the relationship between the evaluator and the person being evaluated (e.g., superior and subordinate). Furthermore, the predetermined attribute information is not limited to relative attribute information from the perspective of the evaluator, but may also be relative attribute information from the perspective of the person being evaluated. For example, if the relationship between the evaluator and the person being evaluated is that of superior and subordinate, the relative attribute information from the perspective of the evaluator is "superior of the person being evaluated," and the relative attribute information from the perspective of the person being evaluated is "subordinate of the person being evaluated." Such relative attribute information may be included in the attribute information of the evaluator and the person being evaluated, respectively.

[0023] The predetermined attribute information is, for example, attribute information on the multi-faceted evaluation survey or the survey method, etc. For example, the predetermined attribute information is attribute information on the multi-faceted evaluation survey, such as the question number and the time of response.

[0024] The information processing device 100 generates a model in which the bias value for each attribute included in the attribute information is output information by adding predetermined attribute information. For example, the information processing device 100 generates a model in which the bias value for each attribute, such as "If the attribute of the evaluator is XX, then it is likely to be like this" or "If the attribute of the person being evaluated is XX, then it is likely to be like this", is output information. This allows the information processing device 100 to evaluate the bias for each attribute based on the bias value for each attribute, and therefore, for example, it is possible to select and output an attribute with a large bias.

[0025] The information processing device 100 generates a machine-learned model based on Bayesian estimation of the multi-faceted evaluation data. For example, the information processing device 100 generates a machine-learned model based on actual measurements based on the multi-faceted evaluation and estimated values ​​indicating the true abilities of the person being evaluated that are estimated based on a predetermined probability distribution. In this way, the information processing device 100 estimates estimated values ​​from a predetermined probability distribution and performs learning based on the estimated values, so that "machine" learning based on Bayesian estimation can be realized. Specifically, the information processing device 100 generates a machine-learned model using bias values ​​for each attribute calculated by subtracting estimated values ​​indicating the true abilities of the person being evaluated from actual measurements based on the multi-faceted evaluation as positive examples. In other words, the bias values, which are output information, are also the estimation results of Bayesian estimation for the multi-faceted evaluation data.

[0026] Here, the bias of the bias value for each attribute calculated by subtracting the estimated value indicating the true ability of the assessee from the actual value based on the multifaceted evaluation includes, for example, the bias of the assessee's job title, the bias of the assessee's grade, the bias of the question content, the bias of the question type, the bias of the evaluation policy of the headquarters that oversees the evaluators, the bias of the individual evaluator's leniency, etc. In other words, the actual value based on the multifaceted evaluation is calculated as the linear sum of the estimated value indicating the true ability of the assessee and the bias value for each attribute.

[0027] The information processing device 100 performs machine learning by applying Bayesian estimation, and unlike general supervised machine learning, does not need to obtain teacher data such as values ​​indicating the true ability of the person being evaluated, so that the efficiency of processing can be improved. In addition, it is possible to promote reduction in collection costs. In addition, the information processing device 100 performs machine learning by applying Bayesian estimation, and can clarify the relationship between factors and output results, so that it is possible to provide information with high interpretability.

[0028] The information processing device 100 can quantify not only the value indicating the true ability of the person being evaluated, but also the bias, and therefore can provide useful information for improving the operation of the evaluation system and providing guidance to evaluators, etc. For example, the information processing device 100 can quantify the bias on a question-by-question or department-by-department basis, and therefore can provide useful information for improving operation.

[0029] The information processing device 100 performs machine learning using Bayesian estimation, and unlike general rule-based methods, does not need to obtain details about bias, making it possible to improve the efficiency of processing. For example, in general rule-based methods, it is necessary to generate rules for calculating to subtract knowledge such as "Department A is evaluated more leniently than Department B" or "Superior evaluations are more lenient" based on the knowledge.

[0030] In contrast, by applying Bayesian estimation to machine learning, it is believed that the model can learn the evaluation tendency based on the attributes of the evaluator and the person being evaluated and the relative relationship based on those attributes. As a result, rather than knowledge such as "Department A tends to be more lenient in evaluations than Department B," it is possible to generate a model with shallower knowledge such as "Department A and Department B may have different leniency levels." Since it does not depend on the situation of the company or other entity to which it is applied, it can promote improved flexibility.

[0031] The information processing device 100 uses the model generated in this way to calculate a bias value that quantifies the bias related to the evaluation included in the multi-faceted evaluation data (step S103).

[0032] The information processing device 100 provides information based on the calculated bias value (step S104). For example, the information processing device 100 provides information on the true evaluation value of the evaluator by subtracting the calculated bias value from the actual measurement value of the multi-faceted evaluation data as the true evaluation value of the evaluator excluding the bias.

[0033] In the above embodiment, the information processing device 100 generates a model that calculates a bias value that quantifies the bias related to the evaluation included in the multi-faceted evaluation data, and calculates a true evaluation value by removing the bias from the actual measurement value using the generated model, but this example is not limited to this. For example, the information processing device 100 may generate a model that directly calculates a true evaluation value by removing the bias from the actual measurement value. In this case, the information processing device 100 generates a model that outputs an evaluation value obtained by subtracting a bias value that quantifies the bias from the actual measurement value.

[0034] In the above embodiment, examples of the specified attribute information include attribute information of the evaluator, attribute information of the person being evaluated, and attribute information related to the multi-faceted evaluation survey, but the specified attribute information is not limited to these attribute information.

[0035] In the above embodiment, the information processing device 100 may perform the above information processing using information regarding combinations based on relative relationships between attributes, such as "a department manager evaluates an ordinary employee" or "a section manager evaluates an ordinary employee," as specified attribute information.

[0036] In the above embodiment, the information processing device 100 may determine whether the bias value has transitioned toward zero based on a comparison between a bias value based on the multi-faceted evaluation data of an evaluator acquired at one response time and a bias value based on the multi-faceted evaluation data of an evaluator acquired after one response time. For example, when the bias included in the multi-faceted evaluation data of an evaluator acquired after one response time approaches zero, the information processing device 100 determines that the bias value has transitioned toward zero.

[0037] Then, when it is determined that the bias value has transitioned in the direction in which the bias becomes zero, the information processing device 100 may determine that the aptitude of the evaluation has improved. Furthermore, the information processing device 100 may provide information that the aptitude of the evaluation has improved.

[0038] 3. Terminal Device Configuration Next, the configuration of the terminal device 10 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the terminal device 10 according to the embodiment. As shown in Fig. 3, the terminal device 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

[0039] (Communications Department 11) The communication unit 11 is realized by, for example, a network interface card (NIC) etc. The communication unit 11 is connected to a predetermined network N by wire or wirelessly, and transmits and receives information to and from the information processing device 100 etc. via the predetermined network N.

[0040] (Input section 12) The input unit 12 accepts various operations from the evaluators. In the example shown in Fig. 2, the input unit 12 accepts various operations from the evaluators U11, U12, and U13. For example, the input unit 12 may accept various operations from the evaluators via a display screen using a touch panel function. The input unit 12 may also accept various operations from buttons provided on the terminal device 10, or a keyboard or mouse connected to the terminal device 10.

[0041] (Output section 13) The output unit 13 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 13 displays information transmitted from the information processing device 100.

[0042] (Control unit 14) The control unit 14 is, for example, a controller, and is realized by a CPU (Central Processing Unit), MPU (Micro Processing Unit), etc., executing various programs stored in a storage device inside the terminal device 10 using a RAM (Random Access Memory) as a working area. For example, the various programs include application programs installed in the terminal device 10. For example, the various programs include an application program that transmits information regarding the evaluator's operation to the information processing device 100. The control unit 14 is also realized by an integrated circuit, for example, an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0043] As shown in FIG. 3, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the information processing operations described below.

[0044] (Receiving unit 141) The receiving unit 141 receives various information. The receiving unit 141 receives various information from an external information processing device. The receiving unit 141 receives various information from another information processing device such as the information processing device 100. For example, the receiving unit 141 receives content for multifaceted evaluation.

[0045] (Transmitter 142) The transmission unit 142 transmits various information to an external information processing device. The transmission unit 142 transmits various information to another information processing device such as the information processing device 100. For example, the transmission unit 142 transmits multifaceted evaluation data. For example, the transmission unit 142 transmits multifaceted evaluation data for the assessee that is accepted based on the operation of the evaluator.

[0046] 4. Configuration of Information Processing Device Next, the configuration of the information processing device 100 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 4, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing device 100 may have an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0047] (Communication unit 110) The communication unit 110 is realized by, for example, a NIC etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the terminal device 10 etc. via the network N.

[0048] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 4, the storage unit 120 has a multi-faceted evaluation data storage unit 121 and a model storage unit 122.

[0049] The multifaceted evaluation data storage unit 121 stores information regarding multifaceted evaluation data of a plurality of evaluators for an assessee. An example of the multifaceted evaluation data storage unit 121 according to an embodiment is shown in Fig. 5. As shown in Fig. 5, the multifaceted evaluation data storage unit 121 has items such as "multifaceted evaluation ID", "assessee ID", "evaluator ID", and "multifaceted evaluation data".

[0050] "Multifaceted evaluation ID" indicates identification information for identifying the multifaceted evaluation data. "Ratee ID" indicates identification information for identifying the ratee. "Evaluator ID" indicates identification information for identifying the evaluator. "Multifaceted evaluation data" indicates multifaceted evaluation data. In the example shown in Figure 5, conceptual information such as "multifaceted evaluation data #11" and "multifaceted evaluation data #12" is stored in "multifaceted evaluation data", but in reality, actual measured values ​​based on multifaceted evaluations, etc. are stored.

[0051] That is, FIG. 5 shows an example in which the assessee identified by the multi-faceted evaluation ID "EV11" is "R11", the evaluator is "U11", and the multi-faceted evaluation data is "multi-faceted evaluation data #11".

[0052] The model storage unit 122 stores information about a model that outputs a bias value that quantifies bias related to the evaluation included in the multi-faceted evaluation data and is machine-learned based on Bayesian estimation of the multi-faceted evaluation data. Here, Fig. 6 shows an example of the model storage unit 122 according to the embodiment. As shown in Fig. 6, the model storage unit 122 has items such as "model ID" and "model (calculation formula)".

[0053] "Model ID" indicates identification information for identifying a model. "Model (calculation formula)" indicates the calculation formula of the model. In the example shown in FIG. 6, conceptual information such as "Model #11" and "Model #12" is stored in "Model (calculation formula)", but in reality, when multi-faceted evaluation data and predetermined attribute information are input, information on the calculation formula for calculating a bias value is stored.

[0054] That is, FIG. 6 shows an example in which the calculation formula for the model identified by the model ID "MD11" is "Model #11".

[0055] (Control unit 130) The control unit 130 is a controller, and is realized, for example, by a CPU, an MPU, or the like, executing various programs stored in a storage device inside the information processing device 100 using a RAM as a working area. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC or an FPGA.

[0056] 4, the control unit 130 has an acquisition unit 131, a generation unit 132, a calculation unit 133, a determination unit 134, and a provision unit 135, and realizes or executes the information processing action described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may be other configurations as long as they perform the information processing described below.

[0057] (Acquisition part 131) The acquisition unit 131 acquires various pieces of information. The acquisition unit 131 acquires various pieces of information from an external information processing device. The acquisition unit 131 acquires various pieces of information from another information processing device such as the terminal device 10.

[0058] The acquisition unit 131 acquires various information from the storage unit 120. The acquisition unit 131 acquires various information from the multi-faceted evaluation data storage unit 121 and the model storage unit 122. In addition, the acquisition unit 131 stores the acquired various information in the storage unit 120. The acquisition unit 131 stores the various information in the multi-faceted evaluation data storage unit 121 and the model storage unit 122.

[0059] The acquiring unit 131 acquires the multi-faceted evaluation data transmitted from the terminal device 10 in accordance with the operation of the evaluator. For example, the acquiring unit 131 acquires the multi-faceted evaluation data for a specific evaluee.

[0060] The acquisition unit 131 acquires predetermined attribute information, such as attribute information of the evaluator, attribute information of the person being evaluated, and attribute information related to the multi-faceted evaluation survey.

[0061] (Generation unit 132) The generation unit 132 receives the multi-faceted evaluation data acquired by the acquisition unit 131 and predetermined attribute information, and generates a model that outputs a bias value for each attribute.

[0062] The generation unit 132 generates a machine-learned model using a bias value based on Bayesian estimation for the multi-faceted evaluation data as a positive example.

[0063] (Calculation unit 133) The calculation unit 133 uses the model generated by the generation unit 132 to calculate a bias value.

[0064] The calculation unit 133 calculates a true evaluation value by subtracting a bias value that quantifies the bias.

[0065] (Judgment unit 134) The determining unit 134 determines whether or not the suitability for evaluation (eg, suitability as an evaluator) has improved based on a comparison with the past bias value calculated by the calculating unit 133.

[0066] (Provider 135) The providing unit 135 provides information on the bias value calculated by the calculating unit 133. The providing unit 135 also provides information on a true evaluation value obtained by subtracting a bias value that quantifies the bias from the actual measurement value of the multi-faceted evaluation data.

[0067] [5. Information processing flow] Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the procedure of information processing by the information processing system 1 according to the embodiment.

[0068] As shown in FIG. 7, the information processing device 100 acquires multi-aspect evaluation data (step S201).

[0069] The information processing device 100 generates a machine-learned model based on Bayesian estimation for the acquired multi-faceted evaluation data (step S202).

[0070] The information processing device 100 inputs the acquired multi-faceted evaluation data and predetermined attribute information into the generated model, and calculates a bias value that quantifies the bias for each attribute included in the multi-faceted evaluation data (step S203).

[0071] The information processing device 100 calculates a true evaluation value excluding the bias by subtracting the calculated bias value from the actual measurement value of the multi-faceted evaluation data (step S204).

[0072] The information processing device 100 provides information on the calculated true evaluation value (step S205).

[0073] 6. Effects As described above, the information processing device 100 according to the embodiment includes the acquisition unit 131, the calculation unit 133, and the provision unit 135. The acquisition unit 131 acquires multi-faceted evaluation data. The calculation unit 133 calculates a bias value that quantifies a bias related to the evaluation included in the multi-faceted evaluation data based on Bayesian estimation of the multi-faceted evaluation data acquired by the acquisition unit 131. The provision unit 135 provides information on an evaluation value obtained by subtracting the bias value calculated by the calculation unit 133 from the actual measurement value of the multi-faceted evaluation data.

[0074] As a result, the information processing device 100 according to the embodiment can improve the efficiency of processing by applying Bayesian estimation to perform machine learning. In addition, the information processing device 100 according to the embodiment can quantify bias, and can provide useful information for improving the operation of the evaluation system and providing guidance to evaluators.

[0075] The information processing device 100 according to the embodiment further includes a generating unit 132 that generates a model using multi-faceted evaluation data and predetermined attribute information as input information, and using bias values ​​for each attribute included in the attribute information, which are estimation results of Bayesian estimation, as output information. The calculating unit 133 calculates the bias value using the model generated by the generating unit 132.

[0076] As a result, the information processing device 100 according to the embodiment can appropriately quantify the bias, and therefore can provide more useful information.

[0077] Furthermore, the calculation unit 133 calculates the bias value by using a model generated based on input information including attribute information of the evaluator as the predetermined attribute information.

[0078] This allows the information processing apparatus 100 according to the embodiment to more appropriately quantify the bias for each attribute of the evaluator.

[0079] In addition, the calculation unit 133 calculates the bias value using a model generated based on input information including attribute information of the assessee as the predetermined attribute information.

[0080] This allows the information processing device 100 according to the embodiment to more appropriately quantify the bias for each attribute of the person to be evaluated.

[0081] Furthermore, the calculation unit 133 calculates the bias value using a model generated based on input information including attribute information of a multifaceted evaluation survey as the predetermined attribute information.

[0082] This allows the information processing apparatus 100 according to the embodiment to more appropriately quantify the bias for each attribute of the multi-faceted evaluation survey.

[0083] Furthermore, the calculation unit 133 calculates a bias value by using a model generated using information on a combination based on a relative relationship between attributes as predetermined attribute information.

[0084] As a result, the information processing device 100 according to the embodiment can quantify bias based on the relative relationship between attributes, thereby providing more useful information for improving the operation of the evaluation system and providing guidance to evaluators.

[0085] In addition, the providing unit 135 calculates a bias value using a model generated using as output information the bias value for each attribute calculated based on the actual measured value based on the multi-faceted evaluation and the estimated value indicating the true ability of the person being evaluated which is estimated based on a predetermined probability distribution.

[0086] This allows the information processing device 100 according to the embodiment to appropriately quantify the bias for each attribute based on Bayesian estimation.

[0087] In addition, when the provision unit 135 determines that the bias value has transitioned toward zero based on a comparison between a bias value based on multi-faceted evaluation data acquired at a certain response time and a bias value based on multi-faceted evaluation data acquired after the certain response time, it provides information that the suitability of the evaluation has improved.

[0088] As a result, the information processing apparatus 100 according to the embodiment can review the operation of the evaluation system, and can provide more useful information for improving the operation of the evaluation system and providing guidance to evaluators.

[0089] [7. Hardware Configuration] Moreover, the terminal device 10 and the information processing device 100 according to the above-described embodiments are realized, for example, by a computer 1000 having a configuration as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the terminal device 10 and the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0090] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0091] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0092] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0093] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0094] For example, when the computer 1000 functions as the terminal device 10 and the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control units 14 and 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from other devices via a predetermined communication network.

[0095] [8. Other] In addition, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0096] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0097] Furthermore, the above-described embodiments can be appropriately combined as long as the processing contents are not contradictory.

[0098] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0099] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0100] 1. Information Processing Systems 10 Terminal Equipment 100 Information processing device 110 Communications Department 120 Storage section 121 Multi-faceted evaluation data storage unit 122 Model Memory Section 130 Control section 131 Acquisition Department 132 Generation part 133 Calculation section 134 Judgment section 135 Provision Department N Network

Claims

1. An acquisition unit for acquiring multi-faceted evaluation data; a generation unit that receives as input information multi-faceted evaluation data and predetermined attribute information including attribute information of an evaluator, and generates as output information a bias value for each attribute included in the predetermined attribute information, the bias value being an estimation result of Bayesian estimation, and quantifying a bias related to the evaluation included in the multi-faceted evaluation data; a calculation unit that calculates the bias value based on Bayesian estimation for the multi-faceted evaluation data acquired by the acquisition unit, using the model generated by the generation unit; a providing unit that provides information regarding an evaluation value obtained by subtracting a bias value calculated by the calculating unit from an actual measurement value of the multi-aspect evaluation data; 13. An information processing device comprising:

2. The calculation unit is The bias value is calculated using a model generated based on input information including attribute information of the assessee as the predetermined attribute information.

2. The information processing apparatus according to claim 1,

3. The calculation unit is The bias value is calculated using a model generated based on input information including attribute information from a multifaceted evaluation survey as the predetermined attribute information.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. The calculation unit is The bias value is calculated using a model generated using information regarding a combination based on a relative relationship between attributes as the predetermined attribute information.

4. The information processing device according to claim 1, wherein the information processing device is a computer.

5. The calculation unit is The bias value for each attribute is calculated based on the actual measured value based on the multifaceted evaluation and the estimated value indicating the true ability of the person being evaluated based on a predetermined probability distribution, and the bias value is calculated using the model generated as the output information.

5. The information processing device according to claim 1, wherein the information processing device is a computer.

6. The providing unit is When it is determined that the bias value has transitioned toward zero based on a comparison between a bias value based on multifaceted evaluation data acquired at a certain response time and a bias value based on multifaceted evaluation data acquired after the certain response time, information is provided that the suitability of the evaluation has improved.

6. The information processing device according to claim 1,

7. 1. A computer-implemented information processing method, comprising: An acquisition step of acquiring multi-faceted evaluation data; a generation step of generating a model in which the input information is multi-faceted evaluation data and predetermined attribute information including attribute information of an evaluator, and the output information is a bias value for each attribute included in the predetermined attribute information, the bias value being an estimation result of Bayesian estimation, and quantifying the bias related to the evaluation included in the multi-faceted evaluation data; a calculation step of calculating the bias value based on Bayesian estimation for the multi-faceted evaluation data acquired in the acquisition step, using the model generated in the generation step; a providing step of providing information on an evaluation value obtained by subtracting the bias value calculated in the calculating step from the actual measurement value of the multi-aspect evaluation data; 13. An information processing method comprising:

8. An acquisition procedure for acquiring multi-dimensional evaluation data; a generation procedure for generating a model in which multi-dimensional evaluation data and predetermined attribute information including attribute information of an evaluator are used as input information, and the output information is a bias value for each attribute included in the predetermined attribute information, the bias value being an estimation result of Bayesian estimation, and quantifying the bias related to the evaluation included in the multi-dimensional evaluation data; a calculation step of calculating the bias value based on Bayesian estimation for the multi-faceted evaluation data acquired by the acquisition step, using the model generated by the generation step; a providing step of providing information on an evaluation value obtained by subtracting the bias value calculated by the calculating step from the actual measurement value of the multi-aspect evaluation data; An information processing program characterized by causing a computer to execute the above.

Images