Score prediction device, score prediction method, and program

Abstract

To solve a conventional problem that a score of an organization cannot be predicted by using daily information of members of the organization.SOLUTION: A score prediction device includes: a daily information storage part for storing one or more pieces of prediction daily information being daily information being acquired by two or more respective members of an organization daily and being daily information in a period of a prediction object of a score of the organization; a score acquisition part for acquiring a prediction score being a score corresponding to the one or more pieces of prediction daily information by using a teacher score being a score of the organization acquired by using a correspondence relation between a plurality of pieces of organization answer information showing answers of questions to two or more respective members of the organization and one or more pieces of teacher daily information being daily information in a period corresponding to the answers or the questions and daily information of the two or more respective members, and the one or more pieces of prediction daily information; and a score output part for outputting a prediction score. The score prediction device can predict a score of the organization by using daily information of members of the organization.SELECTED DRAWING: Figure 13

Description

Technical Field

[0001] The present invention relates to a score prediction device for predicting an organization's score and the like.

Background Art

[0002] Conventionally, there has been a management diagnosis support device that can comprehensively judge the soundness of management (see Patent Document 1).

[0003] This management diagnosis support device totals and analyzes and displays the results of a score-based questionnaire in which answers are selected from a plurality of options for question items, and the questionnaire answer results obtained from each level constituting the organization, and for each of the plurality of question items, an analysis table to which a plurality of diagnosis elements related to corporate management are assigned, and a storage means storing an analysis table in which a score indicating weighting is set for each diagnosis element corresponding to the plurality of question items, an analysis means for analyzing the questionnaire answer results, and an output means for outputting the analysis result by the analysis means. The analysis means multiplies the answer score based on the answer result of the question item by the score for each diagnosis element set in the analysis table corresponding to the question item to calculate an individual element evaluation value for each diagnosis element of each question item, totals the individual element evaluation values of all questions for each diagnosis element to calculate an individual element total value, and the output means totals the individual element total values for each level and outputs them in the form of a graph or a table.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, conventional technologies only presented information that could be used to judge the soundness of management by aggregating and analyzing the results of questionnaires, and were not able to predict an organization's score using the daily information of its members. [Means for solving the problem]

[0006] The score prediction device of the first invention comprises: a daily information storage unit that stores one or more predicted daily information, which is daily information that can be obtained in the daily lives of two or more members of an organization and is daily information for the period over which the organization's score is to be predicted; a teacher score, which is the score of the organization obtained using a plurality of organization response information indicating the answers to questions for two or more members of the organization; a score acquisition unit that acquires a predicted score, which is the score corresponding to one or more predicted daily information, using the correspondence between the teacher daily information, which is daily information for two or more members during the period corresponding to the questions or answers, and one or more predicted daily information; and a score output unit that outputs the predicted score.

[0007] This configuration allows for the prediction of an organization's score using daily information about its members.

[0008] Furthermore, the score prediction device of this second invention, compared to the first invention, is a score prediction device in which each of the one or more teacher daily information items includes teacher work information relating to the work performed by the member, each of the one or more predictive daily information items includes predictive work information relating to the work performed by the member, and the score acquisition unit acquires a predictive score using the correspondence between the one or more teacher daily information items including teacher work information and the teacher score, and the one or more predictive daily information items including predictive work information.

[0009] This configuration allows for the prediction of an organization's score using business information related to the tasks performed by its members.

[0010] Furthermore, the score prediction device of this third invention, compared to the second invention, is a score prediction device in which teacher work information includes teacher input information entered by members, prediction work information includes prediction input information entered by members, and the score acquisition unit acquires a predicted score using the correspondence between one or more teacher daily information including teacher input information and teacher scores, and one or more prediction daily information including prediction input information.

[0011] This configuration allows for the prediction of an organization's score using input information provided by its members.

[0012] Furthermore, the score prediction device of the fourth invention, compared to the third invention, includes teacher input information which includes teacher work input information relating to inputs made by members for the performance of their own duties, and predictive input information which includes predictive work input information relating to inputs made by members for the performance of their own duties, and the score acquisition unit is a score prediction device that acquires a predicted score using the correspondence between one or more teacher daily information including teacher work input information and teacher scores, and one or more predictive daily information including predictive work input information.

[0013] With this configuration, the organization's score can be predicted using training data related to the input of each member's work performance.

[0014] Furthermore, the score prediction device of this fifth invention is a score prediction device that, compared to the second or third invention, includes teacher communication information relating to communication between two or more members as teacher input information, predictive communication information relating to communication between two or more members as predictive input information, and acquires a predictive score using the correspondence between one or more teacher daily information including teacher communication information and the teacher score, and one or more predictive daily information including predictive communication information.

[0015] This configuration allows for the prediction of an organization's score using communication information about communication among its members.

[0016] Furthermore, the score prediction device of the sixth invention is a score prediction device that, in addition to any one of the third to fifth inventions, has a score acquisition unit that acquires one or more types of information from data quantity information that identifies the amount of data in the teacher input information, input frequency information that identifies the frequency of input of the teacher input information, analysis information that shows the analysis results of the teacher input information, and timing information that identifies the timing of input of the teacher input information, and acquires one or more types of information from data quantity information of the prediction input information, input frequency information of the prediction input information, analysis information of the prediction input information, and timing information of the prediction input information, acquires correspondence relationship information that identifies the correspondence relationship between one or more teacher features including one or more types of information acquired from the teacher input information and the teacher score, and acquires a prediction score using the correspondence relationship information and one or more prediction features including one or more types of information acquired from the prediction input information.

[0017] With this configuration, it is possible to predict an organization's score using one or more types of information from among input data volume information, input frequency information, input analysis information, and input timing information.

[0018] Furthermore, the score prediction device of the seventh invention, compared to the second invention, is a score prediction device that acquires a predicted score using the correspondence between one or more teacher daily information items including teacher attendance information and teacher scores, and one or more predicted daily information items including predicted attendance information.

[0019] This configuration allows for the prediction of an organization's score using attendance information of its members.

[0020] Further, for the eighth invention, in the score prediction device, for the second invention, the teacher business information includes teacher business result information regarding the results of the constituent members' business execution, the prediction business information includes prediction business result information regarding the results of the constituent members' business execution, and the score acquisition unit is a score prediction device that acquires a prediction score using the correspondence relationship between one or more teacher daily information including the teacher business result information and the teacher score, and one or more prediction daily information including the prediction business result information.

[0021] With such a configuration, the score of the organization can be predicted using the business result information regarding the results of the organization's business execution.

[0022] Further, for the ninth invention, in the score prediction device, for the first invention, each of the one or more teacher daily information includes teacher health information regarding the health of the constituent members, each of the one or more prediction daily information includes prediction health information regarding the health of the constituent members, and the score acquisition unit is a score prediction device that acquires a prediction score using the correspondence relationship between one or more teacher daily information including the teacher health information and the teacher score, and one or more prediction daily information including the prediction health information.

[0023] With such a configuration, the score of the organization can be predicted using the health information of the constituent members of the organization.

[0024] Further, for the tenth invention, in the score prediction device, for the ninth invention, the teacher health information includes teacher biological information regarding the living body of the constituent members, the prediction health information includes prediction biological information regarding the living body of the constituent members, and the score acquisition unit is a score prediction device that acquires a prediction score using the correspondence relationship between one or more teacher daily information including the teacher biological information and the teacher score, and one or more prediction daily information including the prediction biological information.

[0025] With such a configuration, the score of the organization can be predicted using the biological information of the constituent members of the organization.

[0026] In addition, the score prediction device of the eleventh invention, for the tenth invention, the teacher biological information includes teacher stress information regarding the stress of the members, the predicted biological information includes predicted stress information regarding the stress of the members, and the score acquisition unit uses the correspondence between one or more pieces of teacher daily information including the teacher stress information and the teacher score, and one or more pieces of predicted daily information including the predicted stress information to acquire a predicted score, and is a score prediction device.

[0027] With such a configuration, the score of the organization can be predicted using the stress information of the members of the organization.

[0028] In addition, the score prediction device of the twelfth invention, for the tenth or eleventh invention, the teacher biological information includes teacher measurement information which is the measurement result of the members' bodies, the predicted biological information includes predicted measurement information obtained from the members' bodies, and the score acquisition unit uses the correspondence between one or more pieces of teacher daily information including the teacher measurement information and the teacher score, and one or more pieces of predicted daily information including the predicted measurement information to acquire a predicted score, and is a score prediction device.

[0029] With such a configuration, the score of the organization can be predicted using the measurement information which is the measurement result of the members' bodies of the organization.

[0030] In addition, the score prediction device of the thirteenth invention, for any one of the tenth to twelfth inventions, the teacher biological information includes teacher biological feature information which is an image of the members, or a feature amount of an image of the members, or the voice of the members, or a feature amount of the voice of the members, the predicted biological information includes predicted biological feature information which is an image of the members, or a feature amount of an image of the members, or the voice of the members, or a feature amount of the voice of the members, and the score acquisition unit uses the correspondence between one or more pieces of teacher daily information including the teacher biological feature information and the teacher score, and one or more pieces of predicted daily information including the predicted biological feature information to acquire a predicted score, and is a score prediction device.

[0031] With such a configuration, the score of the organization can be predicted using an image of the members of the organization or the voice of the members.

[0032] Furthermore, the score prediction device of the fourteenth invention is a score prediction device that, in addition to any one of the nineth to thirteenth inventions, includes teacher health information, teacher lifestyle information relating to the lives of members, and predictive health information, predictive lifestyle information relating to the lives of members, and the score acquisition unit acquires a predictive score using the correspondence between one or more teacher daily information including teacher lifestyle information and the teacher score, and one or more predictive daily information including predictive lifestyle information.

[0033] This configuration allows for the prediction of an organization's score using information about the lifestyles of its members.

[0034] Furthermore, the score prediction device of the fifteenth invention is a score prediction device that, in addition to any one of the first to fourteenth inventions, comprises a score acquisition unit which includes a correspondence acquisition means for acquiring correspondence relationship information that identifies the correspondence relationship between one or more teacher daily information items and a teacher score, and a score acquisition means for acquiring a predicted score using the correspondence relationship information and one or more predicted daily information items.

[0035] This configuration allows for the prediction of an organization's score using daily information about its members.

[0036] Furthermore, the score prediction device of the sixteenth invention, compared to the fifteenth invention, has one or more teacher daily information and teacher scores associated with one or more organizational attribute values, the correspondence acquisition means acquires correspondence relationship information that identifies the correspondence between one or more teacher daily information and teacher scores for each organizational condition configured using one or more organizational attribute values, and the score acquisition means acquires a predicted score using the correspondence relationship information corresponding to the organizational condition to which the organization to be predicted matches and one or more predicted daily information.

[0037] This configuration allows for obtaining predictive scores that match the organization's attribute values.

[0038] Furthermore, the score prediction device of the seventeenth invention is a score prediction device that, compared to the fifteenth or sixteenth invention, has a correspondence acquisition means that uses one or more teacher daily information and a teacher score to perform a learning process using a machine learning algorithm to acquire correspondence relationship information, which is a learning model with one or more teacher daily information as explanatory variables and the teacher score as the objective variable, and a score acquisition means that uses the learning model and one or more predicted daily information to perform a prediction process using a machine learning algorithm to acquire a predicted score.

[0039] With this configuration, machine learning techniques can be used to predict an organization's score using daily information about its members.

[0040] Furthermore, the score prediction device of the eighteenth invention is a score prediction device that, compared to the fifteenth or sixteenth invention, has a correspondence acquisition means that acquires a teacher vector, which is a vector having two or more elements, using one or more teacher daily information, and acquires correspondence relationship information, which is a correspondence table having one or more correspondence information pairs of teacher vectors and teacher scores, and a score acquisition means that acquires a prediction vector, which is a vector having two or more elements, using one or more prediction daily information, applies the prediction vector to the correspondence table, and acquires a prediction score.

[0041] With this configuration, data mining techniques can be used to predict an organization's score using daily information about its members.

[0042] Furthermore, the score prediction device of the nineteenth invention is a score prediction device that, compared to the fifteenth or sixteenth invention, has a correspondence acquisition means that acquires a teacher vector, which is a vector having two or more elements, using one or more teacher daily information, and acquires correspondence relationship information, which is a calculation formula that takes each element of the teacher vector as input and outputs a teacher score, and a score acquisition means that acquires a prediction vector, which is a vector having two or more elements, using one or more prediction daily information, provides each element of the prediction vector to a calculation formula, executes the calculation formula and acquires a prediction score.

[0043] With this configuration, data analysis techniques can be used to predict an organization's score using daily information about its members. [Effects of the Invention]

[0044] According to the score prediction device of the present invention, an organization's score can be predicted using daily information of its members. [Brief explanation of the drawing]

[0045] [Figure 1] Conceptual diagram of information system A in Embodiment 1 [Figure 2] Block diagram of information system A [Figure 3] A flowchart illustrating an example of the operation of the information processing device 1. [Figure 4] A flowchart illustrating an example of the score calculation process. [Figure 5] An example of the process for calculating the impact is explained, along with a flowchart. [Figure 6] Diagram showing the information management table for the same item. [Figure 7] A diagram showing the organization's response information. [Figure 8] Figure showing the individual score table. [Figure 9] Figure showing an example of the same output. [Figure 10] Figure showing an example of the same output. [Figure 11] Conceptual diagram of information system B in Embodiment 2 [Figure 12] Block diagram of the same information system B [Figure 13] Block diagram of the score prediction device 3 [Figure 14] Flowchart illustrating an example of the operation of the score prediction device 3. [Figure 15] A flowchart illustrating an example of the corresponding data acquisition process. [Figure 16] This flowchart explains an example of the process for obtaining same-applicability groups. [Figure 17] A flowchart illustrating an example of data entry processing for the same business operations. [Figure 18] A flowchart illustrating an example of communication information processing. [Figure 19] A flowchart illustrating an example of processing attendance status information. [Figure 20] A flowchart illustrating an example of stress information processing. [Figure 21] A flowchart illustrating an example of the measurement information processing. [Figure 22] A flowchart illustrating an example of the same image information processing. [Figure 23] A flowchart illustrating an example of this voice information processing. [Figure 24] A flowchart illustrating an example of cohabitation information processing. [Figure 25] A flowchart illustrating an example of the score acquisition process. [Figure 26] A flowchart illustrating an example of operation for terminal device 4. [Figure 27] Overview of the computer system in the above embodiment [Figure 28] Block diagram of the computer system [Modes for carrying out the invention]

[0046] The following describes embodiments of the score prediction device and the like with reference to the drawings. Note that components denoted by the same reference numerals in these embodiments perform similar operations, and therefore, further explanation may be omitted.

[0047] (Embodiment 1) In this embodiment, we will describe an information system that includes an information processing device that acquires and outputs the degree of influence of each item on an organization's overall score calculated from responses to two or more items. Note that "organization" is broadly interpreted and can refer to, for example, a so-called company, a sole proprietorship, a local government, etc. An organization is, for example, an organization that performs some kind of work. Furthermore, the organization's overall score may also be called an engagement score. The information system may also be called an engagement system. Furthermore, the information processing device may also be called an engagement device.

[0048] Furthermore, in this embodiment, we will describe an information system that includes an information processing device that calculates item scores and an overall organizational score using the expected value of each item. This information system may also be referred to as an engagement system.

[0049] Furthermore, in this embodiment, we will describe an information system that includes an information processing device having a score adjustment function that adjusts the overall score using correlation information regarding the correlation between satisfaction and expectations.

[0050] Furthermore, in this embodiment, we will describe an information system that includes an information processing device that takes into account the attribute values ​​of an organization and outputs different degrees of influence for each attribute value.

[0051] Figure 1 is a conceptual diagram of information system A in this embodiment. Information system A comprises an information processing device 1 and one or more terminal devices 2. The information processing device 1 is, in this case, a so-called server device. The information processing device 1 may be, for example, a cloud server or an ASP server, but its type and installation location are not specified. The terminal devices 2 may be mobile terminals such as smartphones, tablet terminals or mobile phones, or so-called personal computers, and their type is not specified.

[0052] Figure 2 is a block diagram of information system A in this embodiment.

[0053] The information processing device 1 comprises a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 comprises an item information storage unit 111, an organization response information storage unit 112, and an individual score table storage unit 113. The processing unit 13 comprises an item score acquisition unit 131, an overall score acquisition unit 132, and an influence acquisition unit 133. The output unit 14 comprises an item score output unit 141, an overall score output unit 142, and an influence output unit 143.

[0054] The terminal device 2 includes a terminal storage unit 21, a terminal receiving unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal receiving unit 25, and a terminal output unit 26.

[0055] The storage unit 11, which constitutes the information processing device 1, stores various types of information. These types of information include, for example, item information (described later), organizational response information (described later), and individual score tables (described later). The individual score tables may also be called engagement score tables, etc.

[0056] The item information storage unit 111 stores two or more item information items. The item information is information about items of the organization. An item may be a question about the organization. An item may also correspond to a question about the organization. Two or more items include, for example, a general item concerning general matters of the organization and an individual item which is a specific item of the organization. General items are usually items for questions with a high level of abstraction. Individual items are usually items for questions with a lower level of abstraction (more specific questions). The two or more item information items in the item information storage unit 111 may include, for example, item information for four general items and item information for 64 individual items. An item may also correspond to one of two or more targets. A target may also be called a factor. A target may also be called a matter related to the organization. The item information may include, for example, an item identifier that identifies the item and question information. The item identifier may be, for example, an ID or item name. The item identifier may also be the question information itself. The question information is information that indicates a question. Note that "questions" usually refer to survey questions. "Items" can also be referred to as "subjects" or "items."

[0057] The organizational response information storage unit 112 stores organizational response information for two or more organizations. One piece of organizational response information is a set of response information from two or more members of one organization. One piece of organizational response information has two or more pieces of member response information corresponding to two or more members. Member response information is information that includes the results of members answering questions about items. Member response information has two or more pieces of item response information. Member response information usually has as many pieces of item response information as there are items. Item response information has an item identifier and response information. Response information is information about the answer to the question. Response information may include, for example, satisfaction information. Satisfaction information is information that indicates the degree of satisfaction of a member with respect to an item. Satisfaction information may include, for example, information that identifies the level of satisfaction with an item. Satisfaction information is classified into two or more classes. Satisfaction information may take the form of any natural number from 1 to 5. However, satisfaction information may also be an evaluation value with rank or order, such as A, B, C, or any natural number from 1 to 100. Furthermore, the response information includes, for example, satisfaction information and expectation information. Expectation information indicates the degree of expectation of the members regarding the item. Expectation information identifies the degree of expectation for an item. Expectation information is classified into two or more classes. Expectation information can take the form of any natural number from 1 to 5. However, expectation information may also be an evaluation value with rank or order, such as A, B, C, or any natural number from 1 to 100. Note that members include, for example, company employees, school staff, government officials, etc., but may also include company executives, etc.

[0058] The overall items include, for example, company satisfaction (indicating the degree of satisfaction with the company), job satisfaction (indicating the degree of satisfaction with the work), supervisor satisfaction (indicating the degree of satisfaction with the supervisor), and workplace satisfaction (indicating the degree of satisfaction with the workplace). The individual items include, for example, the company's competitive advantage, the communication and dissemination of strategic goals, overall sense of solidarity, and the fairness of evaluations and salaries.

[0059] Furthermore, organizational response information is usually associated with an organizational identifier. The organizational identifier is the organization name, an ID that identifies the organization, etc. It is also preferable that the organizational response information is associated with one or more attribute values ​​of the organization. Attribute values ​​include, for example, an industry identifier indicating the organization's industry (e.g., bank, apparel, manufacturer, etc.), a size identifier classifying the organization's size (e.g., large company, small and medium-sized enterprise, sole proprietorship, etc.), and a regional identifier indicating the location of the headquarters, etc.

[0060] The individual score table storage unit 113 stores the individual score table. Here, the individual score table is information in which item scores are determined when satisfaction information and expectation information are provided. Here, the individual score table is, for example, a table having an axis for satisfaction information and an axis for expectation information, in which an individual score is written in each cell of the table, and the item score is determined when the satisfaction information and expectation information are determined. It is preferable that such an individual score table is one in which a larger item score is obtained the greater the satisfaction indicated by the satisfaction information, and a larger item score is obtained the smaller the expectation indicated by the expectation information.

[0061] Furthermore, when determining item scores, they may be determined by a calculation formula that uses satisfaction information and expectation information as parameters. Preferably, such a formula is an increasing function with satisfaction information as a parameter and a decreasing function with expectation information as a parameter.

[0062] Furthermore, when determining item scores, multiple sets of satisfaction information, expectation information, and item scores may be trained using machine learning, and the acquired trained information may be used. In such cases, the satisfaction information, expectation information, and trained information are applied, and item scores are obtained using machine learning. For example, SVR, deep learning, and decision trees can be used for machine learning. However, the machine learning algorithm is not specified.

[0063] The reception unit 12 receives various types of information and instructions. These types of information and instructions include, for example, instructions to output scores, organizational response information, and questionnaire response information (member response information). Instructions to output scores are instructions to output scores. In this context, "reception" usually refers to reception from the terminal device 2, but it can also be understood as a concept that includes receiving information input from input devices such as keyboards, mice, and touch panels, and receiving information read from recording media such as optical discs, magnetic discs, and semiconductor memory.

[0064] The processing unit 13 performs various processes. These various processes include, for example, the processes performed by the item score acquisition unit 131, the overall score acquisition unit 132, and the influence acquisition unit 133. These various processes include, for example, the process of storing received organizational response information, questionnaire response information, etc., in the storage unit 11.

[0065] The item score acquisition unit 131 statistically processes the response information for members of each of the two or more items included in the response information of each of the two or more organizations, and acquires item scores for each organization and each item.

[0066] The item score acquisition unit 131 statistically processes the satisfaction information contained in the response information for two or more items included in the organizational response information of each organization, for each organization, and acquires item scores for each organization and each item. The item score acquisition unit 131 may, for example, calculate the average value of the satisfaction information for each organization and each item, and store this average value as an item score, paired with the item identifier, in a buffer or storage unit 11 (not shown). Alternatively, the item score acquisition unit 131 may, for example, calculate a weighted average of the satisfaction information for each organization and each item, assigning different weights according to the attribute values ​​of the members, and store this weighted average as an item score, paired with the item identifier, in a buffer or storage unit 11 (not shown). The attribute values ​​of the members are, for example, job title, length of service, gender, etc. For example, the item score acquisition unit 131 may compare the satisfaction information of employees with long years of service with the satisfaction information of employees with short years of service, give them a heavier weight, and calculate a weighted average.

[0067] The item score acquisition unit 131 acquires item scores for each organization using satisfaction information and expectation information for at least some items. The items for which item scores are acquired using satisfaction information and expectation information are, for example, individual items.

[0068] The item score acquisition unit 131 preferably acquires item scores such that, for example, a high satisfaction level results in a high score, and a low expectation level results in a high score.

[0069] The item score acquisition unit 131 calculates, for example, the average value of satisfaction information and the average value of expectation information contained in the response information for each of the two or more items for each of the two or more organizations, and uses the two average values ​​to acquire an item score for each item.

[0070] The item score acquisition unit 131 may, for example, apply satisfaction information and expectation information to the individual score table and acquire an item score for each item. Alternatively, the item score acquisition unit 131 may, for example, apply the statistical processing results of satisfaction information and the statistical processing results of expectation information to the individual score table and acquire an item score for each item. The item score acquisition unit 131 may, for example, apply the average value of satisfaction information and the average value of expectation information to the individual score table and acquire an item score for each item. The item score acquisition unit 131 may, for example, apply the weighted average value of satisfaction information and the weighted average value of expectation information to the individual score table and acquire an item score for each item. Note that the weighted average value is a weighted average value based on the attribute values ​​of the members.

[0071] The item score acquisition unit 131 may calculate the item score for each item using, for example, an increasing function with the average value of satisfaction information as a parameter, or a decreasing function with the average value of expectation information as a parameter.

[0072] The overall score acquisition unit 132 acquires an overall score for each of the two or more organization response information using two or more item scores. The overall score is a comprehensive score for each organization. Generally, the overall score acquisition unit 132 acquires a higher overall score the better the scores of the two or more individual item scores are.

[0073] The overall score acquisition unit 132 preferably acquires the overall score using a score adjustment function as follows. The score adjustment function is a function that adjusts the score using correlation information regarding the degree of correlation between satisfaction information and expectation information. In this case, it is preferable that the score adjustment function is configured so that a higher correlation between satisfaction information and expectation information results in a higher overall score.

[0074] The overall score acquisition unit 132, for example, acquires a provisional overall score for each organization using two or more item scores, acquires correlation information regarding the degree of correlation between satisfaction information and expectation information for two or more items, and uses this correlation information to acquire an overall score from the provisional overall score such that the score increases as the degree of correlation increases. The correlation information may be the correlation value between the set of satisfaction information for two or more items and the set of expectation information, or it may be a value calculated by an increasing function whose parameter is the number of items where the difference between the satisfaction information for two or more items and the expectation information for two or more items is less than or equal to a threshold, or it may be a value calculated by an decreasing function whose parameter is the number of items where the difference between the satisfaction information for two or more items and the expectation information for two or more items is less than or equal to a threshold and the satisfaction information is smaller. In other words, the algorithm for acquiring the correlation information is not specified.

[0075] It is preferable for the overall score acquisition unit 132 to acquire an overall score by using both the item score for the overall item and the item score for the individual item, and by comparing the item score for the overall item with the item score for the individual item and giving it a greater weight.

[0076] The overall score acquisition unit 132 may calculate the overall score using, for example, the formula: "Overall score = α × statistical score of item scores for the overall item + β × statistical score of item scores for individual items". Here, it is preferable that (α > β). In other words, it is preferable for the overall score acquisition unit 132 to compare the item scores for the overall item with the item scores for individual items, give them a larger weight, and acquire the overall score. For example, "α = 0.7, β = 0.3". The statistical score of item scores for the overall item is, for example, the average value or weighted average of the item scores for the overall item. The statistical score of item scores for individual items is, for example, the average value or weighted average of the item scores for individual items.

[0077] Furthermore, the overall score acquisition unit 132 may calculate a provisional overall score using, for example, "provisional overall score = α × statistical score of item scores for the overall item + β × statistical score of item scores for individual items," and then perform score adjustments using the score adjustment function described above to calculate the overall score. In addition, the overall score acquisition unit 132 may, for example, use the overall scores of multiple organizations to calculate the standard score of the overall score of each organization, and use this standard score as the final overall score.

[0078] The impact acquisition unit 133 acquires the degree of influence that each item score has on the overall score. The degree of influence that each item score has on the overall score can also be described as the degree of influence that each item has on the overall score.

[0079] The impact acquisition unit 133 uses the item scores for two or more items from two or more organizations, and the overall scores from two or more organizations, to acquire the degree of influence that each item's score has on the overall score, item by item. The impact is, for example, information indicating the influence that an item's score has on the overall score, and is the correlation between a set of item scores from multiple organizations and a set of overall scores from those multiple organizations. Note that the process for acquiring correlation, correlation value, and correlation information is publicly known, so a detailed explanation is omitted.

[0080] The impact acquisition unit 133 uses the overall score of two or more organizations and the item scores of each item for two or more organizations to calculate the impact for each item, which is information regarding the correlation between the item score and the overall score for each item.

[0081] The impact acquisition unit 133 preferably acquires the degree of influence that each item's item score has on the overall score for each attribute value of the organization. In other words, if the organization's attribute value is an industry identifier, the impact acquisition unit 133 preferably acquires the degree of influence for each item for each industry corresponding to the industry identifier.

[0082] The output unit 14 outputs various types of information. These various types of information include, for example, a set of pairs of information such as item identifiers and item scores. Other types of information include, for example, a total score. Other types of information include, for example, a set of pairs of information such as item identifiers and impact levels. Here, output usually refers to transmission to an external device such as terminal device 2. However, output can also be considered a concept that includes display on a screen, projection using a projector, printing with a printer, sound output, storage on a recording medium, and delivery of processing results to other processing devices or other programs.

[0083] The item score output unit 141 outputs one or more item scores. The item score output unit 141 usually outputs the item score of the item identified by the item identifier, associating it with the item identifier. For example, the item score output unit 141 outputs the item score that is paired with the organization identifier that has been included in the score output instruction, associating it with the item identifier. It is preferable for the item score output unit 141 to output one or more item scores as associated with the organization identifier. It is also preferable for the item score output unit 141 to output the item scores in a manner that makes it visually possible to distinguish between the item score of the overall item and the item score of the individual item.

[0084] The overall score output unit 142 outputs the overall score. It is preferable for the overall score output unit 142 to output the overall score in association with an organization identifier.

[0085] The impact output unit 143 outputs the impact acquired by the impact acquisition unit 133, associating it with each item. It is preferable for the impact output unit 143 to output the impact acquired by the impact acquisition unit 133, associating it with the item identifier of each item.

[0086] Furthermore, it is preferable for the impact output unit 143 to output the impact level in association with each item so that the classification of impact levels can be visually distinguished.

[0087] The terminal storage unit 21, which constitutes the terminal device 2, stores various types of information. These various types of information include, for example, an organization identifier that identifies the user's organization. These various types of information include, for example, information received by the terminal receiving unit 25. The organization identifier can also be considered as information that identifies the user.

[0088] The terminal reception unit 22 receives various instructions and information. Here, "reception" is a concept that includes receiving information entered from input devices such as keyboards, mice, and touch panels, receiving information transmitted via wired or wireless communication lines, and receiving information read from recording media such as optical discs, magnetic discs, and semiconductor memory. Various instructions and information include, for example, instructions for outputting scores, organizational response information, and questionnaire response information.

[0089] The input methods for various instructions and information can be anything, such as a touch panel, keyboard, mouse, or menu screen. The terminal reception unit 22 can be implemented using device drivers for input methods such as touch panels and keyboards, or control software for menu screens.

[0090] The terminal processing unit 23 performs various processes, such as structuring the information received by the terminal receiving unit 25 into data to be displayed. Other various processes include structuring instructions received by the terminal reception unit 22 into instructions to be transmitted.

[0091] The terminal transmission unit 24 transmits various instructions and information to the information processing device 1. These instructions and information include, for example, instructions configured by the terminal processing unit 23 and instructions and information received by the terminal reception unit 22.

[0092] The terminal receiving unit 25 receives various types of information from the information processing device 1. These types of information include, for example, item scores, overall scores, and impact scores.

[0093] The terminal output unit 26 acquires various types of information. These types of information include, for example, information received by the terminal reception unit 22, information received by the terminal receiving unit 25, and information generated by the terminal processing unit 23. These types of information include, for example, item scores, overall scores, and impact scores.

[0094] The storage unit 11 is preferably made of a non-volatile recording medium, but it can also be made of a volatile recording medium.

[0095] The process by which information is stored in the storage unit 11, item information storage unit 111, organizational response information storage unit 112, individual score table storage unit 113, and terminal storage unit 21 is not relevant. For example, information may be stored in the storage unit 11 etc. via a recording medium, information transmitted via a communication line etc. may be stored in the storage unit 11 etc., or information entered via an input device may be stored in the storage unit 11 etc.

[0096] The reception unit 12 and the terminal receiving unit 25 are usually implemented by wireless or wired communication means, but they may also be implemented by means of receiving broadcasts.

[0097] The processing unit 13, item score acquisition unit 131, overall score acquisition unit 132, influence acquisition unit 133, and terminal processing unit 23 can typically be implemented using an MPU or memory. The processing procedures of the processing unit 13, etc., are typically implemented in software, and this software is recorded on a recording medium such as ROM. However, it may also be implemented in hardware (dedicated circuitry).

[0098] The output unit 14, item score output unit 141, overall score output unit 142, influence output unit 143, and terminal transmission unit 24 are usually implemented by wireless or wired communication means, but may also be implemented by broadcasting means.

[0099] The terminal output unit 26 may or may not be considered to include output devices such as a display or speakers. The terminal output unit 26 can be implemented using driver software for an output device, or driver software for an output device and an output device.

[0100] Next, we will explain the operation of information system A. First, we will explain an example of the operation of information processing device 1 using the flowchart in Figure 3. It should be assumed that the organizational response information storage unit 112 stores organizational response information from multiple organizations. Also, it should be assumed that the individual score table storage unit 113 stores individual score tables.

[0101] (Step S301) The processing unit 13 determines whether or not it is time to calculate the score, etc. If it is time to calculate the score, etc., the process proceeds to step S302; otherwise, it proceeds to step S312. The timing for calculating the score, etc. is, for example, when instructions are input from a user or administrator, when a predetermined timing is reached, or when two or more organizational response information items are received and stored in the organizational response information storage unit 112.

[0102] (Step S302) The processing unit 13 assigns 1 to counter i.

[0103] (Step S303) The processing unit 13 determines whether the i-th attribute value exists. If the i-th attribute value exists, the process proceeds to step S304; otherwise, the process returns to step S301. The i-th attribute value is the i-th attribute value of the organization, and is the attribute value for which the influence is calculated.

[0104] (Step S304) The processing unit 13 obtains two or more pieces of organizational response information, etc., that are paired with the i-th attribute value from the organizational response information storage unit 112. Organizational response information, etc., is, for example, an organizational identifier and organizational response information. Organizational response information, etc., is, for example, an organizational identifier, the i-th attribute value and organizational response information.

[0105] (Step S305) The processing unit 13 assigns 1 to counter j.

[0106] (Step S306) The processing unit 13 determines whether the j-th organization identifier exists among the two or more organization response information obtained in step S304. If the j-th organization identifier exists, the process proceeds to step S307; otherwise, the process proceeds to step S310.

[0107] (Step S307) The processing unit 13 obtains the organization response information that is paired with the j-th organization identifier.

[0108] (Step S308) The processing unit 13 uses the organizational response information obtained in step S307 to calculate various scores corresponding to the j-th organizational identifier. Note that the calculation of a score is synonymous with obtaining a score. The score calculation process will be explained using the flowchart in Figure 4.

[0109] (Step S309) The processing unit 13 increments counter j by 1. The process returns to step S306.

[0110] (Step S310) The impact acquisition unit 133 calculates the impact of each item. This impact calculation process will be explained using the flowchart in Figure 5.

[0111] (Step S311) The processing unit 13 increments counter i by 1. The process returns to step S303.

[0112] (Step S312) The reception unit 12 determines whether or not it has received a score output instruction. If it has received a score output instruction, it proceeds to step S313; otherwise, it returns to step S301.

[0113] (Step S313) The processing unit 13 obtains the organization identifier contained in the score output instruction received in step S312.

[0114] (Step S314) The processing unit 13 obtains the attribute value of the organization that corresponds to the organization identifier obtained in step S313.

[0115] (Step S315) The processing unit 13 retrieves two or more item scores that are paired with the organization identifier obtained in step S313, and item identifiers that are paired with the item scores, from the storage unit 11 or a buffer (not shown). In other words, the processing unit 13 retrieves as many pairs of item identifiers and item scores as there are items.

[0116] (Step S316) The processing unit 13 obtains a total score from the storage unit 11 or a buffer (not shown) that corresponds to the organization identifier obtained in step S313.

[0117] (Step S317) The processing unit 13 obtains two or more influence levels that are paired with the attribute value obtained in step S314, and item identifiers that are paired with the influence levels, from the storage unit 11 or a buffer (not shown). In other words, the processing unit 13 obtains as many pairs of item identifiers and influence levels as there are items.

[0118] (Step S318) The processing unit 13 constructs the output information from the information acquired in steps S315, S316, and S317.

[0119] (Step S319) The output unit 14 outputs the information configured in step S318. The process returns to step S301. Note that the output here usually refers to transmission to the terminal device 2 that sent the score output instruction. The output information should include at least a pair of item identifier and impact level. It is also preferable that the output information includes a pair of item identifier and item score, and a total score.

[0120] Note that in the flowchart of Figure 3, the route for accumulating organizational response information to the organizational response information storage unit 112 is not specified.

[0121] Furthermore, in the flowchart in Figure 3, the degree of influence was obtained for each organizational attribute value. However, it goes without saying that the degree of influence for each item could also be obtained using organizational response information from all organizations, regardless of the organizational attribute values.

[0122] Furthermore, as shown in the flowchart in Figure 3, processing is terminated by power-off or processing termination interrupts.

[0123] Next, an example of the score calculation process in step S308 will be explained using the flowchart in Figure 4.

[0124] (Step S401) The item score acquisition unit 131 assigns 1 to counter i.

[0125] (Step S402) The item score acquisition unit 131 determines whether or not the item identifier for the i-th individual item exists in the organizational response information acquired in step S307. If the item identifier for the i-th individual item exists, the unit proceeds to step S403; otherwise, the unit proceeds to step S409.

[0126] (Step S403) The item score acquisition unit 131 acquires satisfaction information for all members that is paired with the item identifier of the i-th individual item in the organizational response information acquired in step S307.

[0127] (Step S404) The item score acquisition unit 131 statistically processes the satisfaction information acquired in step S403 and calculates statistical satisfaction information. Here, the item score acquisition unit 131 calculates statistical satisfaction information, which is, for example, the average value of the satisfaction information acquired in step S403. The item score acquisition unit 131 then stores the calculated statistical satisfaction information in the storage unit 11 or a buffer (not shown) in pairs with the item identifier of the i-th individual item.

[0128] (Step S405) The item score acquisition unit 131 acquires expectation information for all members that is paired with the item identifier of the i-th individual item in the organizational response information acquired in step S307.

[0129] (Step S406) The item score acquisition unit 131 statistically processes the expectation information acquired in step S405 and calculates statistical expectation information. Here, the item score acquisition unit 131 calculates statistical expectation information, which is, for example, the average value of the expectation information acquired in step S403. The item score acquisition unit 131 then stores the calculated statistical expectation information in the storage unit 11 or a buffer (not shown) in pairs with the item identifier of the i-th individual item.

[0130] (Step S407) The item score acquisition unit 131 uses the statistical satisfaction information and statistical expectation information to acquire the item score of the i-th individual item of the organization under consideration. The item score acquisition unit 131 applies the statistical satisfaction information and statistical expectation information to the individual score table in the individual score table storage unit 113 to acquire the item score of the i-th individual item. The item score acquisition unit 131 then stores the acquired item score in the storage unit 11 or a buffer (not shown) in pairs with the item identifier of the i-th individual item.

[0131] (Step S408) The item score acquisition unit 131 increments counter i by 1. Return to step S402.

[0132] (Step S409) The item score acquisition unit 131 assigns 1 to counter j.

[0133] (Step S410) The item score acquisition unit 131 determines whether or not the item identifier for the j-th comprehensive item exists in the organizational response information acquired in step S307. If the item identifier for the j-th comprehensive item exists, the unit proceeds to step S411; otherwise, the unit proceeds to step S414.

[0134] (Step S411) The item score acquisition unit 131 acquires satisfaction information for all members that is paired with the item identifier of the j-th overall item in the organizational response information acquired in step S307.

[0135] (Step S412) The item score acquisition unit 131 statistically processes the satisfaction information acquired in step S411 and calculates statistical satisfaction information. Here, the item score acquisition unit 131 calculates statistical satisfaction information, which is, for example, the average value of the satisfaction information acquired in step S411. The item score acquisition unit 131 then stores the calculated statistical satisfaction information in the storage unit 11 or a buffer (not shown) in pairs with the item identifier of the j-th overall item.

[0136] (Step S413) The item score acquisition unit 131 increments counter j by 1. Return to step S410.

[0137] (Step S414) The overall score acquisition unit 132 acquires all item scores for individual items from the storage unit 11 or a buffer (not shown). The item scores for individual items are the scores acquired in step S407.

[0138] (Step S415) The overall score acquisition unit 132 acquires the overall score for each individual item from all the item scores acquired in step S414. For example, the overall score acquisition unit 132 calculates the average value of all the item scores acquired in step S414 and acquires this average value as the overall score for each individual item.

[0139] (Step S416) The overall score acquisition unit 132 acquires statistical satisfaction information for all items of the overall items from the storage unit 11 or a buffer (not shown).

[0140] (Step S417) The overall score acquisition unit 132 statistically processes the statistical satisfaction information for all items acquired in step S416 and calculates the overall statistical satisfaction information for the items. For example, the overall score acquisition unit 132 calculates the average value of the statistical satisfaction information for all items acquired in step S416 and acquires it as the overall statistical satisfaction information for the items.

[0141] (Step S418) The overall score acquisition unit 132 calculates a provisional overall score from the overall scores of the individual items acquired in step S415 and the statistical satisfaction information of the overall items acquired in step S417. The overall score acquisition unit 132 calculates the provisional overall score using, for example, the formula "Provisional overall score = α × statistical satisfaction information of the overall items + β × overall score of the individual items".

[0142] (Step S419) The overall score acquisition unit 132 acquires correlation information regarding the correlation between the set of satisfaction information and the set of expectation information from the set of satisfaction information for all individual items and the set of expectation information for all individual items.

[0143] (Step S420) The overall score acquisition unit 132 uses the correlation information acquired in step S419 to adjust the provisional overall score acquired in step S418 and acquires the overall score. It then returns to the higher-level processing. The overall score acquisition unit 132 acquires the overall score such that the greater the degree of correlation indicated by the correlation information, the higher the overall score.

[0144] Next, an example of the impact calculation process in step S310 will be explained using the flowchart in Figure 5.

[0145] (Step S501) The influence acquisition unit 133 assigns 1 to counter i.

[0146] (Step S502) The impact acquisition unit 133 determines whether the item identifier for the i-th individual item exists among the two or more organizational response information obtained in step S304. If the item identifier for the i-th individual item exists, the process proceeds to step S503; otherwise, the process returns to the higher level.

[0147] (Step S503) The impact acquisition unit 133 acquires the item scores of multiple organizations that are paired with the item identifier of the i-th individual item from among the two or more organizational response information obtained in step S304.

[0148] (Step S504) The impact acquisition unit 133 acquires the overall score of multiple organizations from among the two or more organizational response information obtained in Step S304.

[0149] (Step S505) The influence acquisition unit 133 acquires an influence score that indicates the degree of correlation between the multiple item scores acquired in step S503 and the multiple overall scores acquired in step S504. The influence acquisition unit 133 then stores the acquired influence score in the storage unit 11 or a buffer (not shown) in conjunction with the item identifier of the i-th individual item.

[0150] (Step S506) The influence acquisition unit 133 increments the counter i to 1. The process returns to step S502.

[0151] Next, the operation of terminal device 2 will be described. The terminal receiving unit 22 of terminal device 2 receives various instructions and information. Next, the terminal processing unit 23 configures the instructions received by the terminal receiving unit 22 into instructions to be transmitted. The terminal transmitting unit 24 transmits the instructions configured by the terminal processing unit 23 to the information processing device 1. Then, the terminal receiving unit 25 receives information from the information processing device 1 in response to the transmission of instructions. Next, the terminal processing unit 23 configures the information received by the terminal receiving unit 25 into output data. Next, the terminal output unit 26 outputs the information configured by the terminal processing unit 23.

[0152] The specific operation of information system A in this embodiment will be described below. A conceptual diagram of information system A is shown in Figure 1.

[0153] Let's assume that the item information storage unit 111 now stores the item information management table shown in Figure 6. The item information management table is a table that manages a large amount of item information that shows the items of a questionnaire for members (in this case, employees) of an organization (in this case, a company). The item information here includes "Question No.", "Type", "Factor", "Item", "Question: Expectation", and "Question: Satisfaction". "Question No." is an ID that identifies the question and is an example of an item identifier. "Type" is information that shows the type of item and can be either a general item or an individual item. "Factor" is a middle concept of the item and can also be called the target. "Item" is information that shows the content of the item. It can also be thought of as an item identifier. "Question: Expectation" is a question to obtain expectation information. "Question: Satisfaction" is a question to obtain satisfaction information.

[0154] Furthermore, the organizational response information storage unit 112 stores organizational response information, for example, as shown in Figure 7. The organizational response information storage unit 112 stores two or more pieces of organizational response information. Figure 7 is the organizational response information of an organization identified by the organizational identifier "Company A". Also, 701 is the member response information of one employee of the organization identified by the organizational identifier "Company A". The organizational response information of an organization identified by the organizational identifier "Company A" includes member response information of two or more employees. The member response information has a large number (63 or more) of records that have "item identifier", "expectation level information", and "satisfaction level information". Note that records for items with item identifiers 1 to 4 are records for general items and do not have expectation level information. The expectation level information and satisfaction level information that constitute the member response information of 701 are information obtained from the answers given by the employee to "Question: Expectation Level" and "Question: Satisfaction Level" in the item information management table shown in Figure 6. In this case, such answers are natural numbers from 1 to 5. Furthermore, in this case, a value of 1 for the expectation level in "Question: Expectation Level" indicates the lowest expectation level, while a value of 5 indicates the highest expectation level. Similarly, a value of 1 for the satisfaction level in "Question: Satisfaction Level" indicates the lowest satisfaction level, while a value of 5 indicates the highest satisfaction level. Additionally, the attribute value for the industry of the organization identified by the organization identifier "Company A" is assumed to be "Manufacturer".

[0155] Furthermore, the individual score table storage unit 113 stores the individual score table shown in Figure 8. The individual score table manages two or more records that have "expectation information," "satisfaction information," and "score." "Expectation information" is, for example, the average value of expectation information. "Expectation information" may also be, for example, information indicating the range of the average value of expectation information. The attribute values ​​of "expectation information," such as "expectation value 1," "expectation value 2," ... "expectation value N," are specific values ​​or range information. Also, "satisfaction information" is, for example, the average value of satisfaction information. "Satisfaction information" may also be, for example, information indicating the range of the average value of satisfaction information. The attribute values ​​of "satisfaction information," such as "satisfaction value 1," "satisfaction value 2," ... "satisfaction value N," are specific values ​​or range information. "Score" here refers to information indicating the item score. The attribute values ​​of "score," such as "score 1," "score 2," ... "score N," are specific values.

[0156] In this situation, the administrator of the information processing device 1 inputs an instruction to calculate the score, etc. The receiving unit 12 then receives the instruction to calculate the score, etc. Next, the processing unit 13 determines that it is time to calculate the score, etc.

[0157] Next, the processing unit 13 retrieves two or more organizational response information items that correspond to the attribute value "manufacturer" from the organizational response information management table (Figure 7).

[0158] Next, the processing unit 13 calculates the item score for each item and the overall score for each organizational identifier, starting with "Company A," using the organizational response information that is paired with the organizational identifier. The calculation of the item score and the overall score will be explained below using "Company A" as an example.

[0159] In other words, the item score acquisition unit 131 acquires member response information paired with the organization identifier "Company A". Then, from the acquired member response information, the item score acquisition unit 131 acquires satisfaction information for all members for each individual item. Next, the item score acquisition unit 131 acquires the average value of the acquired satisfaction information as statistical satisfaction information for each individual item. The item score acquisition unit 131 also acquires the average value of the acquired expectation information as statistical expectation information for each individual item. Next, the item score acquisition unit 131 applies the statistical satisfaction information and statistical expectation information to the individual score table in Figure 8 and acquires the item score for each individual item. Then, the item score acquisition unit 131 stores the acquired item scores in a buffer paired with the item identifier for each individual item.

[0160] Next, the item score acquisition unit 131 acquires satisfaction information for all members corresponding to the item identifier of each overall item. Then, the item score acquisition unit 131 calculates the average value of the acquired satisfaction information for each overall item and acquires this average value as statistical satisfaction information. Next, the item score acquisition unit 131 stores the statistical satisfaction information for each overall item in a buffer, paired with the item identifier of each overall item.

[0161] Next, the overall score acquisition unit 132 acquires the overall score of all item scores for all individual items. Here, the overall score acquisition unit 132 acquires the average value of all item scores for all individual items.

[0162] Next, the overall score acquisition unit 132 statistically processes the statistical satisfaction information for all items and calculates the overall statistical satisfaction information for the items. Here, the overall score acquisition unit 132 acquires the average value of the statistical satisfaction information for all items as the overall statistical satisfaction information for the items.

[0163] Next, the overall score acquisition unit 132 calculates a provisional overall score using the formula "Provisional overall score = 0.7 × statistical satisfaction information for overall items + 0.3 × overall score for individual items".

[0164] Next, the overall score acquisition unit 132 obtains correlation information regarding the correlation between the set of satisfaction information and the set of expectation information from the set of satisfaction information for all individual items and the set of expectation information for all individual items.

[0165] Next, the overall score acquisition unit 132 adjusts the acquired provisional overall score using the acquired correlation information. The overall score acquisition unit 132 also uses the adjusted provisional overall score of other companies to obtain a standard score. This standard score is the overall score. Here, let's assume that the overall score acquisition unit 132 calculated the overall score of the organization identified by the organization identifier "Company A" to be "68.0". The overall score acquisition unit 132 then stores the overall score "68.0" in a buffer, associating it with the organization identifier "Company A". Note that the calculation of the adjusted provisional overall score of other companies is performed in the same way as the calculation of the value for "Company A".

[0166] The above process is then applied to other organizational response information that corresponds to the attribute value "manufacturer". For all organizational response information (organizations) that corresponds to the attribute value "manufacturer", the item score for each individual item and the overall score are calculated and temporarily stored in a buffer.

[0167] Next, the impact acquisition unit 133 retrieves the item score from the buffer for each individual item, corresponding to the organization identifier that is paired with the attribute value "manufacturer". In other words, the impact acquisition unit 133 retrieves the item score from the buffer for each organization identifier. Next, the impact acquisition unit 133 retrieves the overall score from the buffer, corresponding to the organization identifier that is paired with the attribute value "manufacturer".

[0168] Next, the impact acquisition unit 133 calculates the correlation between the set of multiple item scores acquired for each individual item and the set of multiple overall scores acquired. The correlation can also be expressed as a correlation coefficient. The impact acquisition unit 133 then stores the impact, which is the correlation, in a buffer for each individual item, paired with the item identifier. This information has the structure of "item identifier, impact," and here, for example, it might be "influence within the industry, 0.84," "stability of the customer base, 0.78," "popularity and recognition, 0.65," "soundness of financial condition, 0.86," "communication and transmission of philosophy, 0.50," "degree of penetration of philosophy in the workplace, 0.82," "communication and transmission of strategic goals, 0.78," and "sense of acceptance of strategic goals, 0.50."

[0169] Furthermore, the above processing is also applied to organizational response information corresponding to other attribute values ​​(for example, "trading company" or "bank").

[0170] Furthermore, for each company, item scores and overall scores are accumulated, and here, the impact of each item is accumulated for each organizational attribute value.

[0171] In this situation, suppose a user of "Company A" inputs a score output instruction to terminal device 2. Next, terminal device 2 receives the score output instruction and constructs a score output instruction that has the organization identifier "Company A". Then, terminal device 2 transmits this score output instruction to information processing device 1.

[0172] Next, the receiving unit 12 of the information processing device 1 receives a score output instruction from the terminal device 2. Next, the processing unit 13 obtains the organization identifier "Company A" from the score output instruction. Next, the processing unit 13 obtains the organization attribute value "Manufacturer" which is paired with the organization identifier "Company A".

[0173] Next, the processing unit 13 retrieves two or more item scores that are paired with the organization identifier "Company A," and item identifiers that are paired with the item scores, from the storage unit 11 or a buffer (not shown).

[0174] Next, the processing unit 13 retrieves the overall score "68.0" which is paired with the organization identifier "Company A" from the storage unit 11 or a buffer (not shown).

[0175] Next, the processing unit 13 retrieves two or more influence levels that are paired with the acquired attribute value "manufacturer," and item identifiers that are paired with the influence levels, from the storage unit 11 or a buffer (not shown).

[0176] Next, the processing unit 13 constructs the output information from the acquired information. Then, the output unit 14 outputs the constructed information. An example of such output is shown in Figure 9. In Figure 9, 901 is Company A's overall score of "68.0". Also, 902 is the item score for each overall item. Here, the overall items are company, boss, work, and workplace. Also, 903 is the item score and influence level for the individual items. Figure 10 is an enlarged view of the area of ​​903. In Figure 10, 1001 is the average value of the expectation information for the individual items. 1002 is the average value of the satisfaction information for the individual items. Column 1003 shows the influence level for each individual item. In Figure 10, as can be seen from 1004 to 1006, the influence level output unit 143 outputs the influence level in association with each item so that the classification of influence levels can be visually distinguished. In other words, here, for example, the darkest background color is used when the influence level is 0.8 or higher, a normal-dark background color is used when the influence level is 0.6 or higher but less than 0.8, and a light background color is used when the influence level is less than 0.6, thereby making the influence level classifications visually distinguishable. Needless to say, methods for visually distinguishing the influence level classifications are not limited to background color; various attribute values ​​such as font and size can also be changed.

[0177] In summary, according to this embodiment, important items for an organization can be easily identified.

[0178] Furthermore, according to this embodiment, the degree of influence can be obtained for each attribute value of the organization, and important items can be grasped with high accuracy.

[0179] Furthermore, according to this embodiment, an information processing device 1 can be provided that can acquire an engagement score and can be used as a so-called engagement device.

[0180] In this specific example, the degree of influence was obtained for each attribute value of the organization. However, the degree of influence may also be obtained for each item regardless of the attribute value of the organization. The technology for obtaining the degree of influence for each attribute value of the organization is based on the fact that the characteristics of a company differ depending on the attribute value of the organization. This technology is extremely useful in employee engagement, for example, in which employees spontaneously try to exert their abilities towards achieving organizational goals, and both employees and the organization grow.

[0181] Furthermore, it goes without saying that the "satisfaction level" item in the survey also includes similar terms such as "satisfaction level" and "current situation," and the "expectation level" item also includes similar terms such as "degree of expectation," "importance," and "importance."

[0182] Furthermore, the processing in this embodiment may be implemented in software. This software may be distributed via software download or the like. Alternatively, this software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments described herein. The software that implements the information processing device 1 in this embodiment is the following program. In other words, this program is a program that enables a computer that can access a recording medium equipped with an organization response information storage unit, which stores two or more item response information, each having an item identifier that identifies an item related to an organization and response information that includes satisfaction information, which is a response regarding the degree of satisfaction of members with the said item, for two or more members belonging to an organization, and organization response information, each having two or more organizations, to function as an item score acquisition unit that statistically processes the response information for members of two or more items included in the two or more organization response information and acquires item scores, which are the scores of the items, for each organization and each item; an overall score acquisition unit that uses the two or more item scores to acquire an overall score, which is an overall score for each organization, for the two or more organization response information; an influence acquisition unit that uses the item scores of the two or more items for each of the two or more organizations and the overall score for each of the two or more organizations to acquire the degree to which the item score of each item has an influence on the overall score for each of the said items; and an influence output unit that outputs the influence acquired by the influence acquisition unit in association with each item. It can be said that such a program is a program that realizes an engagement system.

[0183] (Embodiment 2) In this embodiment, we will describe an information system including a score prediction device that predicts a score using a correspondence relationship and daily information for the period to be predicted. The correspondence relationship is the relationship between past scores (e.g., engagement scores) based on responses to questionnaires given to members of an organization and daily information corresponding to the period corresponding to the questionnaire. The daily information is information about the members, and details will be described later.

[0184] Furthermore, in this embodiment, we will describe an information system that includes a score prediction device that uses a machine learning algorithm to predict scores.

[0185] Furthermore, in this embodiment, we will describe an information system that includes a score prediction device that predicts scores using a correspondence table obtained by data mining.

[0186] Furthermore, in this embodiment, we will describe an information system that includes a score prediction device that predicts scores using calculation formulas.

[0187] Figure 11 is a conceptual diagram of information system B in this embodiment. Information system B comprises a score prediction device 3 and one or more terminal devices 4. The score prediction device 3 is a device that acquires an organization's score. Here, the score is, for example, an engagement score. The score is, for example, a score related to the motivation of the organization's members. The score is, for example, a score related to the members' evaluation of the organization. The score may be a numerical value or information indicating a level (e.g., A, B, C). In addition, the score here is usually the overall score as described above, but it may also be a score for one item, or a score that is a representative value (e.g., mean, median) of two or more item scores.

[0188] The score prediction device 3 is, in this context, a server device. The score prediction device 3 could be, for example, a cloud server or an ASP server, but its type and location are not specified. The terminal device 4 is the device used by the user who wants to obtain a score. The terminal device 4 could be a smartphone, tablet, mobile phone, or personal computer, but its type is not specified.

[0189] Figure 12 is a block diagram of information system B. Figure 13 is a block diagram of the score prediction device 3, which is part of information system B.

[0190] The score prediction device 3 comprises a storage unit 31, a receiving unit 32, a processing unit 33, and an output unit 34.

[0191] The storage unit 31 includes an organization information storage unit 311, a daily information storage unit 312, a teacher score storage unit 313, and a correspondence relationship information storage unit 314.

[0192] The daily information storage unit 312 includes a business input information storage means 3121, a communication information storage means 3122, an attendance status information storage means 3123, a business result information storage means 3124, a stress information storage means 3125, a measurement information storage means 3126, an image storage means 3127, an audio storage means 3128, and a lifestyle information storage means 3129.

[0193] The processing unit 33 includes a score acquisition unit 331. The score acquisition unit 331 includes a corresponding acquisition means 3311 and a score acquisition means 3312.

[0194] The output unit 34 includes a score output unit 341.

[0195] The terminal device 4 includes a terminal storage unit 41, a terminal receiving unit 42, a terminal processing unit 43, a terminal transmission unit 44, a terminal receiving unit 45, and a terminal output unit 46.

[0196] The storage unit 31, which constitutes the score prediction device 3, stores various types of information. These types of information include, for example, organizational information (described later), daily information (described later), teacher scores (described later), correspondence relationship information (described later), and information on two or more members. The information stored in the storage unit 31 may be information received from the terminal device 4, information received from a server (not shown), or information acquired and stored by the score prediction device 3.

[0197] Member information is information about a member. A member has a member identifier that identifies them. A member has one or more member attribute values. Member attribute values ​​are attribute values ​​of the member. Each of the one or more member attribute values ​​is, for example, name, age, job title, year of joining the company, email address, telephone number, and member identifier of the supervisor. It is also assumed that member information of management, supervisors, etc., is stored in storage unit 31. Furthermore, two or more member information items may be stored in a member information storage unit that is not shown.

[0198] The organizational information storage unit 311 stores one or more pieces of organizational information. Organizational information is information about an organization. An organization is, for example, an organization that performs some kind of work. An organization is broadly interpreted as, for example, a so-called company, a sole proprietorship, a local government, etc. An organization may also be an organization within a company. In other words, an organization may be, for example, a department, business site, section, or team within a company. Organizational information has, for example, an organizational identifier and one or more organizational attribute values. The organizational identifier is information that identifies an organization. An organizational identifier may be, for example, an organization name or ID. An organizational attribute value is an attribute value of the organization. An organizational attribute value may be, for example, an industry identifier indicating the type of business the organization is in (for example, bank, apparel, manufacturer, etc.), a size identifier classifying the size of the organization (for example, large company, small or medium-sized enterprise, sole proprietorship, etc.), a regional identifier indicating the location of the head office, the number of employees, a classification based on the number of employees (for example, 5 levels from 1 to 5), the number of business sites, a classification based on the number of business sites (for example, 3 levels of "many", "medium", "few"), etc.

[0199] The daily information storage unit 312 stores one or more daily information items. Daily information is information about members. Daily information is information that can be obtained in the daily lives of members. Daily information does not include answers to questions such as questionnaires. Daily information is, for example, a file, but may also be a database record, etc. The data structure of daily information is not specified. Members are persons belonging to the organization. Members are usually persons who work for the organization. Members are, for example, employees, part-timers, and temporary workers. Daily information is associated with, for example, an organization identifier. It is preferable that daily information be associated with a member identifier. Daily information is usually associated with time information. Time information is information that identifies the time corresponding to the daily information. Time information is, for example, information that identifies the time when the daily information was acquired, or information that identifies the time when the daily information was measured. Time information is usually information that identifies a specific point in time, but may also be period information that identifies a period. Time information is, for example, information that identifies the date and time, information that identifies the day, or information that identifies the month.

[0200] Furthermore, for one piece of information to be associated with another piece of information, it may also mean that one piece of information contains the other piece of information, that one piece of information is linked to the other piece of information, or that the other piece of information contains the first piece of information. In other words, it is sufficient if one piece of information can be retrieved from the other piece of information, or if one piece of information can be retrieved from the other piece of information.

[0201] Daily information includes, for example, work-related information and health information. Work-related information is information about the work performed by the members. Health information is information about the health of the members.

[0202] Business information includes, for example, input information, attendance status information, and business result information. Input information is information entered by members. Input information includes, for example, information entered by members into devices used for work (e.g., personal computers, tablet terminals, servers, etc.). Input information includes, for example, business input information and communication information. Details of business input information and communication information will be described later. Details of attendance status information and business result information will also be described later.

[0203] Health information refers to information about the health of the members. Examples of health information include biometric information and lifestyle information. Biometric information refers to information about the members' biological systems. Examples of biometric information include stress information and measurement information. Details of stress information and measurement information will be discussed later. Details of lifestyle information will also be discussed later.

[0204] The everyday information used to obtain correspondences is called teacher everyday information. The everyday information used in the score prediction process is called predictive everyday information.

[0205] Teacher daily information includes, for example, teacher work information and teacher health information. Teacher work information includes, for example, teacher input information, teacher attendance status information, and teacher work results information. Teacher input information includes, for example, teacher work input information and teacher communication information. Teacher health information includes, for example, teacher biometric information and teacher lifestyle information. Teacher biometric information includes, for example, teacher stress information and teacher measurement information.

[0206] Predictive daily information includes, for example, predictive work information and predictive health information. Predictive work information includes, for example, predictive input information, predictive attendance status information, and predictive work result information. Predictive input information includes, for example, predictive work input information and predictive communication information. Predictive health information includes, for example, predictive biological information and predictive lifestyle information. Predictive biological information includes, for example, predictive stress information and predictive measurement information.

[0207] The business input information storage means 3121, which constitutes the daily information storage unit 312, stores one or more business input information. Business input information is information relating to inputs made by members for the performance of their own work.

[0208] Business input information includes, for example, operation logs of equipment used by members for their work, programs created by members, documents created by members, and daily reports created by members. Business input information is associated with time information. Business input information is associated with, for example, an organization identifier and a member identifier. Business input information may also be information obtained from, for example, operation logs, programs, documents, or daily reports. Information that can be obtained from operation logs is, for example, operation log attribute values. Operation log attribute values ​​include, for example, the operation quantity indicating the amount of operation logs, the number of types obtained using operation logs, the average number of operation logs per day, and information on changes in the number of operation logs. Information on changes in the number of operation logs includes, for example, whether the number of operation logs per day is increasing or decreasing, and information indicating the daily variability of the number of operation logs (e.g., variance). Information that can be obtained from programs is, for example, program attribute values. Program attribute values ​​include, for example, the number of steps in a program, the average number of steps in a program per day, and information on changes in the number of steps in a program created per day. Information on changes in the number of program steps includes, for example, whether the number of program steps per day is increasing or decreasing, and information indicating the daily variation in the number of program steps (e.g., variance). Information that can be obtained from documents includes, for example, document attribute values. Document attribute values ​​include, for example, the amount of data in a document, the average amount of data in a document per day, and information on the change in the amount of data in documents created per day. Information on changes in the amount of data in a document includes, for example, whether the amount of data in a document per day is increasing or decreasing, and information indicating the daily variation in the amount of data in documents (e.g., variance). Information that can be obtained from daily reports includes, for example, daily report attribute values. Daily report attribute values ​​include the amount of data in a daily report, the average amount of data in a daily report per day, information on the change in the amount of data, the number of occurrences of negative words in daily reports over a specified period, the occurrence rate of negative words in daily reports over a specified period, the number of occurrences of positive words in daily reports over a specified period, and the occurrence rate of positive words in daily reports over a specified period.Information on changes in data volume includes, for example, whether the amount of data in daily reports is increasing or decreasing, and information indicating the variability of the amount of data in daily reports from day to day (e.g., variance). Note that operation log attribute values, program attribute values, document attribute values, and daily report attribute values ​​are included in the business input attribute values, which are attribute values ​​of business input information.

[0209] The business input information stored in the business input information storage means 3121 is, for example, information received from terminal device 4 or a server (not shown). The operation log attribute values, program attribute values, document attribute values, and daily report attribute values ​​are, for example, information acquired by processing unit 33 or information received from terminal device 4 or a server (not shown).

[0210] The communication information storage means 3122 stores one or more pieces of communication information. The communication information is associated with time information. The communication information is associated with, for example, an organization identifier and a member identifier. The time information here is information that identifies when the communication information was input, transmitted, or received. The organization identifier here is the identifier of the organization to which the member who input the communication information belongs. The member identifier here is the identifier of the member who input the communication information. The communication information is associated with, for example, the member identifiers of one or more members who are the recipients of the communication.

[0211] Communication information refers to information relating to communication between two or more members. Examples of communication information include chat information entered by members into a chat system (or chat application), social networking service (SNS) information entered by members, emails created by members, and text information derived from audio spoken by members during video conferences. Note that the technology for converting audio to text using speech recognition is publicly known and therefore will not be explained further.

[0212] Communication information may include communication attribute values ​​obtained from chat information, SNS information, email, or text information. Communication attribute values ​​include the amount of data in communication information over a specified period, the number of occurrences of negative words in communication information over a specified period, the rate of occurrence of negative words in communication information over a specified period, the number of occurrences of positive words in communication information over a specified period, the rate of occurrence of positive words in communication information over a specified period, and the response rate of members to messages from management, supervisors, and superiors. The specified period is a predetermined period.

[0213] The communication information stored in the communication information storage means 3122 is, for example, information received from the terminal device 4 or a server (not shown). The communication attribute values ​​are, for example, information acquired by the processing unit 33 or information received from the terminal device 4 or a server (not shown).

[0214] The attendance status information storage means 3123 stores one or more attendance status information. Attendance status information is information relating to attendance status. Attendance status information may be attendance information, or information that can be obtained from one or more attendance information. Attendance information includes the working day, the start time of work, and the end time of work. Attendance information may include, for example, information indicating days of annual leave. Attendance information may include, for example, information indicating work on holidays. Attendance information may include, for example, information on normal working hours. Attendance information may include, for example, information that identifies normal working days.

[0215] Attendance information includes, for example, the number of annual leave days a member has taken, the number of overtime hours a member has worked, and the number of holidays a member has worked. This attendance information is associated with, for example, an organization identifier and a member identifier.

[0216] The attendance status information stored in the attendance status information storage means 3123 is, for example, information acquired by the processing unit 33, or information received from the terminal device 4 or a server (not shown).

[0217] The business result information storage means 3124 stores one or more business result information. Business result information is information about the results of business execution. Examples of business result information include team goal achievement rate, individual goal achievement rate, sales figures, and revenue. Business result information is usually associated with an organization identifier and period information.

[0218] The business result information stored in the business result information storage means 3124 is, for example, information acquired by the processing unit 33, or information received from the terminal device 4 or a server (not shown).

[0219] The stress information storage means 3125 stores one or more pieces of stress information. Stress information is information about the stress of a member. Stress information includes a stress level indicating the degree of stress, and information indicating the presence or absence of stress. Stress information is, for example, the result of a stress check. Stress information is, for example, the response to a questionnaire given to a member (for example, "Please select your stress level from 1 to 5"). Stress information is, for example, information obtained using other health information of the member (for example, heart rate, blood pressure), and information obtained using responses to two or more questions in a questionnaire given to the member. Stress information is associated with, for example, an organization identifier and a member identifier.

[0220] The stress information stored in the stress information storage means 3125 is, for example, information acquired by the processing unit 33, or information received from the terminal device 4 or a server (not shown).

[0221] The measurement information storage means 3126 stores one or more pieces of measurement information. The measurement information is the result of measurements of the member's body. For example, the measurement information may be heart rate or blood pressure. For example, the measurement information may be (a) information acquired using a wearable terminal worn by the member or a measuring device (not shown) and transmitted to the score prediction device 3, or (b) information acquired using a wearable terminal worn by the member or a measuring device (not shown) and input by the member. For example, the measurement information may be associated with an organization identifier or a member identifier.

[0222] The measurement information stored in the measurement information storage means 3126 is, for example, information received from the terminal device 4, a wearable terminal (not shown), or a server (not shown).

[0223] The image storage means 3127 stores one or more images. The images are photographs of one or more members. The images are, for example, recordings of video conferences in which members participate. The images are associated with, for example, an organization identifier and a member identifier.

[0224] The images stored in the image storage means 3127 are, for example, images received from the terminal device 4 or a server (not shown), or images acquired by the score prediction device 3.

[0225] The audio storage means 3128 stores one or more audio recordings. These recordings may be voices spoken by members. Other recordings may be, for example, video recordings of video conferences in which members participate. The audio recordings may also be associated with, for example, an organization identifier and a member identifier.

[0226] The audio stored in the audio storage means 3128 is, for example, audio received from the terminal device 4 or a server (not shown), or audio acquired by the score prediction device 3.

[0227] The lifestyle information storage means 3129 stores one or more lifestyle information. Lifestyle information is information about the members' lives. Examples of lifestyle information include sleep duration, whether or not alcohol was consumed, and the number of cigarettes smoked. Examples of lifestyle information include (a) information entered by the members, (b) information automatically acquired by a sleep measuring device (not shown) and transmitted to the score prediction device 3, and (c) information automatically acquired by a sleep measuring device (not shown) and entered by the members. Lifestyle information is associated with, for example, an organization identifier and a member identifier. Lifestyle information is also associated with, for example, time information (e.g., date).

[0228] The teacher score storage unit 313 stores one or more teacher scores. A teacher score is typically an organization score obtained using multiple organizational response information showing the answers to questions for two or more members of the organization. However, a teacher score may be a score manually entered by a user, or a predicted score previously obtained by the score prediction device 3. The questions are, for example, questionnaire questions. A teacher score may be, for example, the overall score obtained by the information processing device 1 described in Embodiment 1. A teacher score may also be, for example, any item score obtained by the information processing device 1 described in Embodiment 1. Furthermore, a teacher score may be a representative value (e.g., mean, weighted mean, median) of two or more members from the answers to a simpler questionnaire than the one described in Embodiment 1 (for example, a questionnaire with one question such as "Please select how satisfied you are with the company from 1 to 5"). In short, a teacher score may be, for example, an organization score obtained using multiple organizational response information showing the answers to questions for two or more members. Teacher scores are associated with, for example, period information and organization identifiers. The period information associated with a teacher score is information about the period covered by the survey (e.g., 1 year, 6 months, 3 months). The period information may also be time information that identifies when the survey was conducted. The organization identifier associated with a teacher score is the identifier of the organization to which the teacher score indicates.

[0229] The correspondence information storage unit 314 stores one or more correspondence information. For example, the correspondence information may be associated with an organization identifier. Alternatively, the correspondence information may be associated with time information or period information.

[0230] Correspondence information is information about the correspondence between one or more teacher features and teacher scores. Correspondence information is, for example, information that identifies the correspondence between one or more teacher features and teacher scores. Teacher features are information obtained using one or more teacher daily information, or information obtained using one or more teacher daily information and one or more teacher daily information.

[0231] Teacher features include, for example, data volume information that specifies the amount of data in the teacher input information, input frequency information that specifies the frequency of teacher input information input, analysis information that shows the analysis results of the teacher input information, and timing information that specifies the timing of teacher input information input. The analysis information may include, for example, business input attribute values ​​and communication attribute values.

[0232] Correspondence information includes, for example, (1) a learning model, (2) a correspondence table, and (3) an arithmetic formula. Correspondence information is acquired, for example, by the correspondence acquisition means 3311 described later.

[0233] A learning model is data obtained through the learning process of machine learning. A learning model can also be called a predictive model, classification model, learner, or predictor. In machine learning, algorithms such as deep learning, decision trees, random forests, SVR, and SVM can be used. In machine learning, multiple regression analysis and neural networks can also be used. In other words, the machine learning algorithm is irrelevant. A learning model is information obtained by a machine learning algorithm using two or more training data sets that have training vectors and training scores. A training vector is a vector whose elements are two or more training features. Note that a vector is a set of two or more pieces of information, and its structure is irrelevant.

[0234] The correspondence table is a table containing two or more pairs of correspondence information, namely, a teacher vector and a teacher score. The structure of the table is not specified.

[0235] The calculation formula is (S=f(a,b,c,···)) which takes two or more teacher features as input and outputs a teacher score. In the calculation formula, a, b, c, etc. are the teacher features, and S is the score (teacher score or predicted score).

[0236] The reception unit 32 receives various types of information and instructions. These types of information and instructions include, for example, prediction instructions and daily information. A prediction instruction is an instruction to output a prediction score. For example, a prediction instruction is... It has training target conditions. The training target conditions are information that identifies the organization identifier paired with the everyday information that forms the basis of the training data. For example, the training target conditions are conditions using the organization identifier. The prediction instructions have information that identifies the correspondence information to be used, for example. The prediction instructions have training period information that identifies the period of the everyday information that forms the basis of the training data, for example.

[0237] Furthermore, while "reception" here usually refers to reception from terminal device 4, it can also be understood as a concept that includes the reception of information input from input devices such as keyboards, mice, and touch panels, as well as the reception of information read from recording media such as optical discs, magnetic discs, and semiconductor memory.

[0238] The processing unit 33 performs various processes. These various processes include, for example, the processes performed by the score acquisition unit 331, the corresponding acquisition means 3311, and the score acquisition means 3312.

[0239] The processing unit 33 stores, for example, the daily information received by the reception unit 32 in the daily information storage unit 312. The processing unit 33 stores, for example, the daily information received by the reception unit 32 in the daily information storage unit 312, associating it with the member identifier of the member corresponding to the daily information. Such member identifiers are, for example, the identifier of the member who input or transmitted the daily information, and the member identifier associated with the daily information.

[0240] The score acquisition unit 331 acquires a predicted score using the correspondence between the teacher score and one or more teacher daily information items, and one or more predicted daily information items. The predicted score is the score corresponding to one or more predicted daily information items.

[0241] The score acquisition unit 331 acquires a predicted score using, for example, the correspondence information in the correspondence information storage unit 314 and one or more predicted daily information items.

[0242] The score acquisition unit 331 may acquire features as follows, for example. Features are teacher features used to acquire correspondence relationship information, or predictive features used to acquire a predicted score. Note that the process by which the score acquisition unit 331 acquires features, as described below, is performed by the correspondence acquisition means 3311 if the feature is a teacher feature, and by the score acquisition means 3312 if the feature is a predictive feature. Features are, for example, daily information, or attribute values ​​of daily information that can be obtained from daily information (e.g., operation log attribute values, program attribute values, document attribute values, daily report attribute values, etc.). A teacher vector is composed of two or more teacher features. A predictive vector is composed of two or more predictive features. Note that it does not matter which of the information acquired by the score acquisition unit 331 described below is used as a feature. The score acquisition unit 331 only needs to use any two or more features to acquire correspondence relationship information or to acquire a predicted score.

[0243] The score acquisition unit 331, for example, acquires operation logs from the business input information storage means 3121 for each member, paired with each member identifier and corresponding to the time information for each day of the processing period. It then acquires one or more types of operation log attribute values ​​from the operation logs and temporarily stores at least one of these operation log attribute values ​​in the business input information storage means 3121. Note that the technology for acquiring business input attribute values ​​such as the amount of data and the aforementioned change information from business input information such as operation logs is publicly known technology, so a detailed explanation is omitted. Operation logs include, for example, login and logout dates and times of PCs operating within the organization, viewing and editing of various files, network connections, and other operation history of members.

[0244] The score acquisition unit 331, for example, acquires a program from the business input information storage means 3121 that corresponds to the time information for each day of the period subject to processing, paired with each member identifier for each member, acquires one or more program attribute values ​​from the program, and temporarily stores at least one or more program attribute values ​​in the business input information storage means 3121.

[0245] The score acquisition unit 331 acquires, for example, the number of steps in one or more program files for each date information corresponding to a program file (for each day it was created). The score acquisition unit 331 then acquires, for example, the average number of steps in program files per day, information showing the variation in the number of steps created each day during the target period, and change information showing whether the number of steps in the program created per day is increasing or decreasing.

[0246] The score acquisition unit 331, for example, acquires a document from the business input information storage means 3121 that corresponds to the time information for each day of the period subject to processing, paired with each member identifier for each member, acquires one or more types of document attribute values ​​from the document, and temporarily stores at least one of these document attribute values ​​in the business input information storage means 3121. A document is a written document that is a direct deliverable of the performance of work. Examples of documents include design specifications in the technical department and accounting information in the accounting department.

[0247] The score acquisition unit 331 acquires, for example, the data volume of one or more documents for each date information corresponding to a document (for each day it was created). The score acquisition unit 331 then acquires, for example, the average value of the document data volume for each day, information showing the variation in the data volume for each day during the target period, and change information showing whether the data volume of documents created in a day is increasing or decreasing.

[0248] The score acquisition unit 331, for example, acquires a daily report from the business input information storage means 3121 that corresponds to the time information for each day of the period subject to processing, paired with each member identifier for each member, acquires one or more types of daily report attribute values ​​from the daily report, and temporarily stores at least one of these daily report attribute values ​​in the business input information storage means 3121.

[0249] The score acquisition unit 331, for example, acquires the data volume of each of the acquired daily reports (one or more). The score acquisition unit 331 then acquires, for example, the average value of the data volume, information indicating the variability of the data volume, and change information indicating whether the data volume is increasing or decreasing. The score acquisition unit 331 also performs morphological analysis on the acquired daily reports (one or more), refers to a dictionary of negative words, and acquires the number of occurrences of negative words. The score acquisition unit 331 also refers to a dictionary of positive words based on the results of the morphological analysis of the acquired daily reports (one or more), and acquires the number of occurrences of positive words. The score acquisition unit 331 also acquires, for example, the number of independent words in the acquired daily reports (one or more), and acquires the occurrence rate of negative words (number of negative words in relation to that number of independent words) and the occurrence rate of positive words (number of positive words in relation to that number of independent words).

[0250] The score acquisition unit 331, for example, acquires communication information from the communication information storage means 3122 that corresponds to the time information for each day of the period to be processed, paired with each member identifier, and acquires, for example, one or more types of communication attribute values ​​for the communication information. The score acquisition unit 331 also acquires, for example, the amount of data of the acquired communication information. The score acquisition unit 331 also performs morphological analysis on the communication information to acquire one or more independent words and acquires the number of negative words, which is the number of such independent words that exist in a negative word dictionary (not shown). The score acquisition unit 331 also performs morphological analysis on the communication information to acquire one or more independent words and acquires the number of positive words, which is the number of such independent words that exist in a positive word dictionary (not shown). The score acquisition unit 331 also performs morphological analysis on the communication information to acquire, for example, the ratio of negative words and the ratio of positive words among the number of acquired independent words.

[0251] The score acquisition unit 331, for example, obtains, for each member, the sent emails corresponding to the time information for each day of the processing period, paired with each member identifier, obtains the source emails of those emails, determines whether the sender identifier (e.g., email address) of the source emails is stored in the organization information storage unit 311 in association with the member identifier, and if it is stored, increments the counter for replies to messages from recipients (management, supervisors, or superiors, etc.) by 1. The score acquisition unit 331 also obtains, for each member, the number of emails from recipients among the received emails corresponding to the time information for each day of the processing period, paired with each member identifier. In more detail, for example, the score acquisition unit 331 obtains, for example, the member identifiers of supervisors, management, and supervisors paired with the member identifier, obtains the email addresses of each member identifier from the member information set, and obtains the number of emails from which that email address originates (the number of emails from recipients). The score acquisition unit 331 then calculates, for example, the response rate of each member to messages from recipients, based on the number of emails from recipients and the value of the response counter for each member. For example, the storage unit 31 stores the identifier of each member's recipient (e.g., email address) so that it corresponds to each member identifier.

[0252] The score acquisition unit 331 acquires, for example, attendance information for each member, paired with a member identifier, for each day of the period to be processed. The score acquisition unit 331 then acquires, for example, attendance status information for each member for the period to be processed (e.g., number of annual leave days, number of overtime hours, number of holiday work days). It should be noted that the technique for acquiring the number of annual leave days, number of overtime hours, number of holiday work days, etc., from a set of attendance information is publicly known.

[0253] The score acquisition unit 331 reads, for example, one or more business result information from the business result information storage means 3124 for each organization.

[0254] The score acquisition unit 331 reads from the storage unit 31, for example, one or more responses to a questionnaire corresponding to the time information for the period to be processed, paired with each member identifier for each member. Next, the score acquisition unit 331 acquires stress information from the one or more responses for each member. The content of the questionnaire and the algorithm for acquiring stress information are not specified. The score acquisition unit 331 acquires, for example, responses to questions inquiring about the stress level. The score acquisition unit 331 calculates the stress level by substituting the responses to the two or more questions regarding the stress level into a calculation formula. The score acquisition unit 331 constructs a vector from the responses to the two or more questions regarding the stress level and acquires the stress level that is paired with the vector that most closely approximates that vector. In this case, it is assumed that two or more corresponding pieces of information, which are pairs of vectors and stress levels, are stored in the storage unit 31.

[0255] The score acquisition unit 331, for example, acquires heart rate and / or blood pressure from the measurement information storage means 3126, paired with each member identifier, for each member, and corresponding to the time information for the period to be processed. Next, the score acquisition unit 331 acquires stress information for each member, for example, where a higher heart rate and / or blood pressure value indicates higher stress. The score acquisition unit 331 acquires, for example, the number of times the heart rate and / or blood pressure value is greater than a threshold, and acquires a stress level based on that number. The stress level based on that number increases with each subsequent occurrence. The score acquisition unit 331 also acquires, for example, the continuous time during which the heart rate and / or blood pressure value is greater than a threshold, and acquires a stress level based on the sum of that continuous time. The stress level based on the sum of that continuous time increases with each subsequent time.

[0256] The score acquisition unit 331 acquires, for example, one or more pieces of measurement information from the measurement information storage means 3126, each member's member identifier paired with the time information for the period to be processed. The score acquisition unit 331 also acquires, for example, representative values ​​(e.g., mean, median) of the measurement information for each type of measurement information.

[0257] The score acquisition unit 331, for example, acquires one or more images from the image storage means 3127 for each member, paired with a member identifier, for the period to be processed. Next, the score acquisition unit 331 performs facial expression analysis on each of the one or more images and acquires a facial expression identifier (for example, any of joy, anger, sadness, or other emotions, or normal). The score acquisition unit 331 also performs statistical processing on the acquired one or more facial expression identifiers and acquires the percentage of negative expressions (angry, crying, etc.). Note that such percentages are examples of features. Furthermore, the process of performing facial expression analysis and acquiring facial expression identifiers is a known technique.

[0258] The score acquisition unit 331, for example, acquires one or more audio recordings from the audio storage means 3128 for each member, paired with a member identifier, for the period to be processed. Next, the score acquisition unit 331 acquires one or more feature quantities (e.g., spectral information, speech intervals, silent intervals, etc.) from each of the one or more audio recordings, and uses these feature quantities to acquire the characteristics of the audio. The score acquisition unit 331 uses the feature quantities to acquire, for example, the proportion of speaking time in the meeting attended, and emotion identifiers (laughing, neutral, angry, crying, etc.). The techniques for acquiring the feature quantities are publicly known techniques, such as LPC analysis and cepstrum analysis.

[0259] The score acquisition unit 331 reads, for example, lifestyle information for the period to be processed from the lifestyle information storage means 3129, paired with each member's identifier. The score acquisition unit 331 then statistically processes the lifestyle information for each member and obtains the characteristics of the lifestyle information. These characteristics of the lifestyle information include, for example, the average amount of sleep time, the variance of sleep time, the number of days alcohol was consumed, the percentage of days alcohol was consumed, and the average number of cigarettes smoked per day.

[0260] The score acquisition unit 331 may acquire correspondence relationship information using two or more teacher data sets, each containing two or more acquired teacher vectors with two or more teacher features and a teacher score. The teacher vector is information acquired by the score acquisition unit 331 through the process described above. The correspondence relationship information may also be stored in advance in the correspondence relationship information storage unit 314.

[0261] The score acquisition unit 331 provides a machine learning module with, for example, a learning model which is correspondence relationship information and a prediction vector which is a vector with two or more prediction features as elements, and performs prediction processing by executing the module to obtain a prediction score. The prediction features are prediction daily information or information that can be obtained from prediction daily information. The prediction vector is information obtained by the score acquisition unit 331 through the above processing. The machine learning module can be any, such as Tiny_SVM, TensorFlow functions, or MicrosoftML functions.

[0262] The score acquisition unit 331 acquires a prediction score using, for example, a correspondence table containing correspondence relationship information and a prediction vector having two or more prediction features as elements. More specifically, the score acquisition unit 331 searches the correspondence table for the teacher vector that best approximates the prediction vector having two or more prediction features as elements, and acquires the teacher score that is paired with that teacher vector as the prediction score.

[0263] Furthermore, the score acquisition unit 331 determines, for example, two or more teacher vectors from a correspondence table whose distance from a prediction vector, which has two or more prediction features as elements, is close enough to satisfy predetermined conditions, and obtains representative values ​​of the teacher scores corresponding to each of these two or more teacher vectors. The representative values ​​are, for example, the mean, median, and weighted average. The weighted average is obtained, for example, by calculating weights inversely proportional to the distance between the vectors and using these weights. The predetermined conditions are, for example, being within or less than a threshold, and the proximity being within the top N (where N is a natural number greater than or equal to 2).

[0264] Furthermore, the score acquisition unit 331, for example, substitutes two or more prediction features into a calculation formula, executes the calculation formula, and calculates a prediction score. The calculation formula is stored in the correspondence relationship information storage unit 314.

[0265] The score acquisition unit 331 acquires a predicted score using, for example, the correspondence between one or more teacher daily information items, including teacher work information, and the teacher score, and one or more predicted daily information items, including predicted work information. Note that using the correspondence usually refers to using the correspondence information described above.

[0266] The score acquisition unit 331 acquires a predicted score using, for example, the correspondence between one or more teacher daily information, including teacher input information, and the teacher score, and one or more predicted daily information, including predictive input information.

[0267] The score acquisition unit 331 acquires a predicted score using, for example, the correspondence between one or more teacher daily information, including teacher work input information, and the teacher score, and one or more predicted daily information, including prediction work input information.

[0268] The score acquisition unit 331 acquires a predicted score using, for example, the correspondence between one or more teacher daily information items, including teacher communication information, and the teacher score, and one or more predicted daily information items, including predicted communication information.

[0269] The score acquisition unit 331 acquires, for example, one or more types of information from data volume information that identifies the amount of data in the teacher input information, input frequency information that identifies the frequency of input of the teacher input information, analysis information that shows the analysis results of the teacher input information, and timing information that identifies the timing of input of the teacher input information, and also acquires one or more types of information from data volume information of the prediction input information, input frequency information of the prediction input information, analysis information of the prediction input information, and timing information of the prediction input information, and acquires correspondence relationship information that identifies the correspondence between one or more teacher features including one or more types of information acquired from the teacher input information and the teacher score, and uses the correspondence relationship information and a prediction vector having two or more prediction features including one or more types of information acquired from the prediction input information to acquire a prediction score.

[0270] For example, the score acquisition unit 331 acquires a predicted score by using the correspondence between one or more teacher daily information including teacher attendance status information and teacher scores, and one or more predicted daily information including predicted attendance status information.

[0271] For example, the score acquisition unit 331 acquires a predicted score by using the correspondence between one or more teacher daily information including teacher business result information and teacher scores, and one or more predicted daily information including predicted business result information.

[0272] For example, the score acquisition unit 331 acquires a predicted score by using the correspondence between one or more teacher daily information including teacher health information and teacher scores, and one or more predicted daily information including predicted health information.

[0273] For example, the score acquisition unit 331 acquires a predicted score by using the correspondence between one or more teacher daily information including teacher biometric information and teacher scores, and one or more predicted daily information including predicted biometric information.

[0274] For example, the score acquisition unit 331 acquires a predicted score by using the correspondence between one or more teacher daily information including teacher stress information and teacher scores, and one or more predicted daily information including predicted stress information.

[0275] For example, the score acquisition unit 331 acquires a predicted score by using the correspondence between one or more teacher daily information including teacher measurement information and teacher scores, and one or more predicted daily information including predicted measurement information.

[0276] For example, the score acquisition unit 331 acquires a predicted score by using the correspondence between one or more teacher daily information including teacher biometric feature information and teacher scores, and one or more predicted daily information including predicted biometric feature information.

[0277] The score acquisition unit 331 acquires a predicted score using, for example, the correspondence between one or more teacher daily information items, including teacher lifestyle information, and the teacher score, and one or more predicted daily information items, including predicted lifestyle information.

[0278] The score acquisition unit 331 may, for example, read past scores corresponding to the acquired predicted score from the storage unit 31, and use the past scores and the acquired predicted score to acquire score fluctuation information regarding the increase or decrease in the score. The score fluctuation information may include, for example, "predicted score - past score", "past score - predicted score", "information indicating whether the score will increase or decrease", and "information indicating the degree of increase or decrease in the score".

[0279] The correspondence acquisition means 3311, which constitutes the score acquisition unit 331, acquires correspondence relationship information that identifies the correspondence between one or more teacher daily information items and teacher scores.

[0280] The correspondence acquisition means 3311 may, for example, acquire correspondence relationship information that identifies the correspondence between one or more teacher daily information and teacher scores for each organizational condition composed of one or more organizational attribute values. An organizational condition is, for example, one organizational attribute value. An organizational condition is, for example, a logical formula (e.g., "Organization A or Organization B") having two or more organizational conditions as elements. An organizational condition is, for example, an industry identifier such as "electrical manufacturer," "bank," or "trading company." An organizational condition is, for example, a size identifier such as "large company" or "small or medium-sized enterprise."

[0281] The following describes an example of the process by which the correspondence acquisition means 3311 acquires the learning model, correspondence table, and calculation formula. (1) When obtaining a learning model

[0282] The correspondence acquisition means 3311, for example, uses one or more pairs of one or more teacher daily information and teacher scores to perform a learning process using a machine learning algorithm and acquire correspondence relationship information, which is a learning model.

[0283] More specifically, the corresponding acquisition means 3311 acquires, for example, two or more sets of teacher daily information for acquiring a learning model from the daily information storage unit 312. Each of the two or more sets of teacher daily information may be, for example, a set of teacher daily information from a different organization. Each of the two or more sets of teacher daily information may be, for example, a set of teacher daily information from a different period.

[0284] Next, for each set of teacher daily information, the correspondence acquisition means 3311 acquires, for example, two or more teacher features using the acquired one or more teacher daily information, and acquires a teacher vector with each of the two or more teacher features as an element. The correspondence acquisition means 3311 also acquires, for example, a teacher score corresponding to the set of teacher daily information to be processed from the teacher score storage unit 313. For example, the teacher score is associated with the organization identifier and / or time information that is paired with the set of teacher daily information to be processed.

[0285] Next, the correspondence acquisition means 3311 acquires teacher data, which includes a teacher vector and a teacher score, for each set of teacher daily information. The correspondence acquisition means 3311 then obtains two or more teacher data. In the teacher data, each teacher feature of the teacher vector can be said to be an explanatory variable, and the teacher score can be said to be an objective variable. Furthermore, the teacher features are teacher daily information or information acquired from teacher daily information.

[0286] Next, the correspondence acquisition means 3311 provides, for example, two or more training data to a module that performs machine learning learning processing, executes the module, acquires a learning model, and at least temporarily stores the learning model in the correspondence relationship information storage unit 314.

[0287] This learning model takes predicted daily information or / or prediction vectors obtained from predicted daily information as input, and outputs a prediction score. Furthermore, the machine learning learning algorithm can be any algorithm, such as deep learning, decision trees, random forests, SVR, or SVM. In other words, the machine learning learning algorithm is not restricted. The module used for the machine learning learning process can also be any module, such as Tiny_SVM, TensorFlow functions, or MicrosoftML functions. (2) When obtaining a correspondence table

[0288] The correspondence acquisition means 3311 acquires two or more teacher data having a teacher vector and a teacher score, for example, in the same manner as the process described in (1). Next, the correspondence acquisition means 3311 constructs a correspondence table having two or more correspondence information having a teacher vector and a teacher score, for example, and temporarily stores the correspondence table in the correspondence relationship information storage unit 314. (3) When obtaining the calculation formula

[0289] The correspondence acquisition means 3311 acquires two or more training data sets having a training vector and a training score, for example, in the same way as the process described in (1). Next, the correspondence acquisition means 3311 acquires a calculation formula that takes each of the two or more training vectors as input and outputs the training score corresponding to each training vector.

[0290] The corresponding acquisition means 3311 is, for example, the original formula that forms the basis of the calculation formula (for example, "Score S = ax1 + bx2 + cx3 + ... + (n-1)x n +n(a,b,c...n is a parameter, x1,x2,x3,...x) n The variable is read from the storage unit 31. Next, the correspondence acquisition means 3311 substitutes, for example, two or more training data into the variable of the calculation formula and acquires the parameters from which each training score can be obtained by multiple regression analysis, multivariate analysis, etc. Then, the correspondence acquisition means 3311 temporarily stores the acquired calculation formula in the correspondence relationship information storage unit 314.

[0291] The score acquisition means 3312 acquires a prediction score by using the correspondence information and one or more pieces of predicted daily information.

[0292] The score acquisition means 3312, for example, acquires the correspondence information corresponding to the organization condition with which the organization to be predicted matches from the correspondence information storage unit 314, and acquires a prediction score by using the correspondence information and one or more pieces of predicted daily information.

[0293] More specifically, the score acquisition means 3312, for example, acquires one or more pieces of predicted daily information, which are the daily information of the organization and period corresponding to the received prediction instruction, from the daily information storage unit 312. Next, the score acquisition means 3312, for example, acquires two or more prediction features by using one or more pieces of predicted daily information, and acquires a prediction vector having the two or more prediction features as elements. Note that the method of acquiring prediction features and the method of acquiring a prediction vector by using predicted daily information have been described above. Next, the score acquisition means 3312 acquires a prediction score by using the correspondence information and the prediction vector.

[0294] Hereinafter, a processing example in which the score acquisition means 3312 acquires a prediction score by using any one of three types of correspondence information will be described. (1) When using a learning model

[0295] The score acquisition means 3312, for example, performs prediction processing by a machine learning algorithm by using a learning model and one or more pieces of predicted daily information, and acquires a prediction score.

[0296] More specifically, the score acquisition means 3312 acquires a prediction vector using one or more prediction daily information items. Next, the score acquisition means 3312 acquires a learning model corresponding to the received prediction instruction from the correspondence relationship information storage unit 314. Then, the score acquisition means 3312 provides the prediction vector and the learning model to a machine learning prediction processing module, executes the module, and acquires a prediction score. Note that the machine learning prediction processing algorithm can be a deep learning algorithm, a decision tree algorithm, a random forest algorithm, a SVR algorithm, etc. In other words, the machine learning prediction processing algorithm is not specified. Also, as mentioned above, the machine learning prediction processing module is not specified. (2) When using a correspondence table

[0297] The score acquisition means 3312 obtains a prediction vector, which is a vector having two or more prediction features, using, for example, one or more prediction daily information. Next, the score acquisition means 3312 applies the prediction vector to a correspondence table and obtains a prediction score.

[0298] More specifically, the score acquisition means 3312 acquires a prediction vector using, for example, one or more prediction daily information. Next, the score acquisition means 3312 searches a correspondence table for, for example, the vector that most closely approximates the prediction vector, and acquires the teacher score that is paired with that vector as the prediction score.

[0299] Furthermore, the score acquisition means 3312 may, for example, determine from a correspondence table vectors that are close enough to the acquired prediction vector to satisfy predetermined conditions, and obtain representative values ​​of the teacher scores corresponding to each of these two or more vectors. The representative values ​​are, for example, the mean, median, and weighted average. The weighted average is obtained, for example, by calculating weights inversely proportional to the distance between vectors and using those weights. The predetermined conditions are, for example, that the distance is within or less than a threshold, and that the shortness of the distance is among the top N (N is 2 or more). (3) When using an arithmetic expression

[0300] The score acquisition means 3312, for example, acquires a prediction vector using one or more prediction daily information, provides each feature of the prediction vector to a calculation formula, executes the calculation formula, and obtains a prediction score. The calculation formula is an example of the correspondence information stored in the correspondence information storage unit 314.

[0301] The score output unit 341 outputs the predicted score acquired by the score acquisition unit 331. The score output unit 341 may also output the score change information acquired by the score acquisition unit 331.

[0302] Here, output usually refers to transmission to terminal device 4. However, it is also acceptable to consider output here as a concept that includes display on a screen, projection using a projector, printing with a printer, sound output, storage on a recording medium, and transfer of processing results to other processing devices or other programs.

[0303] The score output unit 341 may pass the predicted score acquired by the score acquisition unit 331 back to the score acquisition unit 331, have the score acquisition unit 331 acquire score change information using the predicted score, and output the score change information.

[0304] The terminal storage unit 41, which constitutes the terminal device 4, stores various types of information. These types of information include, for example, an organization identifier and a member identifier that identify the user's organization. Other types of information include, for example, information received by the terminal receiving unit 45 (e.g., a prediction score). The organization identifier can also be considered as information that identifies the user.

[0305] The terminal reception unit 42 receives various instructions and information. These instructions and information include, for example, predictive instructions and daily information. Here, "reception" is a concept that includes receiving information input from input devices such as keyboards, mice, and touch panels, receiving information transmitted via wired or wireless communication lines, and receiving information read from recording media such as optical discs, magnetic discs, and semiconductor memory.

[0306] The input methods for various instructions and information can be anything, such as a touch panel, keyboard, mouse, or menu screen. The terminal reception unit 42 can be implemented using device drivers for input methods such as touch panels and keyboards, or control software for menu screens.

[0307] The terminal processing unit 43 performs various processes, such as configuring the information received by the terminal receiving unit 45 into data to be displayed. Other various processes include configuring instructions received by the terminal reception unit 42 into instructions to be transmitted.

[0308] The terminal transmission unit 44 transmits various instructions and information to the score prediction device 3. These instructions and information include, for example, instructions configured by the terminal processing unit 43 and instructions and information received by the terminal reception unit 42.

[0309] The terminal receiving unit 45 receives various types of information from the score prediction device 3. These types of information include, for example, predicted scores.

[0310] The terminal output unit 46 acquires various types of information. These types of information include, for example, information received by the terminal reception unit 42, information received by the terminal receiving unit 45, and information generated by the terminal processing unit 43. These types of information include, for example, a prediction score.

[0311] Here, "output" is a concept that includes display on a screen, projection using a projector, printing with a printer, sound output, transmission to an external device, storage on a recording medium, and transfer of processing results to other processing devices or other programs.

[0312] The storage unit 31, organizational information storage unit 311, daily information storage unit 312, business input information storage means 3121, communication information storage means 3122, business result information storage means 3124, stress information storage means 3125, measurement information storage means 3126, image storage means 3127, voice storage means 3128, lifestyle information storage means 3129, teacher score storage unit 313, correspondence relationship information storage unit 314, and terminal storage unit 41 are preferably made of non-volatile recording media, but can also be made of volatile recording media.

[0313] The process by which information is stored in the storage unit 31, etc. is not relevant. For example, information may be stored in the storage unit 31, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the storage unit 31, etc., or information input via an input device may be stored in the storage unit 31, etc.

[0314] The reception unit 32 and the terminal receiving unit 45 are usually implemented by wireless or wired communication means, but they may also be implemented by means of receiving broadcasts.

[0315] The processing unit 33, score acquisition unit 331, corresponding acquisition means 3311, score acquisition means 3312, and terminal processing unit 43 can typically be implemented using a processor, memory, etc. The processing procedures of the processing unit 33, etc., are typically implemented in software, and this software is recorded on a recording medium such as ROM. However, it may also be implemented in hardware (dedicated circuitry). The processor can be a CPU, MPU, GPU, etc., and the type is not limited.

[0316] The output unit 34, the score output unit 341, and the terminal transmission unit 44 are usually implemented by wireless or wired communication means, but may also be implemented by broadcasting means.

[0317] The terminal output unit 46 may or may not be considered to include output devices such as displays and speakers. The terminal output unit 46 can be implemented using driver software for an output device, or a driver software for an output device and an output device.

[0318] Next, an example of the operation of the score prediction device 3 will be explained using the flowchart in Figure 14.

[0319] (Step S1401) The reception unit 32 determines whether or not it has received daily information from the terminal device 4, associating it with the member identifier. If daily information is received, the unit proceeds to step S1402; if daily information is not received, the unit proceeds to step S1403. Note that daily information is usually associated with the member identifier or the organization identifier.

[0320] (Step S1402) The processing unit 33 stores the daily information received in step S1401 in the daily information storage unit 312. The process returns to step S1401. The stored daily information is usually associated with member identifiers or organization identifiers. The stored daily information is also usually associated with time information. In other words, it is preferable for the processing unit 33 to obtain date and time information from a clock (not shown) and store the daily information in the daily information storage unit 312 in association with that date and time information.

[0321] (Step S1403) The reception unit 32 determines whether or not it has received a predictive instruction from the terminal device 4. If a predictive instruction is received, the process proceeds to step S1404; otherwise, the process returns to step S1401.

[0322] (Step S1404) The correspondence acquisition means 3311 performs correspondence acquisition processing. An example of correspondence acquisition processing will be explained using the flowchart in Figure 15. Correspondence acquisition processing is the process of acquiring correspondence relationship information.

[0323] (Step S1405) The score acquisition means 3312 performs a score acquisition process. An example of the score acquisition process will be explained using the flowchart in Figure 25. The score acquisition process is the process of acquiring a predicted score.

[0324] (Step S1406) The score output unit 341 transmits the predicted score obtained in step S1405 to the terminal device 4 that sent the prediction instruction. The process returns to step S1401.

[0325] In the flowchart of Figure 14, the correspondence acquisition process in step S1404 may be performed before receiving the prediction instruction. In other words, the correspondence acquisition process and the score acquisition process do not need to be performed consecutively.

[0326] Furthermore, in the flowchart of Figure 14, processing is terminated by power off or processing termination interrupt.

[0327] Next, an example of the correspondence acquisition process in step S1404 will be explained using the flowchart in Figure 15.

[0328] (Step S1501) The correspondence acquisition means 3311 acquires teacher period information. The correspondence acquisition means 3311 acquires, for example, teacher period information included in the received prediction instruction. The correspondence acquisition means 3311 acquires, for example, predetermined teacher period information from the storage unit 31. Teacher period information is information that specifies the period of teacher daily information used to acquire correspondence relationship information.

[0329] (Step S1502) The correspondence acquisition means 3311 acquires the target training conditions. The correspondence acquisition means 3311 acquires, for example, the target training conditions included in the received prediction instruction. The correspondence acquisition means 3311 acquires, for example, predetermined target training conditions from the storage unit 31. The target training conditions are the conditions of the target organization used when predicting the score. The target training conditions are, for example, the organization identifier of the target organization from which to obtain the predicted score. The target training conditions are, for example, the organization identifier of all organizations. The target training conditions are, for example, the conditions of the target organization attribute values ​​(for example, industry identifier, size identifier, etc.) from which to obtain the predicted score.

[0330] (Step S1503) The corresponding acquisition means 3311 assigns 1 to counter i.

[0331] (Step S1504) The correspondence acquisition means 3311 determines whether the i-th teacher daily set that matches the conditions including teacher period information and teacher target rules exists in the daily information storage unit 312. If the i-th teacher daily set exists, the process proceeds to step S1505; otherwise, the process proceeds to step S1510. Note that a teacher daily set is a set of one or more teacher daily information items.

[0332] (Step S1505) The corresponding acquisition means 3311 acquires the i-th teacher daily set that matches the conditions including teacher period information and teacher target conditions from the daily information storage unit 312.

[0333] (Step S1506) The corresponding acquisition means 3311 performs the process of acquiring a feature group using the i-th teacher daily set acquired in step S1505. An example of such feature group acquisition process will be explained using the flowchart in Figure 16. A feature group is usually a set of two or more features. Also, the features here are teacher features.

[0334] (Step S1507) The correspondence acquisition means 3311 acquires the teacher score corresponding to the i-th teacher daily set from the teacher score storage unit 313. Note that the teacher daily set and the teacher score are associated. For example, the teacher daily information associated with the time information for the period specified by the period information associated with the teacher score is the teacher daily information corresponding to the teacher score.

[0335] (Step S1508) The corresponding acquisition means 3311 constructs the i-th teacher data having a teacher vector composed of the feature group acquired in step S1506 and a teacher score acquired in step S1507, and temporarily stores it in a buffer (not shown).

[0336] (Step S1509) The corresponding acquisition means 3311 increments counter i by 1. Return to step S1504.

[0337] (Step S1510) The correspondence acquisition means 3311 acquires correspondence relationship information using two or more training data temporarily stored in step S1508. The method for acquiring correspondence relationship information using two or more training data is described above. Also, as described above, the correspondence acquisition means 3311 acquires, for example, a learning device, a correspondence table, or a calculation formula.

[0338] (Step S1511) The correspondence acquisition means 3311 temporarily stores the correspondence relationship information acquired in step S1510 in the correspondence relationship information storage unit 314. Then it returns to the higher-level processing.

[0339] Next, an example of the feature group acquisition process in step S1506 will be explained using the flowchart in Figure 16. In the flowchart in Figure 16, for example, the daily information to be used is predetermined. Furthermore, the information that identifies the daily information to be used is stored in association with, for example, the correspondence relationship information. In other words, the daily information used when acquiring the correspondence relationship information and the daily information used to acquire the prediction score are usually the same.

[0340] (Step S1601) The score acquisition unit 331 determines whether or not to use the business input information to acquire the predicted score. If the business input information is to be used, the process proceeds to step S1602; otherwise, the process proceeds to step S1603.

[0341] (Step S1602) The score acquisition unit 331 performs business input information processing. An example of business input information processing will be explained using the flowchart in Figure 17. Business input information processing is the process of obtaining one or more characteristics related to business input information using business input information.

[0342] (Step S1603) The score acquisition unit 331 determines whether or not to use communication information to acquire the predicted score. If communication information is to be used, the process proceeds to step S1604; otherwise, the process proceeds to step S1605.

[0343] (Step S1604) The score acquisition unit 331 performs communication information processing. An example of communication information processing will be explained using the flowchart in Figure 18. Communication information processing is the process of using communication information to acquire one or more features related to the communication information.

[0344] (Step S1605) The score acquisition unit 331 determines whether or not to use attendance status information to acquire the predicted score. If attendance status information is to be used, the process proceeds to step S1606; if attendance status information is not to be used, the process proceeds to step S1607.

[0345] (Step S1606) The score acquisition unit 331 performs attendance status information processing. An example of attendance status information processing will be explained using the flowchart in Figure 19. Attendance status information processing is the process of obtaining one or more features related to attendance status information using attendance status information.

[0346] (Step S1607) The score acquisition unit 331 determines whether or not to use the business result information to acquire the predicted score. If the business result information is to be used, the process proceeds to step S1608; if the business result information is not to be used, the process proceeds to step S1609.

[0347] (Step S1608) The score acquisition unit 331 reads the business result information to be used from the business result information storage means 3124, which is business result information that corresponds to the organizational identifier of the target organization and the period information of the target period.

[0348] (Step S1609) The score acquisition unit 331 determines whether or not to use stress information to obtain a predicted score. If stress information is to be used, the process proceeds to step S1610; if stress information is not to be used, the process proceeds to step S1611.

[0349] (Step S1610) The score acquisition unit 331 performs stress information processing. An example of stress information processing will be explained using the flowchart in Figure 20. Stress information processing is the process of acquiring one or more features related to stress information.

[0350] (Step S1611) The score acquisition unit 331 determines whether or not to use the measurement information. If the measurement information is to be used, the unit proceeds to step S1611; otherwise, the unit proceeds to step S1612.

[0351] (Step S1612) The score acquisition unit 331 performs measurement information processing. An example of measurement information processing will be explained using the flowchart in Figure 21. Measurement information processing is the process of using measurement information to acquire one or more features related to the measurement information.

[0352] (Step S1613) The score acquisition unit 331 determines whether or not to use an image to acquire the predicted score. If an image is to be used, the process proceeds to step S1614; otherwise, the process proceeds to step S1615.

[0353] (Step S1614) The score acquisition unit 331 performs image information processing. An example of image information processing will be explained using the flowchart in Figure 22. Image information processing is the process of using an image to acquire one or more features related to the image.

[0354] (Step S1615) The score acquisition unit 331 determines whether or not to use voice to acquire the predicted score. If voice is to be used, proceed to step S1616; otherwise, proceed to step S1617.

[0355] (Step S1616) The score acquisition unit 331 performs voice information processing. An example of voice information processing will be explained using the flowchart in Figure 23. Voice information processing is the process of acquiring one or more features related to voice using voice.

[0356] (Step S1617) The score acquisition unit 331 determines whether or not to use lifestyle information to obtain the predicted score. If lifestyle information is to be used, the process proceeds to step S1618; otherwise, it returns to the higher-level processing.

[0357] (Step S1618) The score acquisition unit 331 performs lifestyle information processing. It returns to the higher-level processing. An example of lifestyle information processing will be explained using the flowchart in Figure 24. Lifestyle information processing is the process of using lifestyle information to acquire one or more features related to lifestyle information.

[0358] Next, an example of business input information processing in step S1602 will be explained using the flowchart in Figure 17.

[0359] (Step S1701) The score acquisition unit 331 assigns 1 to counter i.

[0360] (Step S1702) The score acquisition unit 331 determines whether or not the i-th member identifier exists among the member identifiers of the target member. If the i-th member identifier exists, the unit proceeds to step S1703; if the i-th member identifier does not exist, the unit proceeds to step S1712.

[0361] (Step S1703) The score acquisition unit 331 acquires the daily report corresponding to the i-th member identifier from the business input information storage means 3121 for the target period.

[0362] (Step S1704) The score acquisition unit 331 acquires one or more daily report attribute values ​​from the one or more acquired daily reports. The daily report attribute values ​​are, for example, the amount of data for each daily report, the average amount of data for one daily report, information on changes in the amount of data, the number of occurrences of negative words, the occurrence rate of negative words, the number of occurrences of positive words, and the occurrence rate of positive words.

[0363] (Step S1705) The score acquisition unit 331 acquires the document corresponding to the i-th member identifier for the target period from the business input information storage means 3121.

[0364] (Step S1706) The score acquisition unit 331 acquires one or more document attribute values ​​from one or more acquired documents. The document attribute values ​​are, for example, the average data volume of the document for each day it was created, and information on changes in the data volume.

[0365] (Step S1707) The score acquisition unit 331 obtains the program corresponding to the i-th member identifier from the business input information storage means 3121 for the target period. Note that the program is a program created by a software developer.

[0366] (Step S1708) The score acquisition unit 331 acquires one or more program attribute values ​​from the one or more acquired programs. The program attribute values ​​are, for example, the average number of steps in the program created each day, and information on the change in the number of steps.

[0367] (Step S1709) The score acquisition unit 331 acquires the operation log for the target period from the business input information storage means 3121, which is the operation log paired with the i-th member identifier. The operation log is an operation log for a device (e.g., a personal computer) used by the member.

[0368] (Step S1710) The score acquisition unit 331 acquires one or more operation log attribute values ​​from the one or more acquired operation logs. The operation log attribute values ​​are, for example, the average number of operation logs created each day, or information on the change in the number of operation logs.

[0369] (Step S1711) The score acquisition unit 331 increments counter i by 1. Return to step S1702.

[0370] (Step S1712) The score acquisition unit 331 uses the one or more daily report attribute values ​​of all target members obtained in step S1704 to acquire representative values ​​for each type of daily report attribute value. Representative values ​​are, for example, the mean, weighted mean, median, and sum. The score acquisition unit 331 calculates, for example, the representative value of the data volume of all members' daily reports, the representative value of the change information of the data volume of all members, the representative value of the number of occurrences of negative words for all members, the representative value of the occurrence rate of negative words, the representative value of the number of occurrences of positive words, and the representative value of the occurrence rate of positive words. All members are, for example, members identified by a member identifier paired with a specified organization identifier.

[0371] (Step S1713) The score acquisition unit 331 uses the one or more document attribute values ​​of all target members obtained in step S1706 to acquire representative values ​​for each type of document attribute value. The score acquisition unit 331 acquires, for example, representative values ​​of the daily document data volume for all members, representative values ​​of information showing the variation in data volume for each day during the target period for all members, the percentage of all members whose daily document data volume is increasing, and the percentage of all members whose daily document data volume is decreasing.

[0372] (Step S1714) The score acquisition unit 331 uses the one or more program attribute values ​​of all target members obtained in step S1708 to acquire representative values ​​for each type of program attribute value. The score acquisition unit 331 acquires, for example, representative values ​​of the daily number of program steps for all members, representative values ​​of information showing the variation in the number of steps for each day during the target period for all members, the percentage of all members whose data volume of program steps created per day is increasing, and the percentage of all members whose number of program steps created per day is decreasing.

[0373] (Step S1715) The score acquisition unit 331 uses the one or more operation log attribute values ​​for each target member obtained in step S1710 to obtain representative values ​​for each type of operation log attribute value. The score acquisition unit 331 obtains, for example, representative values ​​for the number of operation logs per day for all members, representative values ​​for information showing the variation in the number of operation logs per day for all members during the target period, the percentage of all members whose number of operation logs per day is increasing, and the percentage of all members whose number of operation logs per day is decreasing. The unit returns to the higher-level processing.

[0374] Next, an example of communication information processing in step S1604 will be explained using the flowchart in Figure 18.

[0375] (Step S1801) The score acquisition unit 331 assigns 1 to counter i.

[0376] (Step S1802) The score acquisition unit 331 determines whether or not the i-th member identifier exists among the member identifiers of the target member. If the i-th member identifier exists, the unit proceeds to step S1803; if the i-th member identifier does not exist, the unit proceeds to step S1812.

[0377] (Step S1803) The score acquisition unit 331 acquires chat information for the target period from the communication information storage means 3122, which is the chat information paired with the i-th member identifier.

[0378] (Step S1804) The score acquisition unit 331 acquires one or more chat attribute values ​​from one or more chat information acquired in step S1803. Chat attribute values ​​include, for example, the amount of data in the chat information, the number of occurrences of negative words in the chat information, the occurrence rate of negative words in the chat information, the number of occurrences of positive words in the chat information, and the occurrence rate of positive words in the chat information.

[0379] (Step S1805) The score acquisition unit 331 obtains SNS information for the target period from the communication information storage means 3122, which is the SNS information paired with the i-th member identifier.

[0380] (Step S1806) The score acquisition unit 331 acquires one or more SNS attribute values ​​from one or more SNS information acquired in step S1805. The SNS attribute values ​​are, for example, the amount of data in the SNS information created by the member, the number of occurrences of negative words in the SNS information created by the member, the occurrence rate of negative words in the SNS information created by the member, the number of occurrences of positive words in the SNS information created by the member, and the occurrence rate of positive words in the SNS information created by the member.

[0381] (Step S1807) The score acquisition unit 331 acquires emails from the communication information storage means 3122 that are paired with the i-th member identifier and cover the target period.

[0382] (Step S1808) The score acquisition unit 331 acquires one or more email attribute values ​​from the one or more emails acquired in step S1807. The email attribute values ​​are, for example, the response rate, the number of emails sent by the member, the amount of data in the emails sent by the member, the number of negative words in the emails sent by the member, the rate of negative words in the emails sent by the member, the number of positive words in the emails sent by the member, and the rate of positive words in the emails sent by the member.

[0383] (Step S1809) The score acquisition unit 331 acquires voice text information for the target period from the communication information storage means 3122, which is voice text information paired with the i-th member identifier.

[0384] (Step S1810) The score acquisition unit 331 acquires one or more speech text attribute values ​​from one or more speech text information acquired in step S1809. The speech text attribute values ​​are, for example, the amount of data in the speech text information, the number of occurrences of negative words in the member's speech text information, the occurrence rate of negative words in the member's speech text information, the number of occurrences of positive words in the member's speech text information, and the occurrence rate of positive words in the member's speech text information.

[0385] (Step S1811) The score acquisition unit 331 increments counter i by 1. Return to step S1802.

[0386] (Step S1812) The score acquisition unit 331 uses the one or more chat attribute values ​​of all target members obtained in step S1804 to acquire representative values ​​for each type of chat attribute value. Representative values ​​are, for example, the mean, weighted mean, median, and sum. The score acquisition unit 331 calculates, for example, the representative value of the amount of data in the chat information of all members, the representative value of the number of occurrences of negative words for all members, the representative value of the occurrence rate of negative words, the representative value of the number of occurrences of positive words, and the representative value of the occurrence rate of positive words. All members are, for example, members identified by a member identifier paired with a specified organization identifier.

[0387] (Step S1813) The score acquisition unit 331 uses the one or more SNS attribute values ​​of all target members obtained in step S1806 to acquire representative values ​​for each type of SNS attribute value. The score acquisition unit 331 acquires, for example, representative values ​​of the daily data volume of SNS information for all members, representative values ​​of information showing the variation in the data volume of SNS information for each day during the target period for all members, the percentage of all members whose daily data volume of SNS information is increasing, the percentage of all members whose daily data volume of SNS information is decreasing, representative values ​​of the number of occurrences of negative words in SNS information, representative values ​​of the occurrence rate of negative words in SNS information, representative values ​​of the number of occurrences of positive words in SNS information, and representative values ​​of the occurrence rate of positive words in SNS information.

[0388] (Step S1814) The score acquisition unit 331 uses the one or more email attribute values ​​of all target members obtained in step S1808 to acquire representative values ​​for each type of email attribute value. For example, the score acquisition unit 331 acquires representative values ​​for the response rate of all members, representative values ​​for the number of emails, representative values ​​for the amount of data in emails, representative values ​​for the number of occurrences of negative words in emails, representative values ​​for the occurrence rate of negative words in emails, representative values ​​for the number of occurrences of positive words in emails, and representative values ​​for the occurrence rate of positive words in emails.

[0389] (Step S1815) The score acquisition unit 331 uses the one or more voice text attribute values ​​of all target members obtained in step S1810 to obtain representative values ​​for each type of voice text attribute value. It then returns to the higher-level processing. The score acquisition unit 331 obtains, for example, representative values ​​for the amount of data in the voice text information of all members, representative values ​​for the number of occurrences of negative words in the voice text information of all members, representative values ​​for the occurrence rate of negative words in the voice text information of all members, representative values ​​for the number of occurrences of positive words in the voice text information of all members, and representative values ​​for the occurrence rate of positive words in the voice text information of all members.

[0390] Next, an example of attendance status information processing in step S1606 will be explained using the flowchart in Figure 19.

[0391] (Step S1901) The score acquisition unit 331 assigns 1 to counter i.

[0392] (Step S1902) The score acquisition unit 331 determines whether or not the i-th member identifier exists among the member identifiers of the target member. If the i-th member identifier exists, the unit proceeds to step S1903; if the i-th member identifier does not exist, the unit proceeds to step S1906.

[0393] (Step S1903) The score acquisition unit 331 acquires attendance information for the target period from the attendance status information storage means 3123, which is attendance information paired with the i-th member identifier.

[0394] (Step S1904) The score acquisition unit 331 uses the acquired attendance information to obtain one or more attendance attribute values. Attendance attribute values ​​include, for example, the number of annual leave days for a member, the number of overtime hours for a member, and the number of holiday work days for a member.

[0395] (Step S1905) The score acquisition unit 331 increments counter i by 1. Return to step S1902.

[0396] (Step S1906) The score acquisition unit 331 uses the one or more attendance attribute values ​​for all members obtained in step S1704 to acquire representative values ​​for each type of attendance attribute value. It then returns to the higher-level processing. Representative values ​​include, for example, the mean, weighted mean, median, and sum. The score acquisition unit 331 acquires, for example, representative values ​​for the number of annual holidays for all members, representative values ​​for the number of overtime hours for members, and representative values ​​for the number of holidays worked for members.

[0397] Next, an example of stress information processing in step S1610 will be explained using the flowchart in Figure 20.

[0398] (Step S2001) The score acquisition unit 331 assigns 1 to counter i.

[0399] (Step S2002) The score acquisition unit 331 determines whether or not the i-th member identifier exists among the member identifiers of the target member. If the i-th member identifier exists, the unit proceeds to step S2003; otherwise, the unit proceeds to step S2006.

[0400] (Step S2003) The score acquisition unit 331 acquires one or more responses from the stress information storage means 3125 that are paired with the i-th member identifier, and that represent one or more responses for the target period. The responses are the answers to a questionnaire used to acquire stress information (e.g., stress level).

[0401] (Step S2004) The score acquisition unit 331 acquires stress information using one or more responses obtained in step S2003. The stress information may be one of the responses itself, or it may be a stress level obtained by substituting one or more responses (for example, numerical values) into a calculation formula and performing the calculation, or it may be stress information paired with a vector that most closely approximates a vector having two or more responses as elements. Note that such calculation formulas, or tables having two or more pairs of such vectors and stress information, are stored in the storage unit 31.

[0402] (Step S2005) The score acquisition unit 331 acquires one or more pieces of biometric information (e.g., heart rate, blood pressure) that are paired with the i-th member identifier from the measurement information storage means 3126 for one or more pieces of biometric information for the target period. The response refers to the answer to a questionnaire for acquiring stress information (e.g., stress level).

[0403] (Step S2006) The score acquisition unit 331 acquires stress information using one or more biometric information acquired in step S2003.

[0404] (Step S2007) The score acquisition unit 331 increments counter i by 1. Return to step S2002.

[0405] (Step S2008) The score acquisition unit 331 uses the stress information obtained in Step S2004, based on questionnaires from all target members, to acquire representative values ​​for the first stress information. Representative values ​​include, for example, the mean, weighted mean, median, and sum.

[0406] (Step S2009) The score acquisition unit 331 uses the stress information based on the biological information of all target members, acquired in step S2006, to obtain a representative value of the second stress information. It then returns to the higher-level processing. The representative value may be, for example, the mean, weighted mean, median, or sum.

[0407] Next, an example of measurement information processing in step S1612 will be explained using the flowchart in Figure 21.

[0408] (Step S2101) The score acquisition unit 331 assigns 1 to counter i.

[0409] (Step S2102) The score acquisition unit 331 determines whether or not the i-th member identifier exists among the member identifiers of the target member. If the i-th member identifier exists, the unit proceeds to step S2103; if the i-th member identifier does not exist, the unit proceeds to step S2108.

[0410] (Step S2103) The score acquisition unit 331 acquires one or more heart rates from the measurement information storage means 3126 that are paired with the i-th member identifier, and that represent one or more heart rates during the target period.

[0411] (Step S2104) The score acquisition unit 331 uses one or more heart rates obtained in step S2103 to acquire one or more heart rate attribute values. The heart rate attribute values ​​are the average heart rate, information indicating the variability of the heart rate (e.g., variance), and the maximum heart rate.

[0412] (Step S2105) The score acquisition unit 331 acquires one or more blood pressures for the target period, which are paired with the i-th member identifier, from the measurement information storage means 3126.

[0413] (Step S2106) The score acquisition unit 331 acquires blood pressure attribute values ​​using the blood pressure values ​​of 1 or more obtained in step S2103. The blood pressure attribute values ​​are, for example, the average value of 1 or more blood pressure values, information indicating the variability of blood pressure (for example, variance), and the maximum value of blood pressure. Note that blood pressure refers to systolic blood pressure, diastolic blood pressure, or systolic and diastolic blood pressure.

[0414] (Step S2107) The score acquisition unit 331 increments counter i by 1. Return to step S2102.

[0415] (Step S2108) The score acquisition unit 331 uses the one or more heart rate attribute values ​​of all target members acquired in step S2104 to acquire a representative value for each type of heart rate attribute value. The representative value is, for example, the mean, weighted mean, median, or sum.

[0416] (Step S2109) The score acquisition unit 331 uses the one or more blood pressure attribute values ​​of all target members obtained in step S2106 to obtain a representative value for each type of blood pressure attribute value. It then returns to the higher-level processing. The representative value is, for example, the mean, weighted mean, median, or sum.

[0417] Next, an example of image information processing in step S1614 will be explained using the flowchart in Figure 22.

[0418] (Step S2201) The score acquisition unit 331 assigns 1 to counter i.

[0419] (Step S2202) The score acquisition unit 331 determines whether or not the i-th member identifier exists among the member identifiers of the target member. If the i-th member identifier exists, the unit proceeds to step S2203; if the i-th member identifier does not exist, the unit proceeds to step S2210.

[0420] (Step S2203) The score acquisition unit 331 acquires one or more images from the image storage means 3127 that are paired with the i-th member identifier and cover the target period.

[0421] (Step S2204) The score acquisition unit 331 assigns 1 to counter j.

[0422] (Step S2205) The score acquisition unit 331 determines whether or not the j-th processing unit exists in the acquired image. If the j-th field exists, the process proceeds to step S2206; otherwise, the process proceeds to step S2208. A processing unit is, for example, a field or a file containing one or more fields.

[0423] (Step S2206) The score acquisition unit 331 acquires one or more image attribute values ​​for the j-th processing unit of the image.

[0424] (Step S2207) The score acquisition unit 331 increments counter j by 1. Return to step S2105.

[0425] (Step S2208) The score acquisition unit 331 acquires the image attribute value of the i-th member using each of the one or more image attribute values ​​of the j-th processing unit image. The image attribute values ​​are, for example, a specific facial expression identifier (for example, an identifier for a negative facial expression) and the percentage of negative facial expressions. The identifiers for negative facial expressions are, for example, "anger" and "sadness".

[0426] (Step S2209) The score acquisition unit 331 increments counter i by 1. Return to step S2102.

[0427] (Step S2210) The score acquisition unit 331 uses the one or more image attribute values ​​of all target members obtained in step S2108 to acquire a representative value for each type of image attribute value. It then returns to the higher-level processing. The representative value is, for example, the mean, weighted mean, median, or sum.

[0428] Next, an example of audio information processing in step S1616 will be explained using the flowchart in Figure 23.

[0429] (Step S2301) The score acquisition unit 331 assigns 1 to counter i.

[0430] (Step S2302) The score acquisition unit 331 determines whether or not the i-th member identifier exists among the member identifiers of the target member. If the i-th member identifier exists, the unit proceeds to step S2303; if the i-th member identifier does not exist, the unit proceeds to step S2310.

[0431] (Step S2303) The score acquisition unit 331 acquires one or more voices from the voice storage means 3128 that are paired with the i-th member identifier and cover the target period.

[0432] (Step S2304) The score acquisition unit 331 assigns 1 to counter j.

[0433] (Step S2305) The score acquisition unit 331 determines whether or not the j-th processing unit exists in the acquired audio. If the j-th field exists, the process proceeds to step S2306; otherwise, the process proceeds to step S2308. The processing unit is, for example, audio information or a file representing a unit of time.

[0434] (Step S2306) The score acquisition unit 331 acquires one or more audio attribute values ​​of the audio of the j-th processing unit.

[0435] (Step S2307) The score acquisition unit 331 increments counter j by 1. Return to step S2105.

[0436] (Step S2308) The score acquisition unit 331 acquires the voice attribute value of the i-th member using each voice attribute value of the j-th processing unit of speech for each type of voice attribute value. The voice attribute values ​​are, for example, voice features, the percentage of speaking time in the meeting attended, and emotion identifiers.

[0437] (Step S2309) The score acquisition unit 331 increments counter i by 1. Return to step S2102.

[0438] (Step S2310) The score acquisition unit 331 acquires a representative value of the voice attribute value for each type of voice attribute value, using one or more voice attribute values ​​of all target members acquired in step S2108. It then returns to the higher-level processing. The representative value is, for example, the mean, weighted mean, median, or sum.

[0439] Next, an example of lifestyle information processing in step S1618 will be explained using the flowchart in Figure 24.

[0440] (Step S2401) The score acquisition unit 331 assigns 1 to counter i.

[0441] (Step S2402) The score acquisition unit 331 determines whether or not the i-th member identifier exists among the member identifiers of the target member. If the i-th member identifier exists, the unit proceeds to step S2403; otherwise, the unit proceeds to step S2410.

[0442] (Step S2403) The score acquisition unit 331 obtains the sleep time for each day of the target period from the lifestyle information storage means 3129, which is the sleep time paired with the i-th member identifier.

[0443] (Step S2404) The score acquisition unit 331 acquires one or more sleep attribute values ​​using one or more sleep durations acquired in step S2403. The sleep attribute values ​​include, for example, the average daily sleep duration, information indicating the variability of sleep duration (e.g., variance), the number of days when sleep duration is below a threshold, and the percentage of days when sleep duration is below a threshold.

[0444] (Step S2405) The score acquisition unit 331 obtains the drinking dates for the target period, which are paired with the i-th member identifier, from the lifestyle information storage means 3129.

[0445] (Step S2406) The score acquisition unit 331 acquires one or more drinking attribute values ​​using one or more drinking days acquired in step S2405. The drinking attribute values ​​are, for example, the number of drinking days, the percentage of drinking days, and the maximum value of consecutive drinking days.

[0446] (Step S2407) The score acquisition unit 331 obtains the number of cigarettes smoked, which is paired with the i-th member identifier, from the lifestyle information storage means 3129, and the number of cigarettes smoked each day during the target period.

[0447] (Step S2408) The score acquisition unit 331 uses the number of cigarettes obtained in step S2407 (1 or more) to obtain one or more tobacco attribute values. The tobacco attribute values ​​are, for example, the total number of cigarettes smoked during the period, the average number of cigarettes smoked per day, the number of days when the number of cigarettes smoked is above a threshold, and the percentage of days when the number of cigarettes smoked is above a threshold.

[0448] (Step S2409) The score acquisition unit 331 increments counter i by 1. Return to step S2402.

[0449] (Step S2410) The score acquisition unit 331 uses the one or more sleep attribute values ​​of all target members obtained in step S2404 to acquire representative values ​​for each type of sleep attribute value. Representative values ​​include, for example, the average sleep duration, the average of information indicating the variation in sleep duration, the average number of days with sleep duration below a threshold, and the average percentage of days with sleep duration below a threshold. The score acquisition unit 331 may also acquire, for example, the number or percentage of members whose sleep duration is small enough to satisfy a predetermined condition.

[0450] (Step S2411) The score acquisition unit 331 uses the one or more drinking attribute values ​​of all target members obtained in step S2406 to acquire representative values ​​for each type of drinking attribute value. Representative values ​​are, for example, the average number of drinking days, the average percentage of drinking days, and the average of the maximum number of consecutive drinking days. The score acquisition unit 331 may, for example, acquire the number or percentage of members whose drinking days are large enough to satisfy a predetermined condition.

[0451] (Step S2412) The score acquisition unit 331 uses the one or more tobacco attribute values ​​of all target members obtained in step S2408 to obtain representative values ​​for each type of tobacco attribute value. It then returns to the higher-level processing. The representative values ​​are, for example, the average total number of cigarettes smoked, the average number of cigarettes smoked, the average number of days when the number of cigarettes smoked is above a threshold, and the average percentage of days when the number of cigarettes smoked is above a threshold. The score acquisition unit 331 may, for example, obtain the number or percentage of members whose number of cigarettes smoked is high enough to satisfy a predetermined condition.

[0452] Next, an example of the score acquisition process in step S1405 will be explained using the flowchart in Figure 25.

[0453] (Step S2501) The score acquisition means 3312 acquires prediction information corresponding to the prediction instruction.

[0454] (Step S2502) The score acquisition means 3312 acquires a predicted organization identifier, which is an organization identifier corresponding to the prediction instruction.

[0455] (Step S2503) The score acquisition means 3312 acquires a set of predicted daily information to be used to acquire the predicted score. The set of predicted daily information is one or more daily information items that correspond to the period specified by the prediction inter-information acquired in step S2501 and to the predicted organization identifier acquired in step S2502.

[0456] (Step S2504) The score acquisition means 3312 acquires a feature group using one or more predicted daily information obtained in step S2503. This feature group acquisition process is explained using the flowchart in Figure 16.

[0457] (Step S2505) The score acquisition means 3312 acquires correspondence information to be used for prediction processing from the correspondence information storage unit 314.

[0458] (Step S2506) The score acquisition means 3312 acquires a prediction vector whose elements are each of the features of the feature group acquired in step S2504, and uses this prediction vector and the correspondence information acquired in step S2505 to acquire a prediction score. It then returns to the higher-level processing. An example of the algorithm for acquiring the prediction score is described above.

[0459] Next, an example of the operation of terminal device 4 will be explained using the flowchart in Figure 26.

[0460] (Step S2601) The terminal reception unit 42 determines whether or not it has acquired daily information. If it has acquired daily information, it proceeds to step S2602; if it has not acquired daily information, it proceeds to step S2605.

[0461] (Step S2602) The terminal processing unit 43 obtains the member identifier of the terminal storage unit 41.

[0462] (Step S2603) The terminal processing unit 43 associates the daily information obtained in step S2601 with the member identifier obtained in step S2602, and constitutes the information to be transmitted.

[0463] (Step S2604) The terminal transmission unit 44 transmits the information configured in step S2603 to the score prediction device 3. Return to step S2601.

[0464] (Step S2605) The terminal reception unit 42 determines whether or not it has received a predictive instruction. If it has received a predictive instruction, it proceeds to step S2606; otherwise, it returns to step S2601.

[0465] (Step S2606) The terminal processing unit 43 configures the prediction instruction to be transmitted. The prediction instruction to be transmitted includes, for example, an organization identifier and period information. The organization identifier is the identifier of the organization for which the score is to be predicted. The period information is information that specifies the period of daily information used for score prediction. Default values ​​exist for the organization identifier and period information and may be stored in the terminal storage unit 41.

[0466] (Step S2607) The terminal transmission unit 44 transmits the prediction instruction configured in step S2606 to the score prediction device 3.

[0467] (Step S2608) The terminal receiving unit 45 determines whether or not it has received a predicted score. If it has received a predicted score, it proceeds to step S2609; otherwise, it returns to step S2608.

[0468] (Step S2609) The terminal processing unit 43 uses the prediction score received in step S2608 to configure the prediction score to be output. The terminal output unit 46 outputs the prediction score. The process returns to step S2601.

[0469] Furthermore, as shown in the flowchart in Figure 26, processing is terminated by power-off or processing termination interrupts.

[0470] The following describes specific examples of the operation of the score prediction device 3 in this embodiment. There are eight specific examples, as follows. In each specific example, it is assumed that the daily information necessary for processing is stored in the daily information storage unit 312. In addition, the following specific examples describe how to obtain a predicted score using a learning device, but as mentioned above, the predicted score may also be obtained using other correspondence information such as correspondence tables or calculation formulas.

[0471] (Specific example 1) Specific example 1 involves obtaining a predictive score using the email response rate of team members to emails from management and their superiors.

[0472] The correspondence acquisition means 3311 of the score prediction device 3 acquires two or more member identifiers that are paired with the organization identifier "A" of the target organization. Next, the correspondence acquisition means 3311 acquires emails that are paired with the two or more member identifiers, for each unit period (here, one year) (for example, each year from 2000 to 2019) for the purpose of constituting the learning device, from the communication information storage means 3122, associating them with the member identifiers.

[0473] Then, the correspondence acquisition means 3311, through the process described above, obtains one or more member identifiers of the responding persons (management, superiors, etc.) that correspond to each member identifier from the member information database (database of two or more member information databases) of the organization identifier "A" (not shown).

[0474] Next, the correspondence acquisition means 3311 calculates the response rate for each member identifier and for each unit period. Then, the correspondence acquisition means 3311 obtains a representative value (e.g., the average value) of the response rate for all members for each unit period.

[0475] Next, the correspondence acquisition means 3311 reads the teacher score corresponding to each year from the teacher score storage unit 313. The teacher score is associated with, for example, the identifier of the unit period (in this case, a year) and the organization identifier "A".

[0476] Next, the response acquisition means 3311 constructs two or more training data sets, with the representative value of the response rate as the explanatory variable and the teacher score as the dependent variable.

[0477] The correspondence acquisition means 3311 then provides the two or more training data to a module that performs machine learning learning processing, executes the module, acquires a learner, and stores the learner in the correspondence relationship information storage unit 314 in pairs with the organization identifier "A". The correspondence acquisition means 3311 may also acquire the learner using two or more pieces of information as explanatory variables for each unit period, such as the average response rate of all members, the median response rate of all members, and the variance.

[0478] Next, the score prediction device 3 receives a prediction instruction from the terminal device 4. Then, the score acquisition means 3312 acquires the predicted daily information from the communication information storage means 3122, which is an email that is paired with the above-mentioned organization identifier and is an email sent on or after January 1, 2020.

[0479] Next, the score acquisition means 3312 calculates the response rate for each member identifier using the acquired email. Then, the score acquisition means 3312 obtains a representative value (e.g., the average) of the response rates for all members.

[0480] Next, the score acquisition means 3312 acquires the learner paired with the organization identifier "A" in the correspondence relationship information storage unit 314. Then, the score acquisition means 3312 provides the acquired 2020 response rate and the learner to a machine learning prediction processing module, and obtains a predicted score by executing the module. The score acquisition means 3312 may perform the prediction processing using two or more pieces of information, such as the average response rate of all members, the median response rate of all members, and the variance.

[0481] Next, the score output unit 341 transmits the predicted score to the terminal device 4.

[0482] Then, terminal device 4 receives and outputs the predicted score.

[0483] (Specific example 2) Specific example 2 involves obtaining a predictive score using daily reports. In specific example 2, the unit period is one year.

[0484] The correspondence acquisition means 3311 of the score prediction device 3 acquires two or more member identifiers that are paired with the organization identifier "A" of the target organization. Next, the correspondence acquisition means 3311 acquires daily reports that are paired with the two or more member identifiers, for each year (for example, from 2000 to 2019), from the business input information storage means 3121, associating them with the member identifiers and time identifiers.

[0485] Next, the corresponding acquisition means 3311 acquires one or more daily report attribute values ​​for each member identifier and for each year using each daily report. The daily report attribute values ​​to be acquired include, for example, information on changes in data volume, the occurrence rate of negative words in the daily reports for a predetermined period, and the occurrence rate of positive words in the daily reports for a predetermined period.

[0486] Next, the correspondence acquisition means 3311 acquires, for each year and for each type of daily report attribute value, a representative value (e.g., the average value) of the daily report attribute value in the daily reports of each member identifier for one year. Next, the correspondence acquisition means 3311 acquires, for each year and for each type of daily report attribute value, a representative value (e.g., the average value) of the daily report attribute value for all members. In other words, for each year, the correspondence acquisition means 3311 acquires, for example, the average of the data volume change information, the average value of the occurrence rate of negative words in the daily reports for a predetermined period (in this case, one year), and the average value of the occurrence rate of positive words in the daily reports for a predetermined period, for all members of the organization with organization identifier "A".

[0487] Next, the correspondence acquisition means 3311 acquires a teacher vector for each year, with each acquired daily report attribute value as an element. Next, the correspondence acquisition means 3311 reads the teacher score corresponding to each year from the teacher score storage unit 313. Next, the correspondence acquisition means 3311 acquires teacher data for each year, which includes the teacher vector and the teacher score.

[0488] Next, the correspondence acquisition means 3311 provides the acquired training data to a module that performs machine learning learning processing, and by executing the module, it acquires a learner, which is then stored in the correspondence relationship information storage unit 314 in pairs with the organization identifier "A".

[0489] Next, the score prediction device 3 receives a prediction instruction from the terminal device 4. Then, the score acquisition means 3312 of the score prediction device 3 acquires the predicted daily information, which is a daily report corresponding to the organization identifier "A" mentioned above, and is a daily report from January 1, 2020 onwards, from the business input information storage means 3121.

[0490] Next, the score acquisition means 3312 uses the acquired daily reports for each member identifier to obtain two or more daily report attribute values ​​for each member identifier. Then, the score acquisition means 3312 obtains representative values ​​(e.g., average values) for each of the two or more daily report attribute values ​​for all members, and constructs a prediction vector using these representative values ​​as elements. The prediction vector is, for example, a vector whose elements are the average value of the change in data volume information, the occurrence rate of negative words, and the occurrence rate of positive words.

[0491] Next, the score acquisition means 3312 acquires the learner paired with the organization identifier "A" in the correspondence relationship information storage unit 314. Then, the score acquisition means 3312 provides the acquired 2020 prediction vector and the learner to a machine learning prediction processing module, and by executing the module, obtains a prediction score.

[0492] Next, the score output unit 341 transmits the predicted score to the terminal device 4.

[0493] Then, terminal device 4 receives and outputs the predicted score.

[0494] (Specific example 3) Specific example 3 involves obtaining a predictive score using overtime hours from attendance data. In specific example 3, the unit period is one month.

[0495] The correspondence acquisition means 3311 of the score prediction device 3 acquires two or more member identifiers that are paired with the organization identifier "A" of the target organization. Next, the correspondence acquisition means 3311 acquires attendance information that is paired with the two or more member identifiers, and acquires attendance information for each year (for example, from 2000 to 2019) from the attendance status information storage means 3123, associating the member identifier with the time identifier.

[0496] Next, the correspondence acquisition means 3311 calculates the average monthly overtime hours for each member identifier and each year, using the attendance information for each member identifier and each year. Then, the correspondence acquisition means 3311 obtains the average and variance of overtime hours for all members of organization "A" for each year.

[0497] Next, the correspondence acquisition means 3311 acquires a teacher vector for each year, whose elements are the average and variance of the overtime hours of all acquired members. Next, the correspondence acquisition means 3311 reads the teacher score corresponding to each year from the teacher score storage unit 313. Next, the correspondence acquisition means 3311 acquires teacher data for each year, which includes the teacher vector and the teacher score.

[0498] Next, the correspondence acquisition means 3311 provides the acquired training data to a module that performs machine learning learning processing, and by executing the module, it acquires a learner, which is then stored in the correspondence relationship information storage unit 314 in pairs with the organization identifier "A".

[0499] Next, the score prediction device 3 receives a prediction instruction from the terminal device 4. Then, the score acquisition means 3312 of the score prediction device 3 acquires the predicted daily information, which is attendance information from January 1, 2020 onwards, and is paired with the above-mentioned organization identifier "A", from the attendance status information storage means 3123.

[0500] Next, the score acquisition means 3312 uses the attendance information acquired for each member identifier to calculate the average monthly overtime hours for each member identifier. Next, the score acquisition means 3312 obtains the average and variance of overtime hours for all members. Next, the score acquisition means 3312 constructs a prediction vector using the average and variance of overtime hours for all members as its elements.

[0501] Next, the score acquisition means 3312 acquires the learner paired with the organization identifier "A" in the correspondence relationship information storage unit 314. Then, the score acquisition means 3312 provides the acquired 2020 prediction vector and the learner to a machine learning prediction processing module, and by executing the module, obtains a prediction score.

[0502] Next, the score output unit 341 transmits the predicted score to the terminal device 4.

[0503] Then, terminal device 4 receives and outputs the predicted score.

[0504] (Specific example 4) This example describes a case where a predictive score is obtained using stress information and measurement information. In this specific example, the unit period is one year. In this specific example, stress information (e.g., stress level) is obtained by the score acquisition unit 331 using the method described above, and is stored in the stress information storage means 3125 in association with the member identifier and the time identifier. Furthermore, the score acquisition unit 331 obtains attribute values ​​(e.g., mean, variance, etc.) of the stress information of all members in each year, and stores them in the stress information storage means 3125 in association with the organization identifier "A" and the identifier for each year.

[0505] Furthermore, measurement information (heart rate, blood pressure) is received by the score prediction device 3 from a wearable terminal (not shown) worn by the member, and stored in the measurement information storage means 3126 in association with the member identifier and the time identifier. In addition, the score acquisition unit 331 acquires representative values ​​of heart rate and blood pressure for each member identifier and each year, and also acquires representative values ​​of heart rate and blood pressure for all members each year, and stores them in the measurement information storage means 3126 in pairs with the organization identifier "A" and the identifier for each year.

[0506] In this situation, the correspondence acquisition means 3311 of the score prediction device 3 acquires a teacher vector for each year, whose elements are attribute values ​​of stress information for each year, representative values ​​of heart rate, and representative values ​​of blood pressure, which are paired with the organizational identifier "A" of the target organization. Next, the correspondence acquisition means 3311 reads the teacher score corresponding to each year from the teacher score storage unit 313. Next, the correspondence acquisition means 3311 acquires teacher data for each year, which has the teacher vector and the teacher score.

[0507] Next, the correspondence acquisition means 3311 provides the acquired training data to a module that performs machine learning learning processing, and by executing the module, it acquires a learner, which is then stored in the correspondence relationship information storage unit 314 in pairs with the organization identifier "A".

[0508] Next, the score prediction device 3 receives a prediction instruction from the terminal device 4. Then, the score acquisition means 3312 of the score prediction device 3 acquires stress information corresponding to the organization identifier "A" from the stress information storage means 3125, specifically stress information from January 1, 2020 onwards. The score acquisition means 3312 also acquires attribute values ​​of the stress information (e.g., mean, variance, etc.) from the acquired stress information.

[0509] Furthermore, the score acquisition means 3312 acquires measurement information (heart rate, blood pressure) from the measurement information storage means 3126 that is paired with the organization identifier "A" from January 1, 2020 onwards. Next, the score acquisition means 3312 acquires representative values ​​for each of the acquired measurement information.

[0510] Next, the score acquisition means 3312 constructs a prediction vector whose elements are the attribute values ​​of the stress information and the representative values ​​of each measurement information.

[0511] Next, the score acquisition means 3312 acquires the learner paired with the organization identifier "A" in the correspondence relationship information storage unit 314. Then, the score acquisition means 3312 provides the acquired 2020 prediction vector and the learner to a machine learning prediction processing module, and by executing the module, obtains a prediction score.

[0512] Next, the score output unit 341 transmits the predicted score to the terminal device 4.

[0513] Then, terminal device 4 receives and outputs the predicted score.

[0514] (Specific example 5) Specific example 5 involves obtaining a predictive score using communication information. In specific example 5, the unit period is one month.

[0515] The correspondence acquisition means 3311 of the score prediction device 3 acquires two or more member identifiers that are paired with the organization identifier "A" of the target organization. Next, the correspondence acquisition means 3311 acquires communication information paired with the two or more member identifiers from the communication information storage means 3122, associating it with the time information. The communication information is, for example, one or more types of information from chat information, SNS information, email, and text information.

[0516] Next, the correspondence acquisition means 3311 acquires one or more types of communication attribute values ​​for each member identifier and for each month using communication information. The communication attribute values ​​to be acquired are, for example, the number of occurrences of negative words, the occurrence rate of negative words, the number of occurrences of positive words, and the occurrence rate of positive words. Next, the correspondence acquisition means 3311 acquires representative values ​​(for example, average values) of the communication attribute values ​​for all members on a monthly basis.

[0517] Next, the correspondence acquisition means 3311 acquires a teacher vector for each month, with each acquired communication attribute value as an element. Next, the correspondence acquisition means 3311 reads the teacher score corresponding to each month from the teacher score storage unit 313. Next, the correspondence acquisition means 3311 acquires teacher data for each month, which includes the teacher vector and the teacher score. In this case, it is preferable that the teacher score is stored in the teacher score storage unit 313 in association with the identifier of each month, but for example, only one teacher score may be stored in the teacher score storage unit 313 for each year. If only one teacher score is stored in the teacher score storage unit 313 for each year, the teacher score for each month of a given year will be the same teacher score.

[0518] Next, the correspondence acquisition means 3311 provides the acquired large number of training data to a module that performs machine learning learning processing, and by executing the module, it acquires a learner, and stores the learner in the correspondence relationship information storage unit 314 in pairs with the organization identifier "A".

[0519] Next, the score prediction device 3 receives a prediction instruction from the terminal device 4. Then, the score acquisition means 3312 of the score prediction device 3 acquires the communication information for May 2020 from the communication information storage means 3122, which is the communication information paired with the organization identifier "A" mentioned above.

[0520] Next, the score acquisition means 3312 uses the acquired communication information to obtain communication attribute values ​​for each member identifier. Then, the score acquisition means 3312 obtains representative values ​​(e.g., average values) for each communication attribute value of all members and constructs a prediction vector using these two or more representative values ​​of each communication attribute value as elements.

[0521] Next, the score acquisition means 3312 acquires the learner paired with the organization identifier "A" in the correspondence relationship information storage unit 314. Then, the score acquisition means 3312 provides the acquired prediction vector for May 2020 and the learner to a machine learning prediction processing module, and by executing the module, obtains a prediction score.

[0522] Next, the score output unit 341 transmits the predicted score to the terminal device 4.

[0523] Then, terminal device 4 receives and outputs the predicted score.

[0524] (Specific example 6) Specific example 6 is a case where a prediction score is obtained using audio information from a video call. The audio storage means 3128 stores a large number of audio files, each corresponding to an organization identifier "A" and time information. In specific example 6, the unit period is one year.

[0525] In this situation, the correspondence acquisition means 3311 of the score prediction device 3 acquires voice information that is paired with the organization identifier "A" of the target organization on a yearly basis.

[0526] Next, the correspondence acquisition means 3311 performs spectral analysis on each acquired audio information for each year to obtain two or more feature quantities of the audio. The correspondence acquisition means 3311 also obtains representative values ​​of each type of feature quantity from the two or more feature quantities of the audio for each year. Next, the correspondence acquisition means 3311 obtains a teacher vector for each year, with the representative values ​​of each type of feature quantity as its elements. Next, the correspondence acquisition means 3311 reads the teacher score corresponding to each year from the teacher score storage unit 313. Next, the correspondence acquisition means 3311 obtains teacher data for each year, which includes the teacher vector and the teacher score.

[0527] Next, the correspondence acquisition means 3311 provides the acquired training data to a module that performs machine learning learning processing, and by executing the module, it acquires a learner, which is then stored in the correspondence relationship information storage unit 314 in pairs with the organization identifier "A".

[0528] Next, the score prediction device 3 receives a prediction instruction from the terminal device 4. Then, the score acquisition means 3312 of the score prediction device 3 acquires voice information from the voice storage means 3128 that corresponds to the organization identifier "A" mentioned above, and is voice information from January 1, 2020 onwards.

[0529] Next, the correspondence acquisition means 3311 performs spectral analysis on each audio information acquired from January 1, 2020 onwards, and obtains two or more feature quantities of the audio. The correspondence acquisition means 3311 also obtains representative values ​​for each type of feature quantity from the two or more feature quantities of the audio. Next, the correspondence acquisition means 3311 obtains a prediction vector whose elements are the representative values ​​of each type of feature quantity.

[0530] Next, the score acquisition means 3312 acquires the learner paired with the organization identifier "A" in the correspondence relationship information storage unit 314. Then, the score acquisition means 3312 provides the acquired 2020 prediction vector and the learner to a machine learning prediction processing module, and by executing the module, obtains a prediction score.

[0531] Next, the score output unit 341 transmits the predicted score to the terminal device 4.

[0532] Then, terminal device 4 receives and outputs the predicted score.

[0533] (Specific example 7) This example involves performing facial expression analysis on video call images and obtaining a predictive score from specific facial expressions. The image storage means 3127 stores numerous images (video files) associated with the organization identifier "A" and time information. In this specific example 7, the unit period is one year.

[0534] In this situation, the correspondence acquisition means 3311 of the score prediction device 3 acquires an image paired with the organizational identifier "A" of the target organization for each year. Next, the correspondence acquisition means 3311 performs facial expression analysis on each image and acquires a facial expression identifier (for example, any of joy, anger, sadness, or other emotions, or normal). Next, the correspondence acquisition means 3311 acquires the percentage of negative facial expressions ("anger" or "sadness") for each year.

[0535] Next, the correspondence acquisition means 3311 acquires training data for each year, with the proportion of negative facial expressions as the explanatory variable and the teacher score for each year as the dependent variable. The teacher score for each year is stored in the teacher score storage unit 313.

[0536] Next, the correspondence acquisition means 3311 provides the acquired training data to a module that performs machine learning learning processing, and by executing the module, it acquires a learner, which is then stored in the correspondence relationship information storage unit 314 in pairs with the organization identifier "A".

[0537] Next, the score prediction device 3 receives a prediction instruction from the terminal device 4. Then, the score acquisition means 3312 of the score prediction device 3 acquires an image from the audio storage means 3128 that is paired with the organization identifier "A" mentioned above, and is an image from January 1, 2020 or later.

[0538] Next, the corresponding acquisition means 3311 performs facial expression analysis on each image acquired from January 1, 2020 onwards to obtain a facial expression identifier. Then, the corresponding acquisition means 3311 obtains the percentage of negative facial expressions ("anger" and "sadness") from January 1, 2020 onwards.

[0539] Next, the score acquisition means 3312 acquires the learner paired with the organization identifier "A" in the correspondence relationship information storage unit 314. Then, the score acquisition means 3312 provides the acquired percentage of negative facial expressions for 2020 and the learner to a machine learning prediction processing module, and by executing the module, obtains a predicted score.

[0540] Next, the score output unit 341 transmits the predicted score to the terminal device 4.

[0541] Then, terminal device 4 receives and outputs the predicted score.

[0542] (Specific example 8) Specific example 8 is a case where a predictive score is obtained using daily information from other organizations that match the criteria of the organization identifier of the relevant organization. In specific example 8, the unit period is one year.

[0543] The score prediction device 3 receives a prediction instruction from the terminal device 4 that includes organizational conditions with industry identifier "trading company" and size identifier "large company," as well as the organizational identifier "A" of the organization to be predicted.

[0544] Next, the corresponding acquisition means 3311 acquires one or more types of daily information corresponding to the industry identifier "trading company" and the size identifier "large company" from the daily information storage unit 312, for each organization identifier and for each year.

[0545] Next, the correspondence acquisition means 3311 constructs a teacher vector using the acquired daily information for each organization identifier and each year. The correspondence acquisition means 3311 also reads the teacher score corresponding to each organization identifier and each year from the teacher score storage unit 313.

[0546] Next, the correspondence acquisition means 3311 acquires training data, which includes a training vector and a training score, for each organization identifier and each year.

[0547] Next, the correspondence acquisition means 3311 provides the acquired training data to a module that performs machine learning learning processing, and by executing the module, it acquires a learner, which is then stored in the correspondence relationship information storage unit 314 in pairs with organizational conditions (in this case, the industry identifier "trading company" and the size identifier "large company").

[0548] Next, the score acquisition means 3312 pairs the organization identifier "A" included in the received prediction instruction and acquires one or more types of daily information for the prediction period (for example, from January 1, 2020 onwards) from the daily information storage unit 312.

[0549] Next, the score acquisition means 3312 constructs a prediction vector for 2020 using the acquired daily information.

[0550] Next, the score acquisition means 3312 acquires the learner from the correspondence relationship information storage unit 314. Then, the score acquisition means 3312 provides the acquired 2020 prediction vector and the learner to a machine learning prediction processing module, and by executing the module, obtains a prediction score.

[0551] Next, the score output unit 341 transmits the predicted score to the terminal device 4.

[0552] Then, terminal device 4 receives and outputs the predicted score.

[0553] As described above, according to this embodiment, it is possible to predict an organization's score using the daily information of its members.

[0554] Furthermore, according to this embodiment, an organization's score can be predicted using one or more types of information from among business information, input information, communication information, attendance status information, work result information, health information, biometric information, stress information, measurement information, voice, images, lifestyle information, etc.

[0555] Furthermore, according to this embodiment, an organization's score can be predicted without conducting a survey, using scores based on past surveys and everyday information.

[0556] Furthermore, according to this embodiment, it is possible to predict an organization's score using machine learning techniques, data mining techniques, etc.

[0557] In this embodiment, the type of everyday information used is not limited. However, it is preferable to use two or more types of everyday information in this embodiment.

[0558] Furthermore, the processing in this embodiment may be implemented in software. This software may be distributed by software download or the like. Alternatively, this software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software that implements the score prediction device 3 in this embodiment is the following program. In other words, this program is a program that causes a computer to function as a score acquisition unit that acquires a predicted score, which is the score corresponding to the one or more predicted daily information, using a teacher score, which is the score of an organization obtained using a plurality of organization response information indicating the answers to questions for each of two or more members of the organization, and one or more teacher daily information, which is daily information that can be obtained in the daily lives of each of the two or more members, and one or more predicted daily information, which is daily information of each of the two or more members of the organization, and daily information that is the score corresponding to the one or more predicted daily information, and a score output unit that outputs the predicted score.

[0559] Figure 27 also shows the external appearance of a computer that executes the program described herein to realize the score prediction device 3, etc., of the various embodiments described above. The embodiments described above can be realized with computer hardware and computer programs executed thereon. Figure 27 is an overview of this computer system 300, and Figure 28 is a block diagram of the system 300.

[0560] In Figure 27, the computer system 300 includes a computer 301 with a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0561] In Figure 28, the computer 301 includes, in addition to the CD-ROM drive 3012, an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012, a ROM 3015 for storing programs such as boot-up programs, a RAM 3016 connected to the MPU 3013 for temporarily storing instructions for application programs and providing temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Although not shown here, the computer 301 may further include a network card for providing connectivity to a LAN.

[0562] The program that causes the computer system 300 to execute functions such as the score prediction device 3 of the above-described embodiment may be stored on the CD-ROM 3101, inserted into the CD-ROM drive 3012, and then transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into the RAM 3016 during execution. The program may also be loaded directly from the CD-ROM 3101 or the network.

[0563] The program does not necessarily have to include an operating system (OS) or third-party program that causes the computer 301 to execute functions such as the score prediction device 3 of the above-described embodiment. The program only needs to include the instruction portion that calls appropriate functions (modules) in a controlled manner to obtain the desired result. How the computer system 300 operates is well known, so a detailed explanation is omitted.

[0564] In the above program, steps such as sending information and receiving information do not include hardware-based processing, such as processing performed by a modem or interface card in the transmission step (processing that can only be performed by hardware).

[0565] Furthermore, the computer running the above program may be a single computer or multiple computers. In other words, it may perform centralized processing or distributed processing.

[0566] Furthermore, it goes without saying that in each of the above embodiments, two or more communication means present in a single device may be physically implemented in a single medium.

[0567] Furthermore, in each of the above embodiments, each process may be implemented by centralized processing by a single device, or by distributed processing by multiple devices.

[0568] It goes without saying that the present invention is not limited to the embodiments described above, and various modifications are possible, all of which are also included within the scope of the present invention. [Industrial applicability]

[0569] As described above, the score prediction device according to the present invention has the effect of being able to predict an organization's score using the daily information of the organization's members, and is useful as a score prediction device, etc. [Explanation of Symbols]

[0570] 3. Score Prediction Device 4 Terminal devices 31 Storage section 32 Reception Department 33 Processing Unit 34 Output section 41 Terminal storage section 42 Terminal reception area 43 Terminal Processing Unit 44 Terminal transmission unit 45 Terminal receiving unit 46 Terminal output section 311 Organizational Information Storage Unit 312 Daily Information Storage Unit 313 Teacher Score Storage Unit 314 Correspondence information storage unit 331 Score Acquisition Section 341 Score Output Section 3121 Business input information storage means 3122 Communication information storage means 3123 Attendance status information storage means 3124 Business result information storage means 3125 Stress information storage means 3126 Measurement information storage means 3127 Image storage means 3128 Audio storage means 3129 Means for storing personal information 3311 Means of obtaining the corresponding information 3312 Methods for obtaining scores

Claims

1. A score acquisition unit acquires a teacher score, which is the score of an organization obtained using multiple organizational response information showing the answers to questions for each of two or more members of the organization; a correspondence between the teacher score and one or more teacher daily information, which is daily information for the period corresponding to the question or the answer and can be obtained in the daily lives of each of the two or more members; and one or more predicted daily information, which is daily information for each of the two or more members of the organization, for a period beyond the aforementioned period and for the period targeted for prediction of the organization's score, and acquires a predicted score, which is the score corresponding to the one or more predicted daily information. A score prediction device comprising a score output unit that outputs the aforementioned predicted score.

2. Each of the above one or more pieces of teacher daily information includes teacher work information relating to the duties performed by the member, Each of the above one or more predictive daily information items includes predictive work information related to the work performed by the member, The aforementioned score acquisition unit, The score prediction device according to claim 1, which obtains the predicted score using the correspondence between one or more teacher daily information, including the teacher work information, and the teacher score, and one or more predicted daily information, including the predicted work information.

3. The aforementioned teacher work information includes teacher input information entered by the aforementioned member, The aforementioned forecast business information includes forecast input information entered by the member, The aforementioned score acquisition unit, The score prediction device according to claim 2, which obtains the predicted score using the correspondence between one or more teacher daily information including the teacher input information and the teacher score, and one or more predicted daily information including the predicted input information.

4. The teacher input information includes teacher work input information relating to input for the performance of the member's own duties, The aforementioned predictive input information includes predictive business input information relating to input for the performance of the member's own duties, The aforementioned score acquisition unit, The score prediction device according to claim 3, which obtains the predicted score using the correspondence between one or more teacher daily information, including the teacher work input information, and the teacher score, and one or more predicted daily information, including the prediction work input information.

5. The teacher input information includes teacher communication information relating to communication between the two or more members, The aforementioned predictive input information includes predictive communication information relating to communication between the two or more members, The aforementioned score acquisition unit, The score prediction device according to claim 3, which obtains the predicted score using the correspondence between one or more teacher daily information pieces including the teacher communication information and the teacher score, and one or more predicted daily information pieces including the predicted communication information.

6. The aforementioned score acquisition unit, A score prediction device according to claim 3, which acquires one or more types of information from among data volume information that specifies the amount of data of the teacher input information, input frequency information that specifies the frequency of input of the teacher input information, analysis information that shows the analysis results of the teacher input information, and timing information that specifies the timing of input of the teacher input information, and acquires one or more types of information from among data volume information of the prediction input information, input frequency information of the prediction input information, analysis information of the prediction input information, and timing information of the prediction input information, acquires correspondence relationship information that specifies the correspondence relationship between one or more teacher features including one or more types of information acquired from the teacher input information and the teacher score, and uses the correspondence relationship information and one or more prediction features including one or more types of information acquired from the prediction input information to acquire the prediction score.

7. The aforementioned teacher work information includes teacher attendance status information relating to the attendance of the members, The aforementioned forecast business information includes forecast attendance status information regarding the attendance of the members, The aforementioned score acquisition unit, The score prediction device according to claim 2, which obtains the predicted score using the correspondence between one or more teacher daily information, including the teacher attendance status information, and the teacher score, and one or more predicted daily information, including the predicted attendance status information.

8. The aforementioned teacher work information includes teacher work result information relating to the results of the member's work performance, The aforementioned forecast business information includes forecast business result information relating to the results of the members' work performance, The aforementioned score acquisition unit, The score prediction device according to claim 2, which obtains the predicted score using the correspondence between one or more teacher daily information, including the teacher work result information, and the teacher score, and one or more predicted daily information, including the predicted work result information.

9. Each of the above one or more pieces of teacher daily information includes teacher health information relating to the health of the member, Each of the above one or more predictive daily information items includes predictive health information relating to the health of the member. The aforementioned score acquisition unit, The score prediction device according to claim 1, which obtains the predicted score using the correspondence between one or more teacher daily information, including the teacher health information, and the teacher score, and one or more predicted daily information, including the predicted health information.

10. The teacher health information includes teacher biometric information relating to the biological characteristics of the member, The aforementioned predicted health information includes predicted biological information relating to the biological body of the member, The aforementioned score acquisition unit, The score prediction device according to claim 9, which obtains the predicted score using the correspondence between one or more teacher daily information including the teacher biometric information and the teacher score, and one or more predicted daily information including the predicted biometric information.

11. The teacher bioinformation includes teacher stress information relating to the stress of the member, The predicted biological information includes predicted stress information relating to the stress of the member, The aforementioned score acquisition unit, The score prediction device according to claim 10, which obtains the predicted score using the correspondence between one or more teacher daily information including the teacher stress information and the teacher score, and one or more predicted daily information including the predicted stress information.

12. The aforementioned teacher biometric information includes teacher measurement information, which is the measurement result of the member's body. The predicted biological information includes predicted measurement information obtained from the biological body of the member, The aforementioned score acquisition unit, A score prediction device according to claim 10 or 11, which obtains the predicted score using the correspondence between one or more teacher daily information including the teacher measurement information and the teacher score, and one or more predicted daily information including the predicted measurement information.

13. The aforementioned teacher biometric information includes teacher biometric feature information which is an image taken of the member, or feature quantities of an image taken of the member, or sound emitted by the member, or feature quantities of sound emitted by the member. The predicted biometric information includes predicted biometric feature information which is an image taken of the member, or feature quantities of an image taken of the member, or sound emitted by the member, or feature quantities of sound emitted by the member. The aforementioned score acquisition unit, A score prediction device according to any one of claims 10 to 12, which obtains the predicted score using the correspondence between one or more teacher daily information including the teacher bio-characteristic information and the teacher score, and one or more predicted daily information including the predicted bio-characteristic information.

14. The aforementioned teacher health information includes teacher lifestyle information relating to the lives of the members, The aforementioned predictive health information includes predictive lifestyle information relating to the lives of the members, The aforementioned score acquisition unit, A score prediction device according to any one of claims 9 to 13, which obtains the predicted score using the correspondence between one or more pieces of teacher daily information, including the teacher lifestyle information, and the teacher score, and one or more pieces of predicted daily information, including the predicted lifestyle information.

15. The aforementioned score acquisition unit, Correspondence acquisition means for acquiring correspondence relationship information that identifies the correspondence between the one or more teacher daily information items and the teacher score, A score prediction device according to any one of claims 1 to 14, comprising a score acquisition means for acquiring the predicted score using the correspondence relationship information and the one or more predicted daily information.

16. The aforementioned one or more teacher daily information items and the aforementioned teacher score correspond to one or more organizational attribute values. The aforementioned correspondence acquisition means is For each organizational condition configured using the one or more organizational attribute values, correspondence relationship information is obtained that identifies the correspondence between the one or more teacher daily information and the teacher score. The aforementioned score acquisition means is The score prediction device according to claim 15, which obtains the prediction score using the correspondence relationship information corresponding to organizational conditions that the target organization for prediction matches, and the one or more prediction daily information.

17. The aforementioned correspondence acquisition means is Using the one or more teacher daily information items and the teacher score, a learning process is performed using a machine learning algorithm to obtain correspondence relationship information, which is a learning model in which the one or more teacher daily information items are used as explanatory variables and the teacher score is used as the target variable. The aforementioned score acquisition means is A score prediction device according to claim 15 or 16, which uses the learning model and the one or more predictive daily information to perform prediction processing using a machine learning algorithm and obtains the predicted score.

18. The aforementioned correspondence acquisition means is Using the aforementioned one or more pieces of teacher daily information, a teacher vector is obtained, which is a vector having two or more elements, and correspondence relationship information is obtained, which is a correspondence table having one or more pieces of correspondence information, which is a pair of the teacher vector and the teacher score. The aforementioned score acquisition means is A score prediction device according to claim 15 or 16, which uses one or more predictive daily information items to obtain a prediction vector having two or more elements, applies the prediction vector to the correspondence table, and obtains the prediction score.

19. The aforementioned correspondence acquisition means is Using the aforementioned one or more pieces of teacher daily information, a teacher vector having two or more elements is obtained, and correspondence relationship information is obtained, which is a calculation formula that takes each element of the teacher vector as input and outputs the teacher score. The aforementioned score acquisition means is A score prediction device according to claim 15 or 16, which uses one or more predictive daily information items to obtain a prediction vector having two or more elements, provides each element of the prediction vector to the calculation formula, executes the calculation formula, and obtains the prediction score.

20. A score prediction method having all the processing performed by the score prediction device according to any one of claims 1 to 19.

21. Computers, A program for functioning as a score prediction device according to any one of claims 1 to 19.

Images