Information processing device, information processing method, and program
The information processing device uses a machine learning classifier to generate two-dimensional maps for evaluating specialized task performance, addressing the challenge of inadequate evaluations by distinguishing between ability and luck, thereby improving personnel assessment.
Patent Information
- Application Number
- JP2021540752
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2019-08-21
- Filing Date
- 2020-08-13
- Publication Date
- 2024-11-13
- Estimated Expiration
- 2040-08-13
AI Technical Summary
Evaluating individuals performing highly specialized tasks, such as investment fund management, is challenging when evaluators lack the same level of specialized knowledge, leading to inadequate assessments.
An information processing device and method that utilizes a machine learning algorithm to generate a classifier for contribution analysis, creating a two-dimensional map to evaluate the behavior of individuals based on their performance data, incorporating attributes of objects targeted by their actions, and expressing intensities in heat maps to distinguish between ability and luck in task performance.
Enables more accurate evaluation of individuals by distinguishing between ability and luck in task performance, allowing for better personnel allocation and decision-making in specialized roles.
Smart Images

Figure 0007582195000001 
Figure 0007582195000002 
Figure 0007582195000003
Abstract
Description
[Technical field]
[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]
[0002] It is very important to properly evaluate the performer of a certain task. For this reason, many mechanisms have been proposed to automate or assist such evaluations. For example, Patent Literature 1 proposes a mechanism for rating investment trust funds. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2009-245368 A Summary of the Invention [Problem to be solved by the invention]
[0004] In particular, when evaluating personnel who carry out highly specialized tasks such as investment trust funds, it is necessary to make more appropriate evaluations based on multifaceted analysis. [Means for solving the problem]
[0005] According to one aspect of the present disclosure, an information processing device is provided, comprising an evaluation unit that evaluates the behavior of a person being evaluated based on behavioral performance data indicating the performance of the behavior of the person being evaluated in relation to a specified task, wherein the evaluation unit performs a contribution analysis that analyzes the contribution of the behavior of the person being evaluated to evaluation items in the specified task, and evaluates the behavior of the person being evaluated based on the results of the contribution analysis, and the contribution analysis includes a classifier generated by a machine learning algorithm generating a two-dimensional map in which a plurality of objects are arranged on a plane based on attributes of a plurality of objects that are the subject of the behavior of the person being evaluated that has been input, and the behavioral performance data for the objects.
[0006] According to another aspect of the present disclosure, there is provided an information processing method including a processor evaluating the behavior of the person being evaluated based on behavioral performance data indicating the performance of the behavior of the person being evaluated regarding a specified task, wherein the evaluation further includes performing a contribution analysis to analyze a contribution of the behavior of the person being evaluated to evaluation items in the specified task, and evaluating the behavior of the person being evaluated based on the results of the contribution analysis, wherein the contribution analysis includes generating a two-dimensional map in which a plurality of objects are arranged on a plane based on attributes of a plurality of objects that are the subject of the behavior of the person being evaluated that are input into a classifier generated by a machine learning algorithm, and the behavioral performance data for the objects.
[0007] According to another aspect of the present disclosure, a program is provided for causing a computer to function as an information processing device, comprising an evaluation unit that evaluates the behavior of the person being evaluated based on behavioral performance data indicating the performance of the behavior of the person being evaluated in relation to a specified task, the evaluation unit performing a contribution analysis that analyzes the contribution of the behavior of the person being evaluated to evaluation items in the specified task, and evaluating the behavior of the person being evaluated based on the results of the contribution analysis, the contribution analysis including generating a two-dimensional map in which a plurality of objects are arranged on a plane based on attributes of a plurality of objects that are the subject of the behavior of the person being evaluated that are input into a classifier generated by a machine learning algorithm, and the behavioral performance data for the objects. [Brief description of the drawings]
[0008] [Figure 1] 1 is a block diagram showing an example of a functional configuration of a learning device 10 according to an embodiment of the present disclosure. [Diagram 2] 2 is a block diagram showing an example of a functional configuration of an evaluation device 20 according to the embodiment. FIG. [Diagram 3] 13 is a diagram for explaining generation of a classifier 215 according to the embodiment and a two-dimensional map M0 output by the classifier 215. FIG. [Figure 4] FIG. 4 is a diagram showing an example of an active return map M1 according to the embodiment. [Diagram 5] FIG. 13 is a diagram showing an example of an active weight map M2 according to the embodiment. [Figure 6] FIG. 11 is a diagram showing an example of an active return & active weight map M3 according to the embodiment. [Figure 7] A figure showing an example of a trading volume map M4 according to the same embodiment. [Figure 8] FIG. 13 is a diagram showing an example of an active return & trading volume map M5 according to the embodiment. [Figure 9] FIG. 13 is a diagram showing an example of an order amount map M6 according to the embodiment. [Figure 10] FIG. 13 is a diagram showing an example of a customer staff member age map M7 according to the embodiment. [Figure 11] FIG. 13 is a diagram showing an example of an order amount map & customer staff age map M8 according to the embodiment. [Figure 12] FIG. 13 is a diagram showing an example of a contract map M9 according to the embodiment. [Figure 13] FIG. 13 is a diagram showing an example of a customer visit map M10 according to the embodiment. [Figure 14] 13 is an example of a contract & visit count map according to the embodiment. [Figure 15] 10 is a flowchart showing an example of a process flow by the evaluation device 20 according to the embodiment. [Figure 16] A figure showing an example of a comparison table comparing evaluations of multiple evaluatees in the same embodiment. [Figure 17] FIG. 2 is a block diagram showing an example of a hardware configuration of an information processing device 90 according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configurations are denoted by the same reference numerals, and redundant description will be omitted.
[0010] The explanation will be given in the following order. 1. Embodiment 1.1. Background 1.2. Example of Functional Configuration of Learning Device 10 1.3. Example of Functional Configuration of Evaluation Device 20 1.4. Evaluation based on contribution analysis 1.5.Processing Flow 2. Hardware configuration example 3. Summary
[0011] <1. Embodiment> <<1.1.Background>> As mentioned above, it is very important to properly evaluate a person who performs a task (hereinafter, referred to as the person being evaluated) regardless of the industry or business. However, when the task performed by the person being evaluated is highly specialized and the evaluator does not have the same level of specialized knowledge about the task as the person being evaluated, it may be difficult to perform a proper evaluation.
[0012] As an example, let us assume that a fund manager is evaluated in a certain fund. An evaluator belonging to the fund evaluates the assessee, for example, a fund manager who has already signed a contract or a new fund manager who is a candidate for a future contract.
[0013] However, if the evaluator from the fund does not have the same specialized knowledge as the person being evaluated, it is difficult for the evaluator to properly evaluate the person being evaluated. In addition, the evaluator may not be able to keep up with the person being evaluated's explanation of the strategy, etc., and may be forced to accept everything the person being evaluated says.
[0014] For this reason, it is important to visualize the evaluation based on multifaceted analysis, especially when evaluating assessees who perform highly specialized tasks such as fund managers (or funds).
[0015] In addition to the level of expertise, there are many other factors that make it difficult to evaluate an individual. For example, consider a salesperson who works in a company or other organization to win contracts with customers.
[0016] The sales activities of the sales staff mentioned above include a wide variety of activities, including customer visits, and the characteristics of the customer and the customer representative also have a strong influence on the success or failure of the contract. For this reason, it can be difficult to construct a theory for concluding a contract, and it can also be difficult to properly evaluate the sales activities of the person being evaluated.
[0017] The technical idea of one embodiment of the present invention was conceived with the above points in mind, and is intended to realize a more appropriate evaluation of the behavior of the person being evaluated.
[0018] For this purpose, one of the features of the evaluation device 20 of one embodiment of the present invention is to perform a contribution analysis to analyze the contribution of the behavior of the person being evaluated to the evaluation items in a specified task, and to evaluate the behavior of the person being evaluated based on the results of the contribution analysis.
[0019] The functional configuration for implementing the above-mentioned evaluation will now be described in detail.
[0020] <<1.2. Example of functional configuration of learning device 10>> First, an example of the functional configuration of the learning device 10 according to this embodiment will be described. The learning device 10 according to this embodiment is an information processing device that generates a classifier 215 used in the contribution analysis by the evaluation device 20.
[0021] Fig. 1 is a block diagram showing an example of the functional configuration of a learning device 10 according to this embodiment. As shown in Fig. 1, the learning device 10 according to this embodiment includes a learning unit 110, a storage unit 120, and the like.
[0022] (Learning section 110) The learning unit 110 according to this embodiment generates a classifier 215 used for contribution analysis by the evaluation device 20 using a machine learning algorithm.
[0023] For example, the learning unit 110 according to this embodiment may generate the classifier 215 by unsupervised learning using a neural network.
[0024] The details of the learning by the learning unit 110 according to this embodiment will be described separately in detail. Note that the functions of the learning unit 110 according to this embodiment are realized by a processor such as a GPU.
[0025] (Storage unit 120) The storage unit 120 according to this embodiment stores various information related to the learning performed by the learning unit 110. For example, the storage unit 120 stores the structure of a network used for learning by the learning unit 110, various parameters related to the network, learning data, and the like.
[0026] An example of the functional configuration of the learning device 10 according to this embodiment has been described above. Note that the functional configuration described above using Fig. 1 is merely an example, and the functional configuration of the learning device 10 according to this embodiment is not limited to this example.
[0027] For example, the study device 10 according to this embodiment may further include an operation unit that accepts operations by a user, a display unit that displays various types of information, and the like.
[0028] The functional configuration of the learning device 10 according to this embodiment can be flexibly modified according to the specifications and operation.
[0029] <<1.3. Example of Functional Configuration of Evaluation Device 20>> Next, a description will be given of an example of the functional configuration of the evaluation device 20 according to this embodiment. The evaluation device 20 according to this embodiment is an information processing device that evaluates the behavior of an individual to be evaluated.
[0030] Fig. 2 is a block diagram showing an example of a functional configuration of the evaluation device 20 according to this embodiment. As shown in Fig. 2, the evaluation device 20 according to this embodiment includes an evaluation unit 210, a storage unit 220, an output unit 230, and the like.
[0031] (Evaluation unit 210) The evaluation unit 210 according to this embodiment evaluates the behavior of the assessee based on behavior performance data indicating the performance of the behavior of the assessee with respect to a predetermined task.
[0032] An example of the assessee in this embodiment is the above-mentioned fund manager. In this case, the above-mentioned specified task may be asset management. An example of the behavior of the assessee is buying and selling of financial products such as stocks. The behavioral performance data may be data recording the performance of the transaction (e.g., the date when a certain stock was bought, the amount bought, the date when a certain stock was sold, the amount sold, etc.).
[0033] Furthermore, the person being evaluated in this embodiment may be, for example, a salesperson belonging to a company or the like. In this case, the above-mentioned specified task may be a contract with the company. Furthermore, the actions of the person being evaluated may include various sales activities such as visiting customers (including potential customers), making phone calls, e-mails, and making presentations. Furthermore, the behavioral performance data may be data that records the performance of such sales activities (for example, the date of visit, the number of phone calls, the number of e-mails, whether or not a presentation was given, etc.).
[0034] Moreover, one of the features of the evaluation unit 210 according to this embodiment is that it performs a contribution analysis using the classifier 215, and evaluates the behavior of the person being evaluated based on the result of the contribution analysis.
[0035] The contribution analysis according to this embodiment may include a classifier 215 generated by a machine learning algorithm generating a two-dimensional map in which multiple objects are arranged on a plane based on the attributes of multiple objects that are the subject of the behavior of the person being evaluated and the behavioral performance data for the objects.
[0036] In addition, the contribution analysis according to this embodiment may further include representing the intensities related to the evaluation items and the intensities related to the behavior of the person being evaluated in the form of a heat map in the two-dimensional map output by the classifier 215.
[0037] The contribution analysis using the classifier 215 according to the present embodiment and the evaluation based on the result of the contribution analysis will be described in detail later. The functions of the evaluation unit 210 according to the present embodiment are realized by a processor such as a GPU or a CPU.
[0038] (Storage unit 220) The storage unit 220 according to this embodiment stores various information used by the evaluation device 20. The storage unit 220 stores information such as, for example, behavioral performance data indicating the performance of the behavior of the person to be evaluated, a program used by the evaluation unit 210, and the result of the evaluation by the evaluation unit 210.
[0039] (Output unit 230) The output unit 230 according to the present embodiment outputs the result of the evaluation by the evaluation unit 210. For example, the output unit 230 according to the present embodiment may display the result of the evaluation. In this case, the output unit 230 includes various displays. Also, for example, the output unit 230 may print the result of the evaluation on a paper medium. In this case, the output unit 230 includes a printer.
[0040] The above describes an example of the functional configuration of the evaluation device 20 according to the present embodiment. Note that the functional configuration described with reference to Fig. 2 is merely an example, and the functional configuration of the evaluation device 20 according to the present embodiment is not limited to this example.
[0041] For example, the evaluation unit 210 and the output unit 230 do not necessarily have to be provided in the same device. As an example, the output unit 230 provided in a locally deployed device may obtain a result of evaluation by the evaluation unit 210 provided in a separate device deployed in the cloud, and output the result.
[0042] The functional configuration of the evaluation device 20 according to this embodiment can be flexibly modified according to the specifications and operation.
[0043] <<1.4. Evaluation based on contribution analysis>> Next, the contribution analysis using the classifier 215 by the evaluation unit 210 according to this embodiment and the evaluation based on the result of the contribution analysis will be described.
[0044] The contribution analysis according to this embodiment analyzes the contribution of an assessee's behavior to evaluation items in a specified task.
[0045] In addition, the contribution analysis according to this embodiment includes the classifier 215 generating a two-dimensional map in which multiple objects are arranged on a plane based on the attributes of multiple objects that are the subject of the inputted evaluator's actions and the action performance data for the objects.
[0046] For example, when the task is asset management, the object according to this embodiment may be a stock name.
[0047] Also, for example, if the task is a contract with a customer, the target according to this embodiment may be a customer (which may include a potential customer).
[0048] First, a method for generating the classifier 215 according to this embodiment will be described. Fig. 13 is a diagram for explaining the generation of the classifier 215 according to this embodiment and the two-dimensional map M0 output by the classifier 215.
[0049] The classifier 215 according to the present embodiment uses the attributes of a plurality of objects that are targets of actions taken by an evaluator and the action record data for the objects as input data ID, and outputs a two-dimensional map M0 in which a plurality of objects are arranged on a plane. Each of the rectangles in the two-dimensional map M0 shown in FIG. 10 represents the above-mentioned objects.
[0050] In other words, the classifier 215 according to this embodiment has a function of mapping a high-dimensional data set to a low-dimensional space while preserving the topological structure of the data distribution.
[0051] The classifier 215 according to this embodiment can be generated, for example, by repeatedly performing unsupervised learning in which the above-mentioned input data ID is given to the NN (Neural Network) 116 and the NN 116 outputs the two-dimensional map M0.
[0052] The classifier 215 according to the present embodiment may be, for example, a self-organizing map. On the other hand, the classifier 215 according to the present embodiment may be generated using an algorithm such as a variational autoencoder (VAE).
[0053] The evaluation unit 210 according to the present embodiment performs a contribution analysis using the classifier 215 generated as described above. At this time, one of the features of the evaluation unit 210 according to the present embodiment is that the two-dimensional map M0 output by the classifier 215 expresses the intensities related to the evaluation items in a predetermined task and the intensities related to the behavior of the subject in the form of a heat map.
[0054] For example, when the predetermined task is asset management, an example of the evaluation item is active return, which is an index showing the difference between the return of a portfolio and the return of a benchmark.
[0055] The evaluation unit 210 in this embodiment may calculate an active return based on the attributes of the stock (here, the return of the above-mentioned benchmark) and the behavioral performance data (here, the return of the portfolio), and generate an active return map M1 that represents the active return in the form of a heat map on the two-dimensional map M0.
[0056] Fig. 4 is a diagram showing an example of the active return map M1 according to this embodiment. In the active return map M1 shown in Fig. 4, the strength of the active return is represented by the density of the diagonal lines.
[0057] Specifically, in the active return map M1 shown in Figure 4, areas where the portfolio return significantly exceeds the benchmark return are shown with dense diagonal lines, and areas where there is almost no difference between the portfolio return and the benchmark return are shown with sparse diagonal lines. Also, areas where the portfolio return significantly falls short of the benchmark return are shown in solid white.
[0058] In the active return map M1 shown in FIG. 4, the strength of the active return is represented by the above three stages in order to prioritize ease of viewing, but the evaluation unit 210 according to this embodiment may express the strength of the active return in more stages and continuously.
[0059] In addition, in the active return map M1 shown in Fig. 4, in order to prioritize ease of viewing, the representation of each stock arranged on a flat surface is omitted. The same applies to each heat map shown below.
[0060] In addition, the evaluation section 210 according to this embodiment may further generate a heat map indicating the intensity of the behavior of the subject to be compared with a heat map indicating the intensity of the evaluation items in a specified task, such as the active return map M1.
[0061] An example of an indicator of the strength of the target's behavior is active weight, which is an indicator indicating the deviation between the composition ratio of stocks in a portfolio and the composition ratio of stocks in a benchmark.
[0062] The evaluation unit 210 in this embodiment may calculate active weights based on the attributes of the stocks (here, the composition ratio of the stocks in the above benchmark) and the behavioral performance data (here, the composition ratio of the stocks in the portfolio), and generate an active weight map M2 that represents the active weights in the form of a heat map in the two-dimensional map M0.
[0063] Fig. 5 is a diagram showing an example of an active weight map M2 according to this embodiment. In the active weight map M2 shown in Fig. 5, the strength of the active return is represented by the density of dots.
[0064] Specifically, in the active weight map M2 shown in Figure 5, areas where the amount of stocks held in the portfolio significantly exceeds the amount of stocks held in the benchmark are represented by high density dots. Areas where there is almost no difference between the amount of stocks held in the portfolio and the amount of stocks held in the benchmark are represented by low density dots. Areas where the amount of stocks held in the portfolio is significantly less than the amount of stocks held in the benchmark are represented by a solid color (white).
[0065] In the active weight map M2 shown in FIG. 5, the strength of the active weight is expressed in the above three stages in order to prioritize visibility, but the evaluation unit 210 according to this embodiment may express the strength of the active weight in more stages and continuously.
[0066] Specific examples of heat maps showing intensities related to evaluation items according to this embodiment and heat maps showing intensities related to actions by subjects have been given above.
[0067] The evaluation section 210 according to this embodiment may further generate a heat map by superimposing the above two generated heat maps.
[0068] In addition, at this time, the evaluation unit 210 according to this embodiment may evaluate whether or not the contribution of the behavior of the person being evaluated to the evaluation item is due to the ability of the person being evaluated, based on a heat map (two-dimensional map) in which the above two heat maps are superimposed.
[0069] For example, the evaluation section 210 according to this embodiment may generate the active return & active weight map M3 by superimposing the active return map M1 and the active weight map M2.
[0070] 6 is a diagram showing an example of the active return & active weight map M3 according to this embodiment. In this case, the evaluation unit 210 according to this embodiment can evaluate whether the contribution of the behavior of the assessee to the active return is due to the ability of the assessee based on the active return & active weight map M3.
[0071] Specifically, the evaluation unit 210 according to this embodiment may evaluate an area where an area with high intensity related to an evaluation item overlaps with an area with high intensity related to the behavior of the person being evaluated as an area where the contribution of the ability of the person being evaluated is high.
[0072] For example, in the active return & active weight map M3 shown in Figure 6, areas with high active return and high active weight are expressed by overlapping high density diagonal lines and high density dots. This area can be said to be an area where the stock holdings are large and profits are being generated due to the actions of the assessee.
[0073] For this reason, the evaluation unit 210 in this embodiment may evaluate an area where the strength of active return overlaps with the strength of active weight, as an area where profits have been generated due to the ability of the person being evaluated (Good choice), such as the above-mentioned area.
[0074] In addition, the evaluation unit 210 according to this embodiment may evaluate an area where an area with high intensity related to an evaluation item overlaps with an area with low intensity related to the behavior of the person being evaluated as an area where the contribution of the ability of the person being evaluated is low, i.e., an area where benefits are generated by luck.
[0075] For example, in the active return & active weight map M3 shown in Figure 6, areas where the active return is high and the active weight is low are represented by dense diagonal lines. This area can be said to be an area where the holding volume of stocks is low but relatively profitable.
[0076] For this reason, the evaluation unit 210 according to this embodiment may evaluate an area where the strength of active return is high and the strength of active weight is low, as an area where profits are generated by luck (Luck), as in the above-mentioned area.
[0077] In addition, the evaluation unit 210 may evaluate an area where an area of low intensity related to an evaluation item overlaps with an area of high intensity related to the behavior of the person being evaluated as an area where the behavior of the person being evaluated may be affecting the decline of the evaluation item.
[0078] For example, in the active return & active weight map M3 shown in Figure 6, areas where the active return is low and the active weight is high are represented by dense dots. This area can be said to be an area where the stock holdings are large and losses are occurring due to the actions of the assessee.
[0079] For this reason, the evaluation unit 210 in this embodiment may evaluate an area where the intensity of active return is low and the intensity of active weighting overlap, such as the above-mentioned area, as an area where profits and losses have occurred due to the actions of the person being evaluated (bad choice).
[0080] In addition, the evaluation unit 210 in this embodiment can also calculate an Intentional profit ratio (IPR), which indicates the profit generated in asset management that is due to the ability of the person being evaluated, based on the area of each region evaluated as described above.
[0081] For example, in the case of the example shown in FIG. 13, the IPR may be calculated by the following formula: IPR = Good choice / Good choice + Luck
[0082] In this way, evaluation using the evaluation unit 210 of this embodiment makes it possible to more appropriately evaluate the abilities of the person being evaluated, compared to simply evaluating the person being evaluated using active returns alone.
[0083] In addition, the evaluation unit 210 can continuously calculate the IPR at predetermined intervals, thereby making it possible to evaluate how the ability of the person being evaluated is changing.
[0084] In addition, in the above, an example is given in which the evaluation unit 210 evaluates the evaluatee based on the active return and active weight, but the evaluation by the evaluation unit 210 according to this embodiment is not limited to this example.
[0085] The evaluation unit 210 according to this embodiment may evaluate the person being evaluated based on, for example, active return and trading volume.
[0086] Fig. 7 is a diagram showing an example of a trading volume map M4 according to this embodiment. In the trading volume map M4 shown in Fig. 7, the strength of the trading volume is represented by the density of the diagonal lines.
[0087] Specifically, in the trading volume map M4 shown in Figure 7, areas with high trading volume are indicated by high density diagonal lines, areas with medium trading volume are indicated by low density diagonal lines, and areas with low trading volume are indicated by solid color (white).
[0088] In the trading volume map M4 shown in FIG. 7, the strength of the trading volume is represented by the above three stages in order to prioritize ease of viewing, but the evaluation unit 210 in this embodiment may express the strength of the trading volume in more stages and continuously.
[0089] Furthermore, the evaluation section 210 according to this embodiment may generate an active return & trading volume map M5 by superimposing the active return map M1 and the trading volume map M4.
[0090] 8 is a diagram showing an example of the active return & trading volume map M5 according to this embodiment. In this case, the evaluation unit 210 according to this embodiment can evaluate whether the contribution of the behavior of the assessee to the active return is due to the ability of the assessee based on the active return & trading volume map M5.
[0091] For example, in the active return & trading volume map M5 shown in Figure 8, the area with high active return and trading volume map is expressed by overlapping high density diagonal lines and high density dots. This area can be said to be an area where the stock trading volume is high and profits are being made due to the actions of the assessee.
[0092] For this reason, the evaluation unit 210 in this embodiment may evaluate an area where an area of high active return intensity overlaps with an area of high trading volume intensity as an area where profits have been generated due to the ability of the person being evaluated (Good trade).
[0093] On the other hand, in the active return & trading volume map M5 shown in Figure 8, areas with high active return and low trading volume are represented by densely shaded areas. These areas can be said to be areas where the stock's trading volume is low but where profits are relatively high.
[0094] For this reason, the evaluation unit 210 according to this embodiment may evaluate the area where the area of high intensity of active return overlaps with the area of low intensity of trading volume as an area where profits were generated by luck (Luck).
[0095] On the other hand, in the active return & trading volume map M5 shown in Figure 8, areas with low active return and high trading volume are represented by dense dots. This area can be said to be an area where the stock trading volume is high and losses are occurring due to the actions of the assessee.
[0096] For this reason, the evaluation unit 210 in this embodiment may evaluate an area where an area of low active return intensity overlaps with an area of high trading volume intensity as an area where a profit or loss has occurred due to the actions of the person being evaluated (due to miscalculation) (bad trade).
[0097] The evaluation using the evaluation unit 210 according to the present embodiment has been described above with specific examples. The evaluation unit 210 according to the present embodiment can heat map various attributes and indices based on the attributes in addition to the above-mentioned active return, active weight, and trading volume.
[0098] The evaluation unit 210 according to this embodiment may generate a heat map relating to, for example, PBR (Price Book-value Ratio), PER (Price Earnings Ratio), stock yield, etc., and perform evaluation based on the heat map.
[0099] According to the evaluation method using the evaluation unit 210 of this embodiment, it is possible to evaluate, for example, which industrial sectors the investment was in, or which regional areas the investment was in, in which case the investment demonstrated its true potential (the prediction was wrong).
[0100] In addition, according to the evaluation method using the evaluation unit 210 of this embodiment, it becomes possible to evaluate, for example, whether a lack of profit was unavoidable due to the influence of the market environment, or whether it was due to the investment style.
[0101] The above describes the contribution analysis and the evaluation based on the contribution analysis when the task is asset management and the actions of the assessee are buying and selling financial instruments.
[0102] On the other hand, the tasks and actions of the assessee according to this embodiment are not limited to the above examples. For example, the tasks according to this embodiment may be a contract with a customer. In this case, the actions of the assessee may be sales activities.
[0103] In the following, we will explain contribution analysis when the person being evaluated is a sales employee belonging to a company, etc., and the evaluation based on said contribution analysis, using specific examples.
[0104] In this case, the attributes of the object and the behavioral performance data are also input to the classifier 215. When the task is a contract with a customer, the object may be a customer (which may include a potential customer) or a customer representative.
[0105] When the object is a customer, the attributes include, for example, market capitalization, sales, operating profit, number of employees, region, industry, and the like.
[0106] Furthermore, in the case where the object is a customer representative, the attributes include, for example, the position, age, sex, organization, place of origin, and the like.
[0107] Examples of behavioral performance data input to the classifier 215 include the number of customer visits (frequency), the number of e-mails (frequency), the number of phone calls (frequency), the duration of calls, contract success or failure, order amount, etc. The classifier 215 may receive as many sets of behavioral performance data as there are sales staff to be evaluated.
[0108] Contribution analysis and evaluation based on the results of the contribution analysis will be described below with specific examples.
[0109] When the task is a contract with a customer, the evaluation item of the assessee may be, for example, the order amount. Therefore, the evaluation unit 210 according to the present embodiment may generate an order amount map M6 that expresses the order amount of the corresponding assessee in the form of a heat map based on the inputted attributes of the object and the behavioral performance data.
[0110] 9 is a diagram showing an example of an order amount map M6 according to this embodiment. In the order amount map M6 shown in FIG. 9, the strength of the order amount of the corresponding assessee is expressed by the density of the diagonal lines.
[0111] Specifically, in the order amount map M6 shown in Fig. 9, areas where the order amount is higher than a certain value are shown with high density diagonal lines, and areas where the order amount is medium are shown with low density diagonal lines. Also, areas where the order amount is lower than a certain value (including 0) are shown in a solid color (white).
[0112] In the order amount map M6 shown in Figure 9, the strength of the order amount is represented in the above three stages to prioritize ease of viewing, but the evaluation unit 210 in this embodiment may express the strength of the order amount in more stages and continuously.
[0113] It should be noted that, although various behaviors are expected regarding attributes of objects that can be compared with the order amount, the age of the customer representative is used here as an example.
[0114] 10 is a diagram showing an example of a customer representative age map M7 according to the present embodiment. In the customer representative age map M7 shown in FIG 10, the strength of the age of the customer representative is expressed by the density of dots.
[0115] Specifically, in the customer representative age map M7 shown in Fig. 10, areas where the customer representative is 51 years old or older are represented by high density dots, and areas where the customer representative is 36 to 50 years old are represented by low density dots. Also, areas where the customer representative is 35 years old or younger are represented by a solid color (white).
[0116] In the customer representative age map M7 shown in Figure 10, the age intensity of the customer representative is represented by the above three stages in order to prioritize ease of viewing, but the evaluation unit 210 in this embodiment may express the age intensity in more stages and continuously.
[0117] Furthermore, the evaluation unit 210 according to this embodiment may generate an order amount map & customer staff member age map M8 by superimposing the generated order amount map M6 and customer staff member age map M7.
[0118] Fig. 11 is a diagram showing an example of the order amount map & customer representative age map M8 according to this embodiment. Referring to Fig. 11, it can be seen that the distribution of the area where the intensity of the order amount is high (high density diagonal lines) and the area where the intensity of the age of the customer representative is high (high density dots) are similar, and the area where the two overlap (high density diagonal lines and dots) is large.
[0119] In such a case, the evaluation unit 210 according to this embodiment may evaluate that the person being evaluated tends to receive high order amounts from customer representatives who are 51 years of age or older.
[0120] In addition, the evaluation unit 210 may evaluate that an area where the order amount is still low (or zero) and the customer representative is 51 years old or older, i.e., an area represented only by high density dots in the order amount map & customer representative age map M8, is one in which the person being evaluated in question may be able to demonstrate his or her strengths.
[0121] By looking at the evaluations above, managers can make appropriate personnel allocation decisions, such as having the relevant evaluated individuals conduct sales activities in companies that have customer representatives aged 51 or older who still have low (or no) order volumes.
[0122] In addition, in the order amount map and customer representative age map M8 shown in Figure 11, it can be seen that there is a large overlap between the area with low order amounts (or 0) (solid white) and the area of customer representatives aged 35 or younger (solid white).
[0123] In this case, the evaluation unit 210 may further superimpose a heat map relating to the behavior of the person being evaluated (e.g., customer visits, etc.) and perform further evaluation.
[0124] Here, for example, if the intensity of customer visits by the assessee is low in an area where the order amount is low and the customer representative is 35 years old or younger, the evaluation unit 210 may evaluate that the assessee does not have difficulty with customer representatives aged 35 or younger, and that there is a possibility that the order amount will increase by making more customer visits in the future.
[0125] In this way, the evaluation unit 210 according to this embodiment is also capable of performing multifaceted evaluation based on a plurality of attributes and actions.
[0126] Next, another example of evaluation relating to sales activities will be given with reference to FIGS.
[0127] Fig. 12 is a diagram showing an example of a contract map M9 according to this embodiment. In the contract map M9 shown in Fig. 12, whether a contract with a customer has been concluded or not is expressed by the presence or absence of a diagonal line.
[0128] Specifically, in the contract map M9 shown in FIG. 12, areas where a contract has been concluded with a customer are indicated by diagonal lines, and areas where a contract has not been concluded with a customer are indicated by plain white.
[0129] In addition, Fig. 13 is a diagram showing an example of a customer visit map M10 according to this embodiment. In the customer visit map M10 shown in Fig. 13, the intensity of customer visits by the corresponding assessee is expressed by the density of dots.
[0130] Specifically, in the customer visit map M10 shown in Fig. 13, areas where the number of customer visits is greater than a predetermined number are represented by high-density dots, areas where the number of customer visits is medium are represented by low-density dots, and areas where the number of customer visits is less than a predetermined number are represented by solid white.
[0131] In the customer visit map M10 shown in FIG. 13, the intensity of customer visits is represented by the above three stages in order to prioritize ease of viewing, but the evaluation unit 210 in this embodiment may express the intensity of customer visits in more stages and continuously.
[0132] Fig. 14 is an example of a contract and visit count map according to this embodiment. Referring to Fig. 14, it can be seen that the distribution of areas where contracts have been concluded (diagonal lines) and areas where the intensity of customer visits is high (high density dots) are different, and the area where the two overlap (diagonal lines and high density dots) is very small.
[0133] In such a case, the evaluation unit 210 according to this embodiment may evaluate that the customer visits made by the person being evaluated have not led to the conclusion of a contract (current situation).
[0134] In such a case, the evaluation unit 210 may further superimpose a heat map relating to another behavior by the person being evaluated (for example, the number of phone calls, etc.) and perform a further evaluation.
[0135] Here, for example, in an area where a contract has been concluded, if the strength of the number of phone calls made by the assessee is high, the evaluation unit 210 may evaluate that there is a higher possibility of closing the contract by making sales calls rather than visiting customers.
[0136] By looking at the evaluations as described above, managers and others will be able to give appropriate advice to the person being evaluated regarding future sales activities.
[0137] <<1.5. Processing flow>> Next, an example of the flow of processing by the evaluation device 20 according to this embodiment will be described. Fig. 15 is a flow chart showing an example of the flow of processing by the evaluation device 20 according to this embodiment.
[0138] As shown in FIG. 15, first, the evaluation unit 210 inputs the attributes of the object and the behavioral performance data to the classifier 215 (S102).
[0139] Next, the evaluation unit 210 performs a contribution analysis using a classifier (S104).
[0140] Next, the evaluation unit 210 performs an evaluation based on the result of the contribution analysis in step S104 (S106).
[0141] Next, the output unit 230 outputs the result of the evaluation in step S106 (S108).
[0142] For example, the output unit 230 may output the maps shown in FIGS.
[0143] Furthermore, the output unit 230 may output, for example, a comparison table comparing the evaluations of multiple evaluatees, as shown in FIG.
[0144] In the example of the comparison table shown in FIG. 16, the active return and the results of evaluation by the evaluation unit 210 are listed for each of the evaluatees, namely, Company A, Company B, and Company C.
[0145] Furthermore, by referring to a comparison table such as that shown in Figure 16, evaluators belonging to the fund can select from multiple evaluators to contract with in the future, or consider terminating the contract with a currently contracted fund manager. <2. Hardware configuration example> Next, a hardware configuration example common to the learning device 10 and the evaluation device 20 according to an embodiment of the present disclosure will be described. FIG. 17 is a block diagram showing a hardware configuration example of an information processing device 90 according to an embodiment of the present disclosure. The information processing device 90 may be a device having a hardware configuration equivalent to each of the above devices. As shown in FIG. 17, the information processing device 90 has, for example, a processor 871, a ROM 872, a RAM 873, a host bus 874, a bridge 875, an external bus 876, an interface 877, an input device 878, an output device 879, a storage 880, a drive 881, a connection port 882, and a communication device 883. Note that the hardware configuration shown here is an example, and some of the components may be omitted. In addition, the information processing device 90 may further include components other than the components shown here.
[0146] (Processor 871) The processor 871 functions, for example, as an arithmetic processing device or control device, and controls all or part of the operation of each component based on various programs recorded in the ROM 872, the RAM 873, the storage 880, or the removable recording medium 901.
[0147] (ROM 872, RAM 873) The ROM 872 is a means for storing the programs read into the processor 871, data used in calculations, etc. The RAM 873 temporarily or permanently stores, for example, the programs read into the processor 871 and various parameters that change appropriately when the programs are executed.
[0148] (host bus 874, bridge 875, external bus 876, interface 877) The processor 871, ROM 872, and RAM 873 are connected to one another via, for example, a host bus 874 capable of high-speed data transmission. On the other hand, the host bus 874 is connected to an external bus 876 having a relatively low data transmission speed via, for example, a bridge 875. In addition, the external bus 876 is connected to various components via an interface 877.
[0149] (Input Device 878) The input device 878 may be, for example, a mouse, a keyboard, a touch panel, a button, a switch, a lever, etc. Furthermore, a remote controller capable of transmitting a control signal using infrared rays or other radio waves may be used as the input device 878. The input device 878 may also include an audio input device such as a microphone.
[0150] (Output Device 879) The output device 879 is a device capable of visually or audibly notifying the user of acquired information, such as a display device such as a CRT (Cathode Ray Tube), LCD, or organic EL, an audio output device such as a speaker or a headphone, a printer, a mobile phone, a facsimile, etc. The output device 879 according to the present disclosure also includes various vibration devices capable of outputting tactile stimuli.
[0151] (Storage 880) The storage 880 is a device for storing various types of data. For example, a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, or a magneto-optical storage device may be used as the storage 880.
[0152] (Drive 881) The drive 881 is a device that reads information recorded on a removable recording medium 901 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, or writes information to the removable recording medium 901.
[0153] (Removable recording media 901) The removable recording medium 901 is, for example, a DVD medium, a Blu-ray (registered trademark) medium, an HD DVD medium, various semiconductor storage media, etc. Of course, the removable recording medium 901 may be, for example, an IC card equipped with a non-contact type IC chip, an electronic device, etc.
[0154] (Connection port 882) The connection port 882 is a port for connecting an external device 902, such as a Universal Serial Bus (USB) port, an IEEE 1394 port, a Small Computer System Interface (SCSI), an RS-232C port, or an optical audio terminal.
[0155] (External connection device 902) The external connection device 902 is, for example, a printer, a portable music player, a digital camera, a digital video camera, or an IC recorder.
[0156] (Communication Device 883) The communication device 883 is a communication device for connecting to a network, such as a communication card for wired or wireless LAN, Bluetooth (registered trademark), or WUSB (Wireless USB), a router for optical communications, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various types of communications.
[0157] <3. Summary> As described above, the evaluation device 20 according to an embodiment of the present disclosure includes the evaluation unit 210 that evaluates the behavior of the assessee based on the behavior performance data indicating the performance of the behavior of the assessee in relation to a specific task. In addition, the evaluation unit 210 according to an embodiment of the present disclosure is characterized in that it performs a contribution analysis that analyzes the contribution of the behavior of the assessee to the evaluation items in the specific task, and evaluates the behavior of the assessee based on the result of the contribution analysis. In addition, the contribution analysis is characterized in that a classifier generated by a machine learning algorithm generates a two-dimensional map in which multiple objects are arranged on a plane based on the attributes of multiple objects that are the targets of the behavior of the assessee that is input and the behavior performance data for the objects.
[0158] According to the above configuration, it is possible to realize a more appropriate evaluation of the behavior of the person being evaluated.
[0159] Although the preferred embodiment of the present disclosure has been described in detail above with reference to the attached drawings, the technical scope of the present disclosure is not limited to such examples. It is clear that a person having ordinary knowledge in the technical field of the present disclosure can conceive of various modified or amended examples within the scope of the technical ideas described in the claims, and it is understood that these also naturally belong to the technical scope of the present disclosure.
[0160] Furthermore, the steps of the processes described in this specification do not necessarily have to be processed in chronological order according to the order described in the flowchart or sequence diagram. For example, the steps of the processes of each device may be processed in an order different from the order described, or may be processed in parallel.
[0161] Furthermore, the series of processes performed by each device described in this specification may be realized using any of software, hardware, and a combination of software and hardware. The programs constituting the software are stored in advance, for example, in a recording medium (non-transitory medium) provided inside or outside each device. Then, each program is loaded into a RAM when executed by a computer, for example, and executed by various processors. The recording medium is, for example, a magnetic disk, an optical disk, a magneto-optical disk, a flash memory, etc. Furthermore, the computer programs may be distributed, for example, via a network, without using a recording medium.
[0162] In addition, the effects described in this specification are merely descriptive or exemplary and are not limiting. In other words, the technology according to the present disclosure may achieve other effects that are apparent to a person skilled in the art from the description of this specification, in addition to or in place of the above effects.
[0163] Note that the following configurations also fall within the technical scope of the present disclosure. (1) an evaluation unit that evaluates the behavior of the person to be evaluated based on behavior performance data indicating the behavior of the person to be evaluated regarding a predetermined task; Equipped with The evaluation unit performs a contribution analysis to analyze a contribution of the behavior of the person being evaluated to the evaluation items in the predetermined task, and evaluates the behavior of the person being evaluated based on a result of the contribution analysis; The contribution analysis includes a classifier generated by a machine learning algorithm generating a two-dimensional map in which a plurality of objects are arranged on a plane based on the input attributes of the objects that are the targets of the actions of the assessee and the action performance data for the objects. Information processing device. (2) The contribution analysis further includes expressing the intensity related to the evaluation item and the intensity related to the behavior of the assessee in a heat map form in the two-dimensional map. The information processing device according to (1). (3) The evaluation unit evaluates whether or not the contribution of the behavior of the person being evaluated to the evaluation item is due to the ability of the person being evaluated based on the two-dimensional map. The information processing device according to (2). (4) The evaluation unit evaluates, in the two-dimensional map, an area where an area with high intensity related to the evaluation item and an area with high intensity related to the behavior of the person being evaluated overlap as an area where the contribution of the ability of the person being evaluated is high. The information processing device according to (3). (5) The evaluation unit evaluates, in the two-dimensional map, an area where an area with high intensity related to the evaluation item overlaps with an area with low intensity related to the behavior of the person being evaluated, as an area where the contribution of the person being evaluated's ability is low. The information processing device according to (3) or (4). (6) The evaluation unit evaluates an area in the two-dimensional map where an area with low intensity related to the evaluation item overlaps with an area with high intensity related to the behavior of the person being evaluated as an area where the behavior of the person being evaluated may be affecting the decline of the evaluation item; Evaluate as an area, The information processing device according to any one of (3) to (5). (7) The predetermined task includes asset management. The information processing device according to any one of (3) to (6). (8) The actions of the assessee include buying and selling of financial instruments; The information processing device according to any one of (3) to (7). (9) The evaluation unit evaluates an area in the two-dimensional map where an area with high active return intensity and an area with high active weight intensity overlap as an area where a profit has been generated by the ability of the person being evaluated. The information processing device according to (7) or (8). (10) The evaluation unit evaluates an area in the two-dimensional map where an area with a high intensity of active return and an area with a low intensity of active weight overlap as an area where a profit is generated by luck. The information processing device according to any one of (7) to (9). (11) The evaluation unit evaluates an area in the two-dimensional map where an area with low active return intensity and an area with high active weight intensity overlap as an area where a profit or loss has occurred due to the behavior of the person being evaluated. The information processing device according to any one of (7) to (10). (12) The evaluation unit evaluates an area in the two-dimensional map where an area of high active return intensity and an area of high trading volume intensity overlap as an area where profits have been generated by the ability of the person being evaluated. The information processing device according to any one of (7) to (11). (13) The evaluation unit evaluates an area in the two-dimensional map where an area of high active return intensity and an area of low trading volume intensity overlap as an area where profits have been generated by luck. The information processing device according to any one of (7) to (12). (14) The evaluation unit evaluates an area in the two-dimensional map where an area of low active return intensity and an area of high trading volume intensity overlap as an area where profits and losses have occurred due to the actions of the person being evaluated. The information processing device according to any one of (7) to (13). (15) The predetermined task includes contracting with a customer. The information processing device according to any one of (3) to (6). (16) The actions of the assessee include sales activities, The information processing device according to any one of (3) to (6) or (15). (17) The classifier comprises a self-organizing map. The information processing device according to any one of (1) to (16). (18) an output unit that outputs a result of the evaluation by the evaluation unit; Further comprising: The information processing device according to any one of (1) to (17). (19) The processor evaluates the behavior of the person to be evaluated based on behavior performance data indicating the performance of the behavior of the person to be evaluated regarding a predetermined task; Including, The evaluation further includes performing a contribution analysis to analyze a contribution of the behavior of the assessee to the evaluation items in the predetermined task, and evaluating the behavior of the assessee based on a result of the contribution analysis; The contribution analysis includes generating a two-dimensional map in which a plurality of objects are arranged on a plane based on attributes of the plurality of objects that are the targets of the behavior of the assessee inputted to a classifier generated by a machine learning algorithm and the behavior performance data for the objects; Information processing methods. (20) Computer, an evaluation unit that evaluates the behavior of the person to be evaluated based on behavior performance data indicating the behavior of the person to be evaluated regarding a predetermined task; Equipped with The evaluation unit performs a contribution analysis to analyze a contribution of the behavior of the person being evaluated to the evaluation items in the predetermined task, and evaluates the behavior of the person being evaluated based on a result of the contribution analysis; The contribution analysis includes generating a two-dimensional map in which a plurality of objects are arranged on a plane based on attributes of the plurality of objects that are the targets of the behavior of the assessee inputted to a classifier generated by a machine learning algorithm and the behavior performance data for the objects; Information processing device, A program to function as a [Explanation of symbols]
[0164] 10 Learning Device 110 Learning Department 120 Storage section 20 Evaluation Equipment 210 Evaluation Department 215 Classifier 220 Storage section 230 Output section
Claims
1. an evaluation unit that evaluates the behavior of the person to be evaluated based on behavior performance data indicating the behavior of the person to be evaluated regarding a predetermined task; Equipped with The evaluation unit performs a contribution analysis to analyze a contribution of the behavior of the person being evaluated to the evaluation items in the predetermined task, and evaluates the behavior of the person being evaluated based on a result of the contribution analysis; The contribution analysis includes: a classifier generated by a machine learning algorithm generates a two-dimensional map in which a plurality of objects are arranged on a plane based on the attributes of a plurality of objects that are the targets of the actions of the assessee and the action performance data for the objects; and expressing the intensities related to the evaluation items and the intensities related to the actions of the assessee in a heat map form on the two-dimensional map; The evaluation unit evaluates whether or not the contribution of the behavior of the person being evaluated to the evaluation item is due to the ability of the person being evaluated based on the two-dimensional map. Information processing device.
2. The evaluation unit evaluates, in the two-dimensional map, an area where an area with high intensity related to the evaluation item and an area with high intensity related to the behavior of the person being evaluated overlap as an area where the contribution of the ability of the person being evaluated is high. The information processing device according to claim 1 .
3. The evaluation unit evaluates, in the two-dimensional map, an area where an area with high intensity related to the evaluation item and an area with low intensity related to the behavior of the person being evaluated overlap as an area where the contribution of the person being evaluated's ability is low. The information processing device according to claim 1 .
4. The evaluation unit evaluates an area in the two-dimensional map where an area with low intensity related to the evaluation item overlaps with an area with high intensity related to the behavior of the person being evaluated as an area where the behavior of the person being evaluated may be affecting the decline of the evaluation item; Evaluate as an area, The information processing device according to claim 1 .
5. The predetermined task includes asset management. The information processing device according to claim 1 .
6. The actions of the assessee include buying and selling of financial instruments; The information processing device according to claim 1 .
7. The evaluation unit evaluates an area in the two-dimensional map where an area with high active return intensity and an area with high active weight intensity overlap as an area where a profit has been generated by the ability of the person being evaluated. The information processing device according to claim 5 .
8. The evaluation unit evaluates, in the two-dimensional map, an area where an area where the intensity of active return is high and an area where the intensity of active weight is low overlap as an area where a profit is generated by luck. The information processing device according to claim 5 .
9. The evaluation unit evaluates an area in the two-dimensional map where an area with low active return intensity and an area with high active weight intensity overlap as an area where a profit or loss has occurred due to the behavior of the person being evaluated. The information processing device according to claim 5 .
10. The evaluation unit evaluates an area in the two-dimensional map where an area of high active return intensity and an area of high trading volume intensity overlap as an area where a profit has been generated by the ability of the person being evaluated. The information processing device according to claim 5 .
11. The evaluation unit evaluates, in the two-dimensional map, an area where an area of high intensity of active return and an area of low intensity of trading volume overlap as an area where profits have been generated by luck. The information processing device according to claim 5 .
12. The evaluation unit evaluates an area in the two-dimensional map where an area of low active return intensity and an area of high trading volume intensity overlap as an area where profits and losses have occurred due to the actions of the person being evaluated. The information processing device according to claim 5 .
13. The predetermined task includes contracting with a customer. The information processing device according to claim 1 .
14. The actions of the assessee include sales activities, The information processing device according to claim 1 .
15. The classifier comprises a self-organizing map. The information processing device according to claim 1 .
16. an output unit that outputs a result of the evaluation by the evaluation unit; Further comprising: The information processing device according to claim 1 .
17. The processor evaluates the behavior of the person to be evaluated based on behavior performance data indicating the performance of the behavior of the person to be evaluated regarding a predetermined task; Including, The evaluation further includes performing a contribution analysis to analyze a contribution of the behavior of the assessee to the evaluation items in the predetermined task, and evaluating the behavior of the assessee based on a result of the contribution analysis; The contribution analysis includes: generating a two-dimensional map in which a plurality of objects are arranged on a plane based on attributes of a plurality of objects that are the targets of the actions of the assessee and the action performance data for the objects, which are input to a classifier generated by a machine learning algorithm; and expressing the intensities related to the evaluation items and the intensities related to the actions of the assessee in a heat map form on the two-dimensional map; The evaluation further includes evaluating whether the contribution of the behavior of the assessee to the evaluation item is due to the ability of the assessee based on the two-dimensional map. Information processing methods.
18. Computer, an evaluation unit that evaluates the behavior of the person to be evaluated based on behavior performance data indicating the behavior of the person to be evaluated regarding a predetermined task; Equipped with The evaluation unit performs a contribution analysis to analyze a contribution of the behavior of the person being evaluated to the evaluation items in the predetermined task, and evaluates the behavior of the person being evaluated based on a result of the contribution analysis; The contribution analysis includes: generating a two-dimensional map in which a plurality of objects are arranged on a plane based on attributes of a plurality of objects that are the targets of the actions of the assessee and the action performance data for the objects, which are input to a classifier generated by a machine learning algorithm; and expressing the intensities related to the evaluation items and the intensities related to the actions of the assessee in a heat map form on the two-dimensional map; The evaluation unit evaluates whether or not the contribution of the behavior of the person being evaluated to the evaluation item is due to the ability of the person being evaluated based on the two-dimensional map. Information processing device, A program to function as a
Citation Information
Patent Citations
Method, system, and computer program for rating investment fund
JP2009245368A
Schedule information analysis system and program
JP2019070913A
Agile teams freelance-sourcing: online system and method for enhancing success potential of freelance projects
US20180365628A1
