Information processing device, information processing method, and program

Abstract

To solve the problem that conventionally, it is not possible to appropriately propose information that is transmitted to members of an organization.SOLUTION: It is possible to appropriately propose information transmitted to members of an organization by an information processing device 1. The information processing device 1 comprises: an information reception unit 121 for receiving a target organization answer including two or more member answers to a questionnaire presented to target members of a target organization; an information acquisition unit 133 for acquiring learning information based on two or more teaching data including an organization answer which is a set of member answers that are answers to a questionnaire presented to two or more members of an organization or a statistical result from statistical processing of the organization answer and new transmission information having been newly transmitted after answers to the questionnaire; and transmission information pertaining to information transmitted to the target members by using the target organization answer; and an information output unit 141 for outputting the transmission information.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an information processing device or the like that proposes information to be transmitted to members of an organization. [Background technology]

[0002] Conventionally, there has been an improvement support system that generates job satisfaction evaluation information based on survey results or reports from employees at production sites and supports the improvement of job satisfaction for employees engaged in the work (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2022-47836 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, it has not been possible to appropriately suggest information to be transmitted to members of an organization. [Means for solving the problem]

[0005] The information processing device of the first invention is an information processing device that includes an information receiving unit that receives a target organization response having two or more member responses that are responses to a questionnaire to target members belonging to a target organization, learning information based on two or more teacher data that includes organization responses that are a collection of member responses that are responses to a questionnaire to two or more members belonging to an organization or statistical results that are the result of statistical processing of the organization responses, and new transmission information regarding information newly transmitted after the responses to the questionnaire, an information acquisition unit that acquires transmission information regarding information to be transmitted to the target members using the target organization responses, and an information output unit that outputs the transmission information.

[0006] With this configuration, it is possible to appropriately propose information to be transmitted to members of an organization.

[0007] In addition, the information processing device of the second invention, compared to the first invention, further includes an organizational information storage unit in which organizational information including outgoing information regarding information previously sent to target members is stored in correspondence with an organizational identifier that identifies the target organization, the teacher data has communication information including outgoing information regarding information previously sent to two or more members belonging to an organization, and the information acquisition unit is an information processing device that acquires the outgoing information using the learning information, the target organization responses, and the communication information including outgoing information regarding information previously sent to target members.

[0008] With this configuration, it is possible to appropriately propose information to be transmitted to members of an organization.

[0009] In addition, the information processing device of the third invention is an information processing device in which, compared to the second invention, the organizational information has reaction information regarding the reactions of target members to past communications, and the communication information has reaction information regarding the reactions of members to past communications.

[0010] With this configuration, it is possible to appropriately propose information to be transmitted to members of an organization by using reaction information as well.

[0011] In addition, the information processing device of the fourth invention is an information processing device that, with respect to any one of the first to third inventions, further comprises a response storage unit in which organizational responses having two or more member responses which are responses to a questionnaire from each member belonging to an organization are stored, and a statistical processing unit that statistically processes the organizational responses and obtains the statistical results, wherein the teacher data has statistical results which are the result of statistically processing the organizational responses of an organization and newly transmitted information, and the information acquisition unit is an information processing device that acquires the transmitted information using the statistical results which are the result of statistically processing the target organizational responses and learning information.

[0012] With this configuration, it is possible to appropriately propose information to be sent to members of an organization by using the statistical results of the response set as well.

[0013] Furthermore, compared to the first invention, the information processing device of the fifth invention further includes an organization information storage unit in which business information related to an organization's business, or one or more pieces of organization information including one or more organization attribute values ​​which are attribute values ​​of the organization, are stored, the teacher data has business information of an organization or one or more organization attribute values ​​of an organization, and the information acquisition unit is an information processing device that acquires outgoing information using the business information of a target organization or the one or more organization attribute values ​​of the target organization, the target organization's response, and learning information.

[0014] With this configuration, it is possible to appropriately propose information to be transmitted to members of an organization by using business information as well.

[0015] In addition, the information processing device of the sixth invention is an information processing device according to any one of the first to fifth inventions, wherein the learning information is a learning model obtained by performing a machine learning learning process using two or more teacher data, and the information acquisition unit is an information processing device that performs a machine learning prediction process using the target organization's responses or statistical results and the learning model, and acquires the transmission information.

[0016] With this configuration, it is possible to use a machine learning algorithm to appropriately suggest information to be disseminated to members of an organization.

[0017] In addition, the information processing device of the seventh invention is an information processing device according to any one of the first to fifth inventions, in which the information acquisition unit provides two or more teacher data to a generative AI module, and provides target organization responses or statistical results to the generative AI module to acquire outgoing information.

[0018] With this configuration, the generative AI module can be used to appropriately suggest information to be disseminated to members of an organization.

[0019] Furthermore, in the information processing device of the eighth invention, compared to the seventh invention, the transmission information is a transmission identifier that identifies the transmission content or title information that is the title of the transmission content, the information acquisition unit provides the title information or title information that pairs with the transmission identifier to a generative AI module to acquire transmission content information that is information indicating the transmission content, and the information output unit is an information processing device that transmits the transmission content information instead of the transmission information.

[0020] With this configuration, it is possible to appropriately propose information to be transmitted to members of an organization.

[0021] In addition, the information processing device of the ninth invention is an information processing device according to any one of the first to fifth inventions, wherein the teacher data is a vector having as elements two or more pieces of information contained in the organizational responses or the statistical results, the learning information is a correspondence table having two or more pieces of correspondence information indicating the correspondence between the vector and the newly transmitted information, and the information acquisition unit determines from the correspondence table a vector that is closest to a vector having as elements two or more pieces of information contained in the target organizational responses or the statistical results that are the result of statistical processing of the target organizational responses accepted by the information receiving unit, and acquires the newly transmitted information that pairs with the vector.

[0022] With this configuration, it is possible to use the correspondence table to appropriately suggest information to be transmitted to members of an organization.

[0023] Furthermore, the information processing device of the tenth invention is an information processing device in which, compared to any one of the first to ninth inventions, the two or more pieces of teacher data have one or more positive examples which are teacher data corresponding to an improved organization in response to the new transmission, and one or more negative examples which are teacher data corresponding to an organization that has not been improved in response to the new transmission, and the information acquisition unit refers to a transmission information storage unit in which two or more pieces of transmitted information are stored, and for each of the two or more pieces of transmitted information, uses the transmission information, the target organization response or statistical result, and the learning information to acquire a flag indicating whether the organization will be improved or not, and acquires the transmission information corresponding to the flag indicating that the organization will be improved.

[0024] With this configuration, it is possible to appropriately propose information to be transmitted to members of an organization.

[0025] In addition, the information processing device of the eleventh invention is an information processing device in which, compared to any one of the first to ninth inventions, each of the two or more teaching data has an organizational response or statistical result, newly transmitted information, and a score indicating the degree to which the organization has improved in response to the new transmission, and the information acquisition unit refers to a transmitted information storage unit in which two or more pieces of transmitted information are stored, and for each of the two or more pieces of transmitted information, acquires a score using the transmitted information, the target organization response or statistical result, and learning information, and acquires the transmitted information corresponding to the highest score.

[0026] With this configuration, it is possible to appropriately propose information to be transmitted to members of an organization.

[0027] In addition, the information processing device of the twelfth invention is an information processing device in which, compared to any one of the first to ninth inventions, each of the two or more teaching data has an organizational response or statistical result and new outgoing information when the organization is improved, and the information acquisition unit acquires the outgoing information using the target organizational response or statistical result and the learning information.

[0028] With this configuration, it is possible to appropriately propose information to be transmitted to members of an organization. Effect of the Invention

[0029] According to the information processing device of the present invention, it is possible to appropriately propose information to be transmitted to members of an organization. [Brief description of the drawings]

[0030] [Figure 1] Conceptual diagram of information system A in embodiment 1. [Diagram 2] Block diagram of Information System A [Diagram 3] A flowchart illustrating an example of the operation of the information processing device 1. [Figure 4] Flowchart for explaining an example of a process for acquiring data from the same source [Diagram 5] 11 is a flowchart illustrating a first example of the information acquisition process. [Figure 6] 11 is a flowchart illustrating a second example of the information acquisition process. [Figure 7] 11 is a flowchart illustrating a third example of the information acquisition process. [Figure 8] A flowchart illustrating an example of the statistical processing [Figure 9] A flowchart illustrating an example of the score calculation process [Figure 10] A flowchart illustrating an example of the learning process. [Figure 11] FIG. 13 shows an example of the questionnaire management table. [Figure 12] FIG. 13 is a diagram showing an example of the transmitted information management table. [Figure 13] A diagram showing an example of the file [Figure 14] An example of the organization management table [Figure 15] FIG. 13 shows an example of the response management table. [Figure 16] An example of the model management table [Figure 17] Overview of the computer system [Figure 18] Block diagram of the computer system DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0031] Hereinafter, an embodiment of an information processing device and the like will be described with reference to the drawings. Note that, in the embodiments, components with the same reference numerals perform similar operations, and therefore repeated description may be omitted.

[0032] (Embodiment 1) In this embodiment, learning information is stored that is created using two or more teacher data including organizational answers, which are answers to one or more questions in a questionnaire and are a collection of answers from one or more members of an organization, or statistical results that are the result of statistical processing of the organizational answers, and past information sent to members of the organization. The information processing device acquires and outputs information to be sent to a target member using the organizational answers of a target organization or the statistical results of the organizational answers and the learning information. The teacher data includes communication information such as one or more attribute values ​​of the organization to which the member belongs, past information sent to members of the organization, and the member's reaction to the past information sent. The learning information is, for example, a learning model, a model possessed by a generative AI, or a correspondence table. The organization is, for example, a company, a local government, a school, or an individual business entity, but the type is not important.

[0033] In this specification, information X being associated with information Y means that information Y can be obtained from information X, or information X can be obtained from information Y, and the method of association is not important. Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, or information Y may be included in information X, etc.

[0034] 1 is a conceptual diagram of an information system A according to the present embodiment. The information system A includes an information processing device 1 and one or two terminal devices 2.

[0035] The information processing device 1 is a device that uses responses to a questionnaire given to one or more members of an organization to suggest information to be transmitted to the one or more members. The information processing device 1 is a so-called server device here. The information processing device 1 is, for example, a cloud server or an ASP server, but the type and location of the information processing device 1 are not important. The information processing device 1 may also be a standalone device.

[0036] The terminal device 2 is a terminal used by a user. A user is usually a member of an organization. A member is a part of an organization. A member is, for example, a company employee, a part-time worker, etc. A member of an organization is usually a person who receives a message. A member of an organization may also be a person who sends information. A person who sends information is, for example, a representative of an organization or a superior of other members. The terminal device 2 is a mobile terminal such as a smartphone, a tablet terminal, or a mobile phone, a so-called personal computer, etc., and the type does not matter.

[0037] 2 is a block diagram of an information system A according to the present embodiment. The information processing device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit .

[0038] The storage unit 11 includes a questionnaire storage unit 111, a transmitted information storage unit 112, an organization information storage unit 113, a response storage unit 114, and a learning information storage unit 115. The reception unit 12 includes an information reception unit 121. The processing unit 13 includes a statistical processing unit 131, a learning unit 132, and an information acquisition unit 133. The output unit 14 includes an information output unit 141.

[0039] The terminal device 2 includes a terminal storage unit 21, a terminal reception unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal reception unit 25, and a terminal output unit .

[0040] Various types of information are stored in the storage unit 11 constituting the information processing device 1. The various types of information include, for example, a questionnaire (to be described later), transmitted information (to be described later), organizational information (to be described later), answers (to be described later), and learning information (to be described later).

[0041] The questionnaire storage unit 111 stores a questionnaire. A questionnaire usually has two or more questions. The questions may be called items, questions, etc. It is preferable that each of the one or more questions is a question that asks about expectations for an item related to an organization such as a company or about satisfaction with the item. When members are asked about their expectations and satisfaction with an item, the question asking about expectations for the item and the question asking about satisfaction with the item may be considered to be separate questions, or one item may be considered to be one question. When one item is considered to be one question, one question is a question that asks about both expectations and satisfaction.

[0042] Expectations are the degree of expectation towards an object (e.g., a company, a job, a boss, a workplace, influence within an industry, salary, etc.). Needless to say, "expectations" may be considered to have the meaning of similar terms such as "importance" or "influence" and may be replaced with similar terms. Satisfaction is the degree of satisfaction towards an object (e.g., a company, a job, a boss, a workplace, influence within an industry, salary, etc.). Needless to say, "satisfaction" may be considered to have the meaning of similar terms such as "realization" or "achievement" and may be replaced with similar terms.

[0043] One or more pieces of transmitted information are stored in the transmitted information storage unit 112. Usually, two or more pieces of transmitted information are stored in the transmitted information storage unit 112.

[0044] The transmitted information is information about information to be transmitted to one or more members, or information about information transmitted to one or more members. The transmitted information is, for example, transmitted content information, title information, or a transmission identifier.

[0045] The transmission content information is information that specifies the transmission content. The transmission content information is preferably information that is ultimately transmitted, but may also be template information of the information that is ultimately transmitted. Template information is information in which part of the information that is ultimately transmitted is blank or variable, or sample information of the information that is ultimately transmitted. The transmission content information is, for example, information that has information of two or more data types among these data types. The data type of the transmission content information does not matter. The transmission content information is, for example, a text to convey the stability of the company through an explanation of financial results, a text to convey the degree of impact on the outside through external public relations, a text to convey an interpretation of the philosophy and policy through a company-wide general meeting, a text to increase understanding of the strategy by sharing the contents of the meeting, and a text to convey future business policies through a review of the end of the term.

[0046] The title information is information that specifies the title of the transmitted content information. The title information is usually the title of the transmitted content information.

[0047] The transmission identifier is an identifier of the transmission content information, for example, an ID of the transmission content information.

[0048] The person who sends the message to the member is, for example, the head of the organization to which the member belongs or the member's superior. In other words, the sent information is information for use by, for example, the head of the organization to which the member belongs or the member's superior.

[0049] The organization information storage unit 113 stores one or more pieces of organization information. The organization information is information related to an organization. The organization information includes, for example, an organization identifier, business information, one or more organization attribute values, an outgoing call history, and reaction information. Note that the reaction information may be called response information.

[0050] The organization identifier is information for identifying an organization. For example, the organization identifier is an organization ID or an organization name. For example, the organization name is a company name, a department name, a company name and a department name, or a city, town, or village name.

[0051] Business information is information about the organization's business, such as sales, profits, profit margins, productivity, and growth rates.

[0052] An organization attribute value is an attribute value of an organization. Examples of organization attribute values ​​include industry type, size information that specifies the size of the organization, annual ratio information that specifies the annual ratio of the organization, age ratio information that specifies the age ratio of members of the organization, business content, gender composition information that specifies the gender composition of the organization, settlement month, and general meeting timing information that specifies the timing of the general meeting. Business information may be considered to be an organization attribute value.

[0053] A calling history is information about sent information. A calling history is information about information sent to one or more members. A calling history includes sending information about information sent in the past to one or more members. A calling history has, for example, a calling identifier, title information, sending content information, and date. The date is the day the message was sent.

[0054] The reaction information is information about the reaction of members to a message based on the message information. The reaction information is, for example, a comment, information indicating that the "Like" button was pressed, the number of positive comments among the comments, the number of negative comments among the comments, the ratio of positive comments among the comments, and the ratio of negative comments among the comments.

[0055] The answer storage unit 114 stores an answer set. An answer set is a set of one or more organizational answers. An organizational answer is a set of member answers of one or more members of an organization. A member answer is a set of answers to a questionnaire for one member. A member answer is usually a set of answers to two or more questions in a questionnaire. An organizational answer is usually associated with an organizational attribute value. An organizational answer is associated with, for example, one or more statistical results. The statistical results are information obtained from the organizational answers by the statistical processing unit 131 described later.

[0056] The learning information storage unit 115 stores one or more pieces of learning information. The learning information is, for example, information acquired by the learning unit 132 described later. The learning information may be associated with a model condition. In other words, learning information may exist for each model condition. The model condition is a condition for determining the learning information to be used in the prediction process. The model condition is a condition using one or more organization attribute values. An example of the model condition is "industry type=trading company AND size=large company".

[0057] The learning information is information based on two or more pieces of teacher data. The learning information is usually information acquired using two or more pieces of teacher data. The learning information is, for example, a learning model or a correspondence table. The learning information is, for example, a learning model possessed by the generative AI. When using a learning model possessed by the generative AI, the learning information storage unit 115 exists in an external device other than the information processing device 1. The generative AI may also be called a generative AI. The generative AI is usually an AI that generates text. The generative AI is, for example, ChatGPT (registered trademark) or Jasper.

[0058] Teacher data is information that serves as the basis for learning information. Teacher data includes original data and newly transmitted information. Original data is information that serves as the basis for teacher data. Original data is an organizational response or one or more statistical results. Original data may include an organizational response and one or more statistical results. Statistical results are the results of statistical processing of the organizational responses. Newly transmitted information is transmitted information regarding information that has been newly transmitted after the organizational response has been obtained (after the survey).

[0059] When the teaching data includes original data and newly transmitted information, the original data may be an explanatory variable and the newly transmitted information may be a target variable.

[0060] When the training data has original data and newly transmitted information, the training data is, for example, a positive example or a negative example. A positive example is training data having original data and newly transmitted information in a case where an organization improves as a result of transmitting information specified by the newly transmitted information. A negative example is training data having original data and newly transmitted information in a case where an organization does not improve as a result of transmitting information specified by the newly transmitted information. In such a case, for example, a flag indicating a positive example or a negative example is the objective variable.

[0061] The teacher data includes, for example, original data, communication information, and newly transmitted information. Such teacher data is, for example, a positive example or a negative example. In such a case, for example, the original data, communication information, and newly transmitted information are explanatory variables, and a flag indicating a positive example or a negative example is an objective variable. The objective variable in such teacher data is the newly transmitted information, and the original data and communication information may be explanatory variables.

[0062] The teacher data includes, for example, original data, communication information, newly transmitted information, and a score. The score is, for example, information indicating the degree to which the organization has improved, or information indicating the degree to which the organization has not improved. In this case, the original data, communication information, and newly transmitted information are explanatory variables, and the score is a target variable.

[0063] The score is, for example, the difference between a first score obtained using the organization's response to a questionnaire after the transmission specified by the new transmission information is made (usually the first after the transmission) and a second score obtained using the organization's response to a questionnaire before the transmission specified by the new transmission information is made (usually the last before the transmission). The first score and the second score are, for example, engagement scores described later, but may also be the number of items with "satisfaction-expectation>=0" or the number of items with "satisfaction>=4", etc.

[0064] The score is, for example, the difference between an engagement score obtained using the organization's responses to a survey after the message specified by the new message information is made (usually the first after the message is made) and an engagement score obtained using the organization's responses to a survey before the message specified by the new message information is made (usually the last before the message is made).

[0065] The score is, for example, the amount of change in the engagement score before and after the transmission specified by the new transmission information. However, the score may be any information indicating the degree to which the organization has improved or deteriorated.

[0066] The communication information is information regarding communication with members. The communication information includes transmission information regarding information transmitted to members in the past. The communication information includes, for example, reaction information. The reaction information is information regarding the member's reaction to information transmitted to the member. The reaction information is, for example, the number of presses of the "Like" button, the number of comments by the member, the number of positive comments among the member's comments, and the number of negative comments among the member's comments.

[0067] The newly transmitted information is information related to information that has been newly transmitted to the organization in a situation where an organization response and communication information exist. The newly transmitted information is, for example, transmitted content information, title information, or a transmission identifier.

[0068] The original data includes, for example, business information, and for example, one or more organizational attribute values ​​of an organization.

[0069] A learning model is information configured by a machine learning learning process using two or more pieces of teacher data, and is information used in machine learning prediction processing. A learning model may be called a learner, a classifier, a classification model, or the like. Machine learning algorithms may be deep learning, random forest, decision tree, SVM, SVR, or the like. In addition, for machine learning, various machine learning functions such as the TensorFlow (registered trademark) library, the random forest module of the R language, fastText, TinySVM, and various existing libraries can be used.

[0070] The correspondence table is a table having two or more pieces of correspondence information. The correspondence information is, for example, information indicating the correspondence between original data and newly transmitted information. The correspondence information is, for example, information indicating the correspondence between original data, newly transmitted information, and scores.

[0071] The reception unit 12 receives various information, instructions, etc. Here, reception usually means reception from the terminal device 2, but may be considered as a concept including reception of information input from an input device such as a keyboard, mouse, or touch panel, and reception of information read from a recording medium such as an optical disk, a magnetic disk, or a semiconductor memory.

[0072] The various information and instructions are, for example, a target organization response, a member response, a start instruction, etc. A start instruction is an instruction to start an operation for outputting the transmission information.

[0073] The information receiving unit 121 receives the target organization response. The target organization response is the organization response of the target organization. The target organization is the organization to which the transmission information is proposed. The organization response is a collection of member responses of one or more members. The information receiving unit 121 may acquire the target organization response from the response storage unit 114.

[0074] The information receiving unit 121 does not need to receive member responses from all two or more members at the same time.

[0075] Here, acceptance usually means receiving information from the terminal device 2, but it may also be considered as a concept including, for example, the acceptance of information input from an input device such as a keyboard, mouse, or touch panel, and the acceptance of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

[0076] The processing unit 13 performs various types of processing. The various types of processing are, for example, processing performed by a statistical processing unit 131, a learning unit 132, and an information acquisition unit 133.

[0077] The processing unit 13 judges, for example, whether a start condition is met. The start condition is a condition for outputting transmission information. The start condition is, for example, that a start instruction has been accepted, that a predetermined time has arrived, that information regarding settlement has been accepted (such as immediately after settlement), and that questionnaire responses to all members have been accepted. Acceptance of all questionnaire responses may also be that an engagement score has been calculated.

[0078] Statistical processing unit 131 statistically processes the organizational responses to obtain one or more statistical results. The organizational responses are stored, for example, in response storage unit 114. Note that the content of the statistical processing is not important.

[0079] The statistical results may be, for example, engagement score (hereinafter referred to as "ES" where appropriate), the average value of the difference between expectations and satisfaction for two or more items for two or more members, the deviation of the average value of expectations for each of two or more items for two or more members, the deviation of the average value of satisfaction for each of two or more items for two or more members, the deviation of the difference between expectations and satisfaction for each of two or more items for two or more members, the variance of expectations for each of two or more items, the variance of satisfaction for each of two or more items for two or more members, the variance of the difference between expectations and satisfaction for each of two or more items for two or more members, the average value of expectations for each of two or more items for two or more members, and the average value of satisfaction for each of two or more items for two or more members.

[0080] The statistical processing unit 131 calculates the score of each organization by using, for example, the organizational response of one or more organizations. The statistical processing unit 131 calculates the score, for example, as follows.

[0081] The statistical processing unit 131 statistically processes the answers of the members for each of two or more items, and obtains an item score for each item. The item score is the score for each item.

[0082] The statistical processing unit 131, for example, statistically processes the satisfaction level information for each of two or more items included in the organizational response for each organization, and obtains an item score for each organization and each item. The statistical processing unit 131 may, for example, calculate a representative value (e.g., average value, median value) of the satisfaction level for each organization and each item, and accumulate such representative value as an item score in a buffer (not shown) or the response storage unit 114 in pairs with an item identifier.

[0083] Furthermore, the statistical processing unit 131 may, for example, calculate a weighted average of satisfaction levels by applying different weights for each organization and each item according to the attribute values ​​of the members, and accumulate such weighted averages as item scores in pairs with item identifiers in a buffer (not shown) or the answer storage unit 114. Note that the attribute values ​​of members are, for example, job titles, years of service, gender, etc. For example, the statistical processing unit 131 may compare the satisfaction levels of employees with long years of service with those of employees with short years of service, weighting them more heavily to calculate the weighted average.

[0084] The statistical processing unit 131 acquires an item score for each organization using the satisfaction level and the expectation level for at least some of the items. Note that the items for which the item scores are acquired using the satisfaction level and the expectation level are, for example, individual items.

[0085] It is preferable that the statistical processing unit 131 acquires item scores such that, for example, the higher the satisfaction level, the higher the score, and the lower the expectation level, the higher the score.

[0086] The statistical processing unit 131, for example, calculates a representative value of the satisfaction level of the organizational responses and a representative value of the expectation level of the organizational responses for each of two or more items for one or more organizations, and obtains an item score for each item using the two representative values.

[0087] The statistical processing unit 131 may, for example, apply the satisfaction level and the expectation level to an individual score table described later, and obtain an item score for each item. The statistical processing unit 131 may also, for example, apply the statistical processing result of the satisfaction level and the statistical processing result of the expectation level to an individual score table, and obtain an item score for each item. The statistical processing unit 131 may, for example, apply a representative value of the satisfaction level and a representative value of the expectation level to an individual score table, and obtain an item score for each item. The statistical processing unit 131 may, for example, apply a weighted average value of the satisfaction level and a weighted average value of the expectation level to an individual score table, and obtain an item score for each item. The weighted average value is a weighted average value based on the attribute values ​​of the members.

[0088] The individual score table here is information for determining an item score when satisfaction and expectation are given. The individual score table here is, for example, a table having an axis of satisfaction and an axis of expectation, in which an individual score is entered in each cell of the table, and in which an item score is determined when satisfaction and expectation are determined. It is preferable that such an individual score table is a table in which the greater the satisfaction, the higher the item score obtained, and the smaller the expectation, the higher the item score obtained.

[0089] The statistical processing unit 131 may calculate the item score for each item using, for example, an increasing function with the representative value of the satisfaction level as a parameter and a decreasing function with the representative value of the expectation level as a parameter.

[0090] The above describes the process of calculating so-called absolute item scores by the statistical processing unit 131. The absolute item scores are item scores that do not depend on an organization identifier such as an industry, and are usually obtained only from organization responses corresponding to the organization identifier of one organization.

[0091] However, the statistical processing unit 131 may calculate so-called relative item scores. That is, the statistical processing unit 131 acquires item scores according to, for example, an organization attribute value. In such a case, the statistical processing unit 131 calculates, for example, absolute item scores for each item of the organization. Then, the statistical processing unit 131 calculates the relative item scores using, for example, one or more item scores acquired from organization responses corresponding to one or more organization identifiers paired with the same organization attribute value (for example, the same industry) as the organization attribute value of the organization.

[0092] For example, the statistical processing unit 131 calculates the deviation value of the absolute item score of the organization using the item scores of organizations identified by one or more organization identifiers that are paired with the same organization attribute value as the organization. Note that the technique of calculating a relative item score, which is the deviation value of one absolute item score, using multiple absolute item scores is a well-known technique.

[0093] Furthermore, the statistical processing unit 131 may, for example, calculate an average value of two or more absolute item scores obtained from organization responses corresponding to one or more organization identifiers that are paired with the same organization attribute value as the organization attribute value of the organization, and obtain a relative item score using the difference between the average value and the absolute item score of the organization. Note that such a relative item score may be the difference between the average value of the item scores and the absolute item score of the organization, or may be a value calculated by substituting the difference as a parameter into an arithmetic formula.

[0094] In other words, there are various methods for calculating the relative item score of an organization using the absolute item scores of multiple organizations corresponding to the same organizational attribute value. The same organizational attribute value means that one or more organizational attribute values ​​are the same. For example, the statistical processing unit 131 may calculate the relative item score of a focused company among multiple companies in the same industry for each item, or may calculate the relative item score of a focused company among multiple companies in the same industry and of a similar size.

[0095] The statistical processing unit 131 obtains a total score using two or more item scores for one or two or more organizational responses. The total score is a comprehensive score for each organization. The statistical processing unit 131 usually obtains a higher total score for better scores for each item score of two or more. The total score may also be called an engagement score.

[0096] The statistical processing unit 131 obtains an attribute value-added overall score, which is a score of an organization identified by an organization identifier and corresponds to one or more organization attribute values ​​paired with the organization identifier, by using a plurality of organization responses. The attribute value-added overall score may also be called an engagement score.

[0097] That is, the statistical processing unit 131 may acquire an attribute value-added overall score, which is a relative overall score of one organization among a plurality of organizations that meet a condition configured using, for example, one or more organizational attribute values. For example, the statistical processing unit 131 may acquire an attribute value-added overall score of "Laboratory + Technical Department" of a manufacturer, Company A, from the member responses of members who belong to a research laboratory or technical department of a specific organization (for example, Company A) among a plurality of organizations whose industry identifier is "manufacturer" and whose department identifier is "research laboratory or technical department." In such a case, the condition is "(industry identifier=manufacturer) AND (department identifier=research laboratory OR technical department)".

[0098] The statistical processing unit 131 obtains an absolute overall score using, for example, absolute item scores of 2 or more.

[0099] Furthermore, the statistical processing unit 131 obtains an attribute-value-added overall score, which is a relative overall score, using, for example, two or more relative item scores.

[0100] It is preferable that the statistical processing unit 131 obtains a total 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 weighting it more. Note that even in this case, if absolute item scores are used, the statistical processing unit 131 can obtain an absolute total score. Also, if relative item scores are used, the statistical processing unit 131 can obtain a total score taking into account attribute values.

[0101] The statistical processing unit 131 may calculate the overall score by, for example, "total score = α × statistical score of item scores for overall items + β × statistical score of item scores for individual items." Here, it is preferable that (α>β). That is, it is preferable that the statistical processing unit 131 obtains the overall score by comparing the item scores for overall items with the item scores for individual items and increasing the weighting. Also, for example, "α=0.7, β=0.3." The statistical score of the item scores for overall items is, for example, the average value or weighted average of the item scores for overall items. The statistical score of the item scores for individual items is, for example, the average value or weighted average of the item scores for individual items.

[0102] The statistical processing unit 131 acquires the overall score and the organization attribute value paired with the organization identifier, and acquires the attribute value-added overall score, which is the score of the organization according to the organization attribute value, using the overall score and the organization attribute value. The attribute value-added overall score may be considered as a relative overall score that depends on the organization attribute value. The attribute value-added overall score may also be called a relative engagement score. The organization attribute value in this case is one or more organization attribute values.

[0103] The statistical processing unit 131 acquires, for example, an attribute value-added overall score, which is the score of an organization identified by an organization identifier and corresponds to an organization attribute value paired with the organization identifier, using a plurality of organization response information.

[0104] The statistical processing unit 131 obtains the overall score and the organization attribute value paired with the organization identifier, and obtains the attribute value-added overall score using the overall score and the organization attribute value. The overall score here is an absolute overall score, and the attribute value-added overall score is a relative overall score.

[0105] The statistical processing unit 131 obtains an attribute value-taking-in overall score using the two or more relative item scores obtained. The statistical processing unit 131 usually obtains a larger attribute value-taking-in overall score as the relative item score becomes larger. For example, the statistical processing unit 131 obtains the attribute value-taking-in overall score by an increasing function (for example, average, weighted average, sum, etc.) using the two or more relative item scores obtained as parameters. For example, the storage unit 11 stores a correspondence table between a set of two or more relative item scores and an attribute value-taking-in overall score, and the statistical processing unit 131 refers to the correspondence table and obtains an attribute value-taking-in overall score corresponding to the two or more relative item scores obtained from the correspondence table.

[0106] The learning unit 132 acquires learning information using two or more pieces of teacher data. Below, the case where the learning information is a learning model and the case where the learning information is a correspondence table will be described separately. (1) When the learning information is a learning model (1-1) When two or more training data have one or more positive examples and one or more negative examples

[0107] In such a case, the original data contained in the teacher data includes newly transmitted information. Such original data is an explanatory variable, and for example, a positive example has a response variable of "1" and a negative example has a response variable of "0." The original data includes, for example, one or more statistical results.

[0108] The learning unit 132 performs a machine learning learning process using the two or more pieces of teacher data to obtain a learning model. The learning model is a model used for binary classification. The learning model is used together with the original data having the newly transmitted information to obtain a target variable of "1" or "0" by a machine learning prediction process.

[0109] As mentioned above, the machine learning algorithm can be any algorithm, such as deep learning, random forest, decision tree, SVM, etc. (1-2) When each teacher data has a score of 2 or more

[0110] In such a case, the explanatory variables in the training data include the original data and the newly transmitted information. The objective variable in the training data is a score. The score here is, for example, the difference between the engagement score after transmitting the message corresponding to the newly transmitted information and the engagement score before transmitting the message corresponding to the newly transmitted information.

[0111] The learning unit 132 performs a machine learning learning process using the two or more pieces of teacher data to obtain a learning model. The learning model is a model used for multi-value classification. The learning model is used together with the newly transmitted information and the original data to obtain a score, which is a target variable, by a machine learning prediction process.

[0112] The machine learning algorithm can be any type, including deep learning, random forest, decision tree, SVR, etc. (1-3) When the objective variable is newly published information

[0113] In this case, the explanatory variables in the training data have the original data, and the objective variable in the training data is the newly transmitted information. Note that the newly transmitted information here is a transmission identifier that identifies the information to be transmitted, or title information of the information to be transmitted.

[0114] The learning unit 132 performs a machine learning learning process using the two or more pieces of teacher data to obtain a learning model. The learning model is a model used for multi-value classification. The learning model is used together with the original data to obtain newly transmitted information, which is a target variable, by a machine learning prediction process.

[0115] The machine learning algorithm can be any type, including deep learning, random forest, decision tree, SVR, etc. (2) When the learning information is a correspondence table (2-1) When the correspondence information is information showing the correspondence between the original data and the newly issued information when the organization makes improvements

[0116] The learning unit 132 acquires correspondence information having the original data and the newly transmitted information from each of the two or more pieces of teacher data. The learning unit 132 creates a correspondence table having the two or more pieces of correspondence information. (2-2) When the correspondence information is information showing the correspondence between the original data having the new transmission information and the score

[0117] The learning unit 132 acquires correspondence information having the newly transmitted information, the original data, and the score from each of the two or more pieces of teacher data. The learning unit 132 creates a correspondence table having the two or more pieces of correspondence information.

[0118] The information acquiring unit 133 acquires transmission information using the target organization response accepted by the information accepting unit 121 and the learning information in the learning information storage unit 115 .

[0119] For example, the information acquisition unit 133 acquires a score for each of two or more pieces of transmitted information using the target organization response, the transmitted information, and the learning information accepted by the information acceptance unit 121, and acquires the transmitted information corresponding to the highest score. Note that the transmitted information here is transmitted information that may be proposed, and can also be considered as candidates for transmitted information.

[0120] It is preferable that the information acquiring unit 133 acquires the transmission information by applying the organizational vector to the learning information. The organizational vector is a vector having one or more statistical results acquired using the target organizational responses accepted by the information accepting unit 121 as elements. (1) When performing machine learning prediction processing

[0121] The information acquisition unit 133 performs machine learning prediction processing using the target organization response received by the information reception unit 121 and the learning model in the learning information storage unit 115, and acquires the transmitted information. (1-1) When acquiring information directly

[0122] The information acquisition unit 133 provides the target organization response received by the information reception unit 121 and the learning model in the learning information storage unit 115 to a machine learning prediction module, executes the prediction module, and acquires the transmitted information.

[0123] In such a case, the learning model is a model configured using two or more pieces of teacher data having organizational responses as explanatory variables and transmitted information (for example, title information, transmitted identifier) ​​as objective variables. (1-2) Two or more candidates for each piece of information are given, a score is obtained, and one or more pieces of information that match the score and match the favorable conditions are obtained.

[0124] For each of two or more pieces of transmitted information that can be candidates, the information acquisition unit 133 provides the target organization response, the transmitted information, and the learning model accepted by the information acceptance unit 121 to a machine learning prediction module, executes the prediction module, and acquires a score. Next, the information acquisition unit 133 acquires one or more pieces of transmitted information whose scores match a good condition. The good condition is, for example, the maximum score, a score in the top N (N is a natural number of 2 or more), or a score equal to or greater than a threshold value. (1-2) Given two or more candidates for each piece of information to be transmitted, obtain flag "1" (the organization will improve) or "0" (the organization will not improve), and obtain one or more pieces of information to be transmitted that correspond to flag "1."

[0125] The information acquisition unit 133 provides the target organization answer, the transmitted information, and the learning model accepted by the information acceptance unit 121 to a machine learning prediction module for each of two or more pieces of transmitted information that can be candidates, executes the prediction module, and acquires a flag that is a classification result. Next, the information acquisition unit 133 acquires one or more pieces of transmitted information whose flag matches "1" (the organization will improve).

[0126] The information acquisition unit 133 executes the prediction module to acquire a flag and a likelihood (which may be called a score) returned by the prediction module, and acquires one or more pieces of transmission information corresponding to the likelihood that the flag is "1" and satisfies a favorable condition. The favorable condition is, for example, that the likelihood is maximum, that the likelihood is in the top N (N is a natural number of 2 or more), or that the likelihood is equal to or greater than a threshold value. (2) When using generative AI modules (2-1) When generative AI outputs message content information

[0127] The information acquisition unit 133, for example, provides two or more pieces of teacher data to a generative AI module and causes the generative AI to learn. Next, the information acquisition unit 133, for example, provides the target organization response to the generative AI module to acquire transmission content information. (2-2) When the generative AI outputs the transmission identifier or title information

[0128] The information acquisition unit 133, for example, provides two or more pieces of teacher data to a generative AI module and causes the generative AI to learn. Next, the information acquisition unit 133 provides, for example, the target organization response to the generative AI module to acquire the transmission identifier or title information.

[0129] The information acquisition unit 133 may provide the title information paired with the transmission identifier or the title information returned by the generation AI to the generation AI module, and acquire transmission content information, which is information indicating the transmission content. (3) When using a correspondence table

[0130] The information acquisition unit 133 searches the correspondence table for one or more vectors whose similarity to a vector including two or more elements constituting the target organization response satisfies a good condition, and acquires one or more pieces of transmitted information paired with the vector. The good condition here is, for example, that the similarity is maximum, that the similarity is in the top N (N is a natural number of 2 or more), or that the similarity is equal to or greater than a threshold value.

[0131] The output unit 14 outputs various types of information. Here, the various types of information include, for example, transmitted information.

[0132] In this case, output usually means transmission to terminal device 2, but it may also be considered a concept that includes display on a display, projection using a projector, printing on a printer, sound output, storage on a recording medium, and handing over the processing results to other processing devices or other programs.

[0133] The information output unit 141 outputs the transmission information acquired by the information acquisition unit 133. The information output unit 141 transmits the transmission content information acquired by the information acquisition unit 133, for example.

[0134] Various types of information are stored in the terminal storage unit 21 constituting the terminal device 2. The various types of information are, for example, member responses.

[0135] The terminal reception unit 22 receives various instructions and information. The various instructions and information are, for example, member responses, reaction information, etc. The member responses correspond to, for example, an organization identifier and a member identifier. The reaction information corresponds to the transmitted information or the transmission history.

[0136] Here, reception is a concept that includes reception of information input from input devices such as a keyboard, mouse, or touch panel, reception of information transmitted via a wired or wireless communication line, and reception of information read from recording media such as an optical disk, magnetic disk, or semiconductor memory.

[0137] The means for inputting various instructions and information may be any means, such as a touch panel, a keyboard, a mouse, or a menu screen.

[0138] The device processing unit 23 performs various types of processing. For example, the various types of processing are processing for configuring information received by the device receiving unit 25 into data to be displayed. For example, the various types of processing are processing for configuring instructions, etc. accepted by the device accepting unit 22 into instructions, etc. to be transmitted.

[0139] The terminal transmitting unit 24 transmits various instructions, information, and the like to the information processing device 1. The various instructions, information, and the like are, for example, instructions configured by the terminal processing unit 23, instructions and information accepted by the terminal accepting unit 22, and the like.

[0140] The terminal receiving unit 25 receives various information from the information processing device 1. The various information is, for example, transmission information. The transmission information here is, for example, transmission content information, title information, or a transmission identifier.

[0141] The terminal output unit 26 acquires various information. The various information is, for example, information accepted by the terminal acceptance unit 22, information received by the terminal reception unit 25, and information configured by the device processing unit 23. The various information is, for example, outgoing information. Here, output is a concept including display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, storage on a recording medium, delivery of processing results to other processing devices, other programs, etc.

[0142] The storage unit 11, questionnaire storage unit 111, transmitted information storage unit 112, organizational information storage unit 113, response storage unit 114, learning information storage unit 115, and terminal storage unit 21 are preferably non-volatile recording media, but can also be realized using volatile recording media.

[0143] There is no restriction on the process by which information is stored in the storage unit 11, etc. 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 inputted via an input device may be stored in the storage unit 11, etc.

[0144] It is preferable that the reception unit 12 and the information reception unit 121 are realized by wireless or wired communication means, but they may also be realized by a means for receiving broadcasts, a device driver for an input means such as a touch panel or keyboard, or control software for a menu screen.

[0145] The processing unit 13, the statistical processing unit 131, the learning unit 132, the information acquisition unit 133, and the device processing unit 23 can usually be realized by a processor, a memory, etc. The processing procedure of the processing unit 13, etc. is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, etc., and the type is not important.

[0146] The output unit 14 and the information output unit 141 are usually realized by wireless or wired communication means, but may be realized by broadcasting means.

[0147] The terminal reception unit 22 can be realized by a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen.

[0148] The terminal transmitting unit 24 is usually realized by a wireless or wired communication means, but may also be realized by a broadcasting means.

[0149] The terminal receiving unit 25 is usually realized by a wireless or wired communication means, but may be realized by a means for receiving a broadcast.

[0150] The terminal output unit 26 may be considered to include, or may not include, an output device such as a display, a speaker, etc. The terminal output unit 26 may be realized by driver software for an output device, or a combination of driver software for an output device and an output device, etc.

[0151] Next, an example of the operation of the information processing device 1 will be described with reference to the flowchart of FIG.

[0152] (Step S301) The processing unit 13 judges whether or not the start condition is met. If the start condition is met, the process proceeds to step S302, and if the start condition is not met, the process proceeds to step S310. The start condition includes, for example, information for determining one or more target tissues.

[0153] (Step S302) The processing unit 13 assigns 1 to a counter i.

[0154] (Step S303) The processing unit 13 judges whether or not there is an organization identifier of the i-th organization to which the transmission information is to be output. If there is an organization identifier of the i-th organization, the process proceeds to step S304, and if there is no organization identifier, the process returns to step S301.

[0155] (Step S304) The information acquisition unit 133 acquires the original data. An example of such original data acquisition processing will be described with reference to the flowchart of FIG.

[0156] (Step S305) The information acquisition unit 133 performs a process of acquiring transmitted information. An example of such information acquisition process will be described with reference to the flowcharts of Fig. 5, Fig. 6, and Fig. 7. It is assumed that the transmitted information acquired here is transmitted content information.

[0157] (Step S306) The information output unit 141 outputs the transmission content information acquired in step S305. For example, the information output unit 141 transmits the transmission content information to a contact point (for example, an email address of the head of the organization) paired with the organization identifier of the i-th organization.

[0158] (Step S307) The processing unit 13 creates a call history corresponding to the call content information output in step S306. The call history includes, for example, a call identifier, title information, call content information, and date.

[0159] (Step S308) The processing unit 13 accumulates the outgoing call history constructed in step S307 in the organization information storage unit 113 in association with the i-th organization identifier.

[0160] (Step S309) The processing unit 13 increments the counter i by 1. The process returns to step S303.

[0161] (Step S310) The reception unit 12 judges whether or not a member answer has been received from the terminal device 2. If a member answer has been received, the process proceeds to step S311, and if not, the process proceeds to step S312. The member answer corresponds to, for example, an organization identifier and a member identifier.

[0162] (Step S311) The processing unit 13 stores the member response received in step S310 in the response storage unit 114 in association with the organization identifier and the member identifier. The process returns to step S301.

[0163] (Step S312) The statistical processing unit 131 judges whether it is time for statistical processing. If it is time for statistical processing, the process proceeds to step S313, and if it is not time for statistical processing, the process proceeds to step S317. The timing for statistical processing is, for example, the timing when the processing unit 13 detects that member responses from all members of an organization have been accepted, the timing when an instruction for statistical processing is accepted, or the timing when a specific time has arrived.

[0164] (Step S313) The statistical processing unit 131 assigns 1 to the counter i.

[0165] (Step S314) The statistical processing unit 131 judges whether or not the organization identifier of the i-th organization to be subjected to the statistical processing exists. If the i-th organization identifier exists, the process proceeds to step S315, and if not, the process returns to step S301.

[0166] (Step S315) The statistical processing unit 131 performs statistical processing on the organization responses, which are responses to the most recently sent questionnaire for the i-th organization identifier, to obtain statistical results. An example of such statistical processing will be described with reference to the flowchart in FIG.

[0167] (Step S316) The statistical processing unit 131 increments the counter i by 1. The process returns to step S314.

[0168] (Step S317) The reception unit 12 judges whether or not reaction information has been received from the terminal device 2. If reaction information has been received, the process proceeds to step S318, and if not, the process proceeds to step S319. Note that reaction information is associated with a caller identifier, an organization identifier, and a member identifier.

[0169] (Step S318) The processing unit 13 stores the reaction information received in step S317 in the organization information storage unit 113 in association with the caller identifier, the organization identifier, and the member identifier.

[0170] (Step S319) The learning unit 132 judges whether or not to perform the learning process. If it is judged that the learning process is to be performed, the process proceeds to step S320, and if it is judged that the learning process is not to be performed, the process returns to step S301. It should be noted that the learning process is judged to be performed when, for example, a learning instruction is accepted or a predetermined time has come.

[0171] (Step S320) The learning unit 132 performs a learning process and acquires learning information. An example of the learning process will be described with reference to the flowchart of FIG.

[0172] (Step S321) The learning unit 132 accumulates the learning information acquired in step S320 in the learning information storage unit 115. The process returns to step S301.

[0173] In the flowchart of FIG. 3, the process ends when the power is turned off or an interrupt occurs to end the process.

[0174] Next, an example of the original data acquisition process in step S304 will be described with reference to the flowchart in FIG.

[0175] (Step S401) The information acquiring unit 133 acquires the organization identifier of the target organization (the i-th organization identifier in step S303). The information acquiring unit 133 acquires, from the organization information storage unit 113, one or more organization attribute values ​​that are paired with the organization identifier.

[0176] (Step S402) The information acquiring unit 133 acquires from the answer storage unit 114 one or more organization answers that are paired with the organization identifier acquired in step S401.

[0177] (Step S403) The information acquisition unit 133 acquires one or more outgoing call histories paired with the organization identifier from the organization information storage unit 113. Note that the outgoing call history is information based on outgoing call information sent in the past.

[0178] (Step S404) The information acquisition unit 133 acquires, from the organization information storage unit 113, one or more pieces of reaction information paired with the organization identifier.

[0179] (Step S405) The information acquiring unit 133 acquires from the organization information storage unit 113 one or more outgoing call histories (of other departments) paired with one or more other organization identifiers paired with the organization identifier.

[0180] (Step S406) The information acquiring unit 133 acquires business information paired with the organization identifier from the organization information storage unit 113.

[0181] (Step S407) The information acquisition unit 133 constructs a tissue vector using the information acquired in steps S401 to S406. Then, the process returns to the upper level process. Note that the tissue vector is, for example, a vector having each piece of information acquired in steps S401 to S406 as an element.

[0182] Next, a first example of the information acquisition process in step S305 will be described with reference to the flowchart in Fig. 5. The first example of the information acquisition process is a case where a learning model acquired using two or more pieces of teacher data with a call origination identifier or title information as a response variable is used.

[0183] (Step S501) The information acquisition unit 133 acquires a learning model from the learning information storage unit 115. The learning model is a model acquired using two or more pieces of teacher data in which an organization vector is an explanatory variable and a transmission identifier or title information is an objective variable.

[0184] (Step S502) The information acquiring unit 133 provides the tissue vector and the learning model acquired in step S304 to a machine learning prediction module, and executes the module.

[0185] (Step S503) The information acquisition unit 133 acquires the call origination identifier or title information that is the result of the prediction process in step S502.

[0186] (Step S504) The information acquisition unit 133 acquires the transmission content information corresponding to the transmission identifier or the title information, and returns to the upper level processing.

[0187] The information acquisition unit 133 acquires, for example, transmission content information paired with a transmission identifier or title information from the transmission information storage unit 112. The information acquisition unit 133 gives an inquiry such as "Please tell me about the transmission content when transmitting about 'title information'" to the generation AI, and acquires the transmission content information from the generation AI.

[0188] Next, a second example of the information acquisition process of step S305 will be described with reference to the flowchart of Fig. 6. The second example of the information acquisition process is a case where a learning model acquired using two or more pieces of teacher data with a score as a response variable is used.

[0189] (Step S601) The information acquisition unit 133 acquires a learning model from the learning information storage unit 115. The learning model is a model acquired using two or more pieces of teacher data in which the organizational vector and the transmission identifier or title information are used as explanatory variables, and the score is used as a response variable.

[0190] (Step S602) The information acquiring unit 133 assigns 1 to a counter i.

[0191] (Step S603) Information acquisition unit 133 judges whether or not a candidate for the i-th transmitted information exists in transmitted information storage unit 112. If a candidate for the i-th transmitted information exists, the process proceeds to step S604; if not, the process proceeds to step S608.

[0192] (Step S604) The information acquisition unit 133 acquires a candidate for the i-th transmitted information from the transmitted information storage unit 112. The information acquisition unit 133 configures a vector by adding the candidate for the transmitted information to the organization vector acquired in step S304. This vector is called an input vector.

[0193] (Step S605) The information acquisition unit 133 provides the input vector constructed in step S604 and the learning model acquired in step S601 to a machine learning prediction module, and executes the module.

[0194] (Step S606) The information acquisition unit 133 acquires the score that is the result of the prediction process in step S605. The information acquisition unit 133 associates the score with the i-th candidate for the transmitted information.

[0195] (Step S607) The information acquiring unit 133 increments the counter i by 1. The process returns to step S603.

[0196] (Step S608) The information acquisition unit 133 acquires one or more pieces of newly transmitted information that are transmitted information paired with one or more scores that satisfy the good condition.

[0197] The favorable conditions are conditions based on the score and are conditions for determining the transmitted information to be adopted. For example, favorable conditions are "having the maximum score," "having a score equal to or greater than a threshold," and "having a score in the top N (N is a natural number equal to or greater than 2)."

[0198] Furthermore, when the information acquisition unit 133 acquires two or more pieces of newly transmitted information, it is preferable to perform unique processing to remove duplications.

[0199] (Step S609) The information acquisition unit 133 acquires transmission content information corresponding to each of the one or more pieces of new transmission information acquired in step S608, and then returns to the upper level processing.

[0200] Next, a third example of the information acquisition process in step S305 will be described with reference to the flowchart in Fig. 7. The third example of the information acquisition process is a case where a correspondence table is used.

[0201] (Step S701) The information acquiring unit 133 assigns 1 to a counter i.

[0202] (Step S702) Information acquisition unit 133 judges whether or not the i-th correspondence information exists in the correspondence table of learning information storage unit 115. If the i-th correspondence information exists, the process proceeds to step S703, and if not, the process proceeds to step S705.

[0203] (Step S703) The information acquiring unit 133 acquires the similarity between the vector included in the i-th correspondence information and the tissue vector acquired in S304, and associates the similarity with the i-th correspondence information.

[0204] (Step S704) The information acquiring unit 133 increments the counter i by 1. The process returns to step S702.

[0205] (Step S705) The information acquisition unit 133 acquires one or more pieces of newly transmitted information paired with vectors corresponding to one or more similarities that satisfy the good condition. Here, the newly transmitted information is a transmission identifier or title information.

[0206] The favorable conditions here are conditions based on similarity and are conditions for determining the transmitted information to be adopted. The favorable conditions are, for example, "the similarity is maximum," "the similarity is equal to or greater than a threshold," and "the similarity is in the top N (N is a natural number equal to or greater than 2)."

[0207] Furthermore, when the information acquisition unit 133 acquires two or more pieces of newly transmitted information, it is preferable to perform unique processing to remove duplications.

[0208] (Step S706) The information acquisition unit 133 acquires transmission content information corresponding to each of the one or more pieces of new transmission information acquired in step S705, and then returns to the upper level processing.

[0209] Next, an example of the statistical processing in step S315 will be described with reference to the flowchart in FIG.

[0210] (Step S801) The statistical processing unit 131 acquires an organization response paired with an organization identifier from the response storage unit 114. Such an organization response is an organization response for which a score has not been acquired. In addition, the score is an engagement score.

[0211] (Step S802) The statistical processing unit 131 performs a score calculation process using the organizational response acquired in step S801. An example of the score calculation process will be described with reference to the flowchart of FIG.

[0212] (Step S803) The statistical processing unit 131 assigns 1 to a counter i.

[0213] (Step S804) The statistical processing unit 131 judges whether or not to calculate the i-th statistical value. If the i-th statistical value is to be calculated, the process proceeds to step S805. If the i-th statistical value is not to be calculated, the process proceeds to step S808. The statistical value to be calculated is predetermined.

[0214] (Step S805) The statistical processing unit 131 acquires one or more pieces of information used when calculating the i-th statistical value.

[0215] (Step S806) The statistical processing unit 131 calculates the i-th statistical value by using one or more pieces of information acquired in step S805.

[0216] (Step S807) The statistical processing unit 131 increments the counter i by 1. The process returns to step S804.

[0217] (Step S808) The statistical processing unit 131 uses the score 1 calculated in step S802 and the one or more statistical values ​​calculated in step S806 to generate one or more statistical results to be accumulated. Note that the statistical results may be the statistical values ​​as they are.

[0218] (Step S809) The statistical processing unit 131 associates one or more statistical results constructed in step S808 with the i-th organization identifier and the organization response, and accumulates them in the organization information storage unit 113. The process returns to the upper level process.

[0219] Next, an example of the score calculation process in step S802 will be described with reference to the flowchart in FIG.

[0220] (Step S901) The statistical processing unit 131 assigns 1 to a counter i.

[0221] (Step S902) The statistical processing unit 131 judges whether or not the item identifier of the i-th individual item is present in the organizational response acquired in step S303. If the item identifier of the i-th individual item is present, the process proceeds to step S903, and if not, the process proceeds to step S909.

[0222] (Step S903) The statistical processing unit 131 acquires the satisfaction levels of all members that are paired with the item identifier of the i-th individual item from the organization response acquired in step S307.

[0223] (Step S904) The statistical processing unit 131 performs statistical processing on the satisfaction levels acquired in step S903 to calculate a statistical satisfaction level. Note that here, the statistical processing unit 131 calculates, for example, a statistical satisfaction level that is an average value of the satisfaction levels acquired in step S903. Then, the statistical processing unit 131 accumulates the calculated statistical satisfaction level in the storage unit 11 or a buffer (not shown) in a pair with the item identifier of the i-th individual item.

[0224] (Step S905) The statistical processing unit 131 acquires the expectation levels of all members that are paired with the item identifier of the i-th individual item from the organization response acquired in step S307.

[0225] (Step S906) The statistical processing unit 131 performs statistical processing on the expectation acquired in step S905 to calculate the statistical expectation. Here, the statistical processing unit 131 calculates the statistical expectation, which is, for example, the average value of the expectation information acquired in step S903. Then, the statistical processing unit 131 accumulates the calculated statistical expectation in the storage unit 11 or a buffer (not shown) in a pair with the item identifier of the i-th individual item.

[0226] (Step S907) The statistical processing unit 131 uses the statistical satisfaction degree and statistical expectation degree to obtain an item score for the i-th individual item of the organization of interest. The statistical processing unit 131 applies the statistical satisfaction degree and statistical expectation degree to the individual score table in the individual score table storage unit 113 to obtain an item score for the i-th individual item. The statistical processing unit 131 then accumulates the obtained item score in the storage unit 11 or a buffer (not shown) in a pair with the item identifier of the i-th individual item.

[0227] (Step S908) The statistical processing unit 131 increments the counter i by 1. The process returns to step S902.

[0228] (Step S909) The statistical processing unit 131 assigns 1 to the counter j.

[0229] (Step S910) The statistical processing unit 131 judges whether or not the item identifier of the jth comprehensive item is present in the organizational response acquired in step S307. If the item identifier of the jth comprehensive item is present, the process proceeds to step S911, and if not, the process proceeds to step S914.

[0230] (Step S911) The statistical processing unit 131 acquires the satisfaction levels of all members that are paired with the item identifier of the j-th overall item from the organization response acquired in step S307.

[0231] (Step S912) The statistical processing unit 131 performs statistical processing on the satisfaction levels acquired in step S911 to calculate a statistical satisfaction level. Note that here, the statistical processing unit 131 calculates, for example, a statistical satisfaction level that is an average value of the satisfaction levels acquired in step S911. Then, the statistical processing unit 131 accumulates the calculated statistical satisfaction level in the storage unit 11 or a buffer (not shown) in a pair with the item identifier of the j-th overall item.

[0232] (Step S913) The statistical processing unit 131 increments the counter j by 1. The process returns to step S910.

[0233] (Step S914) The statistical processing unit 131 acquires all item scores of the individual items from the storage unit 11 or a buffer (not shown). Note that the item scores of the individual items are the scores acquired in step S907.

[0234] (Step S915) The statistical processing unit 131 obtains a comprehensive score of the individual items from all the item scores obtained in step S914. For example, the statistical processing unit 131 calculates an average value of all the item scores obtained in step S914, and obtains the average value as a comprehensive score of the individual items.

[0235] (Step S916) The statistical processing unit 131 acquires the statistical satisfaction levels of all the overall items from the storage unit 11 or a buffer (not shown).

[0236] (Step S917) The statistical processing unit 131 performs statistical processing on the statistical satisfaction levels of all items acquired in step S916 to calculate the statistical satisfaction level of the overall item. For example, the statistical processing unit 131 calculates the average value of the statistical satisfaction levels of all items acquired in step S916 and acquires it as the statistical satisfaction level of the overall item.

[0237] (Step S918) The statistical processing unit 131 calculates a provisional overall score from the overall scores of the individual items acquired in step S915 and the statistical satisfaction level of the overall item acquired in step S917. The statistical processing unit 131 calculates the provisional overall score, for example, using the formula "provisional overall score = α × statistical satisfaction level of the overall item + β × overall score of the individual items."

[0238] (Step S919) The statistical processing unit 131 acquires correlation information regarding the correlation between the set of satisfaction levels and the set of expectation levels from the set of satisfaction levels of all individual items and the set of expectation levels of all individual items.

[0239] (Step S920) The statistical processing unit 131 adjusts the provisional overall score acquired in step S918 using the correlation information acquired in step S919 to acquire an overall score. The process returns to the upper level process. Note that the statistical processing unit 131 acquires an overall score such that the greater the degree of correlation indicated by the correlation information, the higher the overall score becomes.

[0240] Next, an example of the learning process in step S320 will be described with reference to the flowchart in FIG.

[0241] (Step S1001) The learning unit 132 assigns 1 to a counter i.

[0242] (Step S1002) The learning unit 132 judges whether or not there is an organization identifier of the i-th organization that can be used to configure training data to be used for learning. If the i-th organization identifier exists, the process proceeds to step S1003, and if not, the process proceeds to step S1013.

[0243] The organization identifiers of organizations that can be used to configure teacher data used for learning are, for example, all organization identifiers stored in the organization information storage unit 113.

[0244] (Step S1003) Learning unit 132 judges whether or not two or more outgoing call histories paired with the i-th organization identifier exist in organization information storage unit 113. If two or more outgoing call histories exist, the process proceeds to step S1004; if not, the process proceeds to step S1012.

[0245] (Step S1004) The learning unit 132 assigns 2 to the counter j.

[0246] (Step S1005) The learning unit 132 judges whether or not the jth call history that is paired with the ith organization identifier exists. If the jth call history exists, the process proceeds to step S1006, and if not, the process proceeds to step S1012.

[0247] (Step S1006) The learning unit 132 acquires the jth call history paired with the i-th organization identifier from the organization information storage unit 113. Note that the call history paired with the i-th organization identifier exists in chronological order, and for example, the second call history is the second oldest call history.

[0248] (Step S1007) The information acquisition unit 133 performs an original data acquisition process. An example of the original data acquisition process has been described with reference to the flowchart of FIG.

[0249] (Step S1008) The learning unit 132 acquires a score (old score) of a date before the date of the j-th call history. The score here is, for example, an engagement score.

[0250] (Step S1009) The learning unit 132 acquires a score (new score) for a date subsequent to the date of the j-th call history. The score here is, for example, an engagement score.

[0251] (Step S1010) The learning unit 132 acquires the difference between the new score and the old score (new score - old score). This difference is information indicating the degree to which the organization has improved or deteriorated due to the transmission of the transmission information corresponding to the j-th transmission history. The learning unit 132 configures training data using the organization vector acquired in step S1007 and the difference between the new score and the old score.

[0252] The teacher data is, for example, a vector having an organization vector and transmission information corresponding to the j-th transmission history as explanatory variables, and a “new score−old score” as a response variable.

[0253] In addition, for example, when the "new score - old score" is a positive value, the training data is a positive example having an organizational vector and transmission information corresponding to the jth transmission history, and when the "new score - old score" is a negative value, the training data is a negative example having an organizational vector and transmission information corresponding to the jth transmission history.

[0254] Moreover, the teacher data is, for example, a vector having an organizational vector as an explanatory variable and having the transmission information corresponding to the j-th transmission history when "new score-old score" is positive as the objective variable.

[0255] (Step S1011) The learning unit 132 increments the counter j by 1. The process returns to step S1005.

[0256] (Step S1012) The learning unit 132 increments the counter i by 1. The process returns to step S1002.

[0257] (Step S1013) The learning unit 132 acquires learning information by using two or more pieces of teacher data acquired in step S1010.

[0258] The learning unit 132, for example, provides two or more pieces of teacher data to a machine learning learning module, executes the learning module, and acquires a learning model.

[0259] For example, the learning unit 132 configures correspondence information indicating the correspondence between the organizational vector of the teacher data and "new score - old score" for each of two or more teacher data. As a result, the learning unit 132 configures a correspondence table having two or more pieces of correspondence information.

[0260] The learning unit 132, for example, obtains an average vector of one or more tissue vectors where "new score - old score" is a positive value. Such a vector is a tissue vector of a positive example. The learning unit 132 also obtains an average vector of one or more tissue vectors where "new score - old score" is a negative value. Such a vector is a tissue vector of a negative example. Next, the learning unit 132 constructs a correspondence table having correspondence information that is the tissue vector of a positive example and correspondence information that is the tissue vector of a negative example.

[0261] (Step S1014) The learning unit 132 accumulates the learning information acquired in step S1013 in the learning information storage unit 115. Then, the process returns to the upper level process.

[0262] A specific example of the operation of the information system A in this embodiment will be described below. In the following table, "ID" is information for identifying a record.

[0263] Assume now that the questionnaire management table shown in FIG. 11 is stored in the questionnaire storage unit 111. The questionnaire management table is a table for managing questionnaires. Here, the questionnaire has a plurality of item information. The item information is information corresponding to the items of the questionnaire. The item information is information indicating the items of the questionnaire for members (employees in this case) of an organization (a company in this case). Here, the item information has "Question No.", "Type," "Factor," "Item," "Question: Expectation," and "Question: Satisfaction." "Question No." is an ID for identifying a question, and is an example of an item identifier. "Type" is information indicating the type of item, and here, it can be either a comprehensive item or an individual item. "Factor" is an intermediate concept of an item, and may be called an object. "Item" is information indicating the contents of an item. Note that "Item" may be considered as an item identifier. "Question: Expectation" is a question for acquiring the expectation. "Question: Satisfaction" is a question for acquiring the satisfaction. Also, it is assumed that the questionnaire storage unit 111 stores information indicating that each item is to be answered on a five-level scale from 1 to 5. In addition, "Type," "Factor," "Item," "Question: Expectation," and "Question: Satisfaction" in the questionnaire management table in Figure 6 are attribute values ​​of questions. Also, "Question: Expectation" and "Question: Satisfaction" can be simply called "Expectation" and "Satisfaction," respectively.

[0264] The outgoing information storage unit 112 stores an outgoing information management table shown in FIG. 12. The outgoing information management table has "ID", "major item", "outgoing identifier", "title information", and "outgoing content". "Major item" is a major item of outgoing information, and is information for grouping outgoing information. "Outgoing content" is information for identifying outgoing content information, and is a file name in this case. A file identified by a file name is stored in the outgoing information storage unit 112. FIG. 13 shows an example of a file entity, for example, "file11". The file here is also a template for information that is ultimately sent to members. In other words, a sender who sends information (for example, the head of an organization, a superior) obtains outgoing information in the form of a file, and then edits the file by replacing "〇〇", "◎◎", or "XX" with information unique to his or her organization, to obtain the information to be ultimately sent.

[0265] The organization information storage unit 113 stores the organization management table shown in FIG. 14. The organization management table manages one or more records having "ID", "organization identifier", "organization attribute value", "transmission history", and "reaction information". The "organization identifier" has "company name" and "department name". The "organization attribute value" has "industry type", "size information", "age composition", "gender composition", "settlement month", "general meeting month", and "sales". The "transmission history" has "transmission identifier" and "transmission date". The "reaction information" has "number of likes", "number of comments", "number of positives", and "number of negatives". The "size information" here can be, for example, "large company", "small and medium-sized enterprise", "individual business", etc. The "age composition" is the ratio of the composition of each age group, and the total is 100. The "gender composition" is the ratio of men and women, and the total is 100. The "number of likes" is the number of employees who pressed the "Like" button in response to the transmission of the corresponding transmission information. The "number of comments" is the number of comments in response to the transmission of the corresponding transmission information. The "number of positive comments" is the number of positive comments among the comments on the posting of the corresponding information. The "number of negative comments" is the number of negative comments among the comments on the posting of the corresponding information. Note that the technology (classification technology) for analyzing comments and other text and classifying them as either "positive" or "negative" is a publicly known technology, so a detailed explanation will be omitted.

[0266] The answer storage unit 114 stores an answer management table shown in FIG. 15. The answer management table includes "ID", "organization identifier", "survey implementation date", "employee identifier", "answer file", and "statistical result". The "organization identifier" includes "company name" and "department name". The "statistical result" includes "engagement score", "expectation variance", "satisfaction variance", and "average of (satisfaction - expectation)". The "answer file" is a file in which the answers of employees to the survey of FIG. 11 are stored. The "engagement score" is a score obtained using the answers of two or more employees for each organization identified by the organization identifier. The engagement score is obtained, for example, by the process described using the flowchart of FIG. 9. The "expectation variance" is the average value of the expectation variance of two or more employees. The "satisfaction variance" is the average value of the satisfaction variance of two or more employees. The "(satisfaction - expectation) average" is the average value of the average value of (satisfaction - expectation) of two or more employees. The statistical results obtained here are examples, and other statistical results may be used.

[0267] In the above situation, the following two concrete examples will be described. Concrete example 1 is an example in which a learning model is accumulated by learning processing. Concrete example 2 is an example in which a prediction process is performed using the learning model, and information to be transmitted is output using the prediction result.

[0268] (Example 1) Assume that the reception unit 12 of the information processing device 1 receives a learning instruction "<Industry> Trading company <Classification> Multi-value" from the terminal device 2. The learning instruction is for the industry "Trading company" and is an instruction to create a learning model for performing multi-value classification. Here, the multi-value classification is a change in the engagement score based on the transmitted information. The change in the engagement score is the difference between the engagement score after the transmission of the transmitted information and the engagement score before the transmission of the transmitted information. If the change in the engagement score is a positive value, it indicates that the transmission of the transmitted information has had a positive impact on the organization. On the other hand, if the change in the engagement score is a negative value, it indicates that the transmission of the transmitted information has had a negative impact on the organization.

[0269] Next, the learning unit 132 acquires the organizational response paired with "industry = trading company" (FIG. 15) and the organizational attribute value paired with "industry = trading company", and acquires the learning model "Model 1" using the information according to the operation of the flowchart in FIG. 10, and accumulates it in the learning information storage unit 115. The learning model "Model 1" is a learning model acquired by machine learning learning processing using two or more teacher data having a structure of, for example, vector (size information, age composition, gender composition, settlement month, general meeting month, sales, . . ., statistical results using organizational responses to a questionnaire at a time point prior to the time of the target transmission history and the closest time point (engagement score, expectation variance, satisfaction variance, average of (satisfaction - expectation), reaction information corresponding to the target transmission history (number of likes, number of comments, number of positives, number of negatives), . . ., transmission identifier of the target transmission history, engagement score after transmission - engagement score before transmission).

[0270] The post-call engagement score is the engagement score obtained using the organizational response to the survey at a point after the target calling history and the point closest to the time of the target calling history. The pre-call engagement score is the engagement score obtained using the organizational response to the survey at a point before the target calling history and the point closest to the time of the target calling history.

[0271] Also, it is assumed that the reception unit 12 of the information processing device 1 receives a learning instruction "<Industry> Trading company <Classification> Binary" from the terminal device 2. The learning instruction is for the industry "Trading company" and is an instruction to create a learning model for performing binary classification. The binary classification here is to classify the outgoing information as either "1" which indicates that the outgoing information had a positive impact on the organization, or "0" which indicates that the outgoing information did not have a positive impact on the organization.

[0272] Next, the learning unit 132 acquires the organizational response paired with "industry = trading company" (FIG. 15) and the organizational attribute value paired with "industry = trading company", and acquires the learning model "Model 2" using the information according to the operation of the flowchart in FIG. 10, and accumulates it in the learning information storage unit 115. The learning model "Model 2" is a learning model acquired by machine learning learning processing using two or more teacher data having a structure of, for example, vector (size information, age composition, gender composition, settlement month, general meeting month, sales, . . ., statistical results using organizational responses to a questionnaire at a time point prior to the time of the target transmission history and the closest time point (engagement score, variance of expectation, variance of satisfaction, average of (satisfaction - expectation)), reaction information corresponding to the target transmission history (number of likes, number of comments, number of positives, number of negatives), . . ., transmission identifier of the target transmission history, flag).

[0273] It should be noted that the flag here is a response variable, and is information that can take either a value of "1" if "engagement score after transmission - engagement score before transmission" is positive, or a value of "0" if it is not positive.

[0274] Similarly, it is assumed that the reception unit 12 of the information processing device 1 receives a learning instruction “<Classification> Multi-value” from the terminal device 2. The learning instruction is an instruction to create a learning model for performing multi-value classification regardless of organizational attribute values ​​such as industry.

[0275] Next, the learning unit 132 acquires all organizational responses (Figure 15) that can be used for learning and all organizational attribute values ​​that can be used for learning, and uses this information to acquire a learning model "Model 3" for multi-value classification in accordance with the operations of the flowchart in Figure 10, and stores this in the learning information storage unit 115.

[0276] Furthermore, it is assumed that the reception unit 12 of the information processing device 1 receives a learning instruction “<Classification> Binary” from the terminal device 2. The learning instruction is an instruction to create a learning model for performing binary classification regardless of organizational attribute values ​​such as industry.

[0277] Next, the learning unit 132 acquires all organizational responses (Figure 15) that can be used for learning and all organizational attribute values ​​that can be used for learning, and uses this information to acquire a learning model "Model 4" for binary classification in accordance with the operations of the flowchart in Figure 10, and stores this in the learning information storage unit 115.

[0278] It is assumed that the model management table shown in FIG. 16 has been constructed in the learning information storage unit 115 by the above processing. The model management table is a table that manages one or more records having "ID", "model condition", "model type", and "learning model". "Model condition" is a condition for using a learning model, and in this case, is a condition based on one or more organizational attribute values. "Model type" is a type of classification, and can be "binary" or "multiple values". "Learning model" is the name of the model. It is assumed that a file identified by "learning model" is stored in the learning information storage unit 115. It is assumed that the learning models "model 1", "model 2", "model 3", "model 4", etc. are the names of files in which models used for machine learning prediction processing are stored.

[0279] (Example 2) It is assumed that it is April 1, 2023, and the information processing device 1 receives survey responses (member responses) from all employees in a department named "B11" at company "C1," and stores them in the response management table (Figure 15).

[0280] Then, the statistical processing unit 131 determines that it is time to perform statistical processing on the organization response having two or more member responses. Note that the condition for starting statistical processing here is that member responses from all employees of the organization have been received.

[0281] Next, the statistical processing unit 131 performs statistical processing on the organizational responses of the company "C1" and department name "B11" according to the operation of the flowchart in FIG. 8, obtains the statistical results, and accumulates the statistical results in the response management table (FIG. 15).

[0282] Next, the processing unit 13 detects that the statistical processing by the statistical processing unit 131 has been completed, and determines that the start condition is met. In other words, the start condition here is that all employees of the organization have completed their responses and the statistical processing by the statistical processing unit 131 has been completed.

[0283] Next, the information acquisition unit 133 acquires a vector containing the original data of company "C1" and department name "B11" (size information, age composition, gender composition, fiscal year end month, general meeting month, sales, ..., engagement score, expectation variance, satisfaction variance, average of (satisfaction - expectation)) in accordance with the operation of the flowchart in Figure 4.

[0284] Next, the information acquisition unit 133 acquires the business type "Trading company" that is paired with the company "C1" and the department name "B11." The information acquisition unit 133 also acquires the learning models "Model 1" and "Model 2" that the business type "Trading company" satisfies.

[0285] Next, the information acquisition unit 133 constructs a vector of explanatory variables (size information, age composition, gender composition, fiscal month, general meeting month, sales, ..., engagement score, expectation variance, satisfaction variance, average (satisfaction - expectation), transmission identifier) ​​for each of two or more transmission identifiers in the transmission information management table (Figure 12), and provides the vector of explanatory variables and the learning model "Model 1" to a machine learning prediction module, executes the prediction module, and obtains a score for each transmission identifier. Then, the information acquisition unit 133 obtains the transmission identifier with the highest score. Here, it is assumed that the information acquisition unit 133 obtains the transmission identifier "11".

[0286] Furthermore, the information acquisition unit 133 constructs a vector of explanatory variables (size information, age composition, gender composition, settlement month, general meeting month, sales, ..., engagement score, expectation variance, satisfaction variance, average (satisfaction - expectation), transmission identifier) ​​for each of two or more transmission identifiers in the transmission information management table (Fig. 12), provides the vector of explanatory variables and the learning model "Model 2" to a machine learning prediction module, executes the prediction module, and acquires a flag of "1" indicating that the transmission information is valid or "0" indicating that the transmission information is not valid, and a likelihood (score), for each transmission identifier. Then, the information acquisition unit 133 acquires the transmission identifier whose flag, which is the prediction result, is "1" and whose likelihood is the highest. Here, it is assumed that the information acquisition unit 133 acquires the transmission identifier "12".

[0287] Next, the information acquisition unit 133 acquires the title information and the transmission content "file11" that are paired with the transmission identifier "11." The information acquisition unit 133 also acquires the title information and the transmission content "file12" that are paired with the transmission identifier "12."

[0288] Next, the information output unit 141 transmits the title information and the transmission content "file11" paired with the transmission identifier "11" and the title information and the transmission content "file12" paired with the transmission identifier "12" to the department manager of the department name "B11" in the company "C1". It is assumed that the contact information (email address, telephone number, or notification app ID) of the department manager is managed in association with the department name "B11" in the company "C1".

[0289] As described above, according to this embodiment, it is possible to appropriately propose information to be transmitted to members of an organization.

[0290] Furthermore, according to this embodiment, the statistical results of the response set can also be used to appropriately suggest information to be transmitted to members of an organization.

[0291] Furthermore, according to this embodiment, it is possible to appropriately propose information to be transmitted to members of an organization by using business information as well.

[0292] Furthermore, according to this embodiment, it is possible to appropriately suggest information to be transmitted to members of an organization by using reaction information as well.

[0293] Furthermore, according to this embodiment, it is possible to use a machine learning algorithm to appropriately suggest information to be transmitted to members of an organization.

[0294] Furthermore, according to this embodiment, a generative AI module can be used to appropriately suggest information to be disseminated to members of an organization.

[0295] Furthermore, according to this embodiment, the correspondence table can be used to appropriately suggest information to be transmitted to members of an organization.

[0296] The processing in this embodiment may be realized by software. This software may be distributed by software download or the like. 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 for realizing the information processing device 1 in this embodiment is the following program. That is, this program is a program for making a computer that can access a learning information storage unit in which learning information based on two or more teacher data is stored, the learning information having an organizational response that is a set of member responses based on responses to a questionnaire to two or more members belonging to an organization or a statistical result that is a result of statistical processing of the organizational response, and new transmission information regarding information newly transmitted after the response to the questionnaire, function as an information receiving unit that receives a target organizational response having two or more member responses that are responses to a questionnaire to a target member belonging to a target organization, an information acquiring unit that acquires transmission information using the target organizational response and the learning information, and an information output unit that outputs the transmission information.

[0297] Fig. 17 shows the appearance of a computer that executes the program described in this specification to realize the information processing device 1 and the like of the various embodiments described above. The above-mentioned embodiments can be realized by computer hardware and a computer program executed thereon. Fig. 17 is an overview of this computer system 300, and Fig. 18 is a block diagram of the system 300.

[0298] In FIG. 17, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0299] 18, computer 301 includes, in addition to CD-ROM drive 3012, MPU 3013, bus 3014 connected to CD-ROM drive 3012 etc., ROM 3015 for storing programs such as a boot-up program, RAM 3016 connected to MPU 3013 for temporarily storing instructions of application programs and providing temporary storage space, and hard disk 3017 for storing application programs, system programs, and data. Although not shown here, computer 301 may further include a network card for providing connection to a LAN.

[0300] A program for causing computer system 300 to execute the functions of information processing device 1 and the like of the above-mentioned embodiment may be stored on CD-ROM 3101, inserted into CD-ROM drive 3012, and further transferred to hard disk 3017. Alternatively, the program may be transmitted to computer 301 via a network (not shown) and stored on hard disk 3017. The program is loaded into RAM 3016 at the time of execution. The program may be loaded directly from CD-ROM 3101 or the network.

[0301] The program does not necessarily include an operating system (OS) or a third party program that causes the computer 301 to execute the functions of the information processing device 1 of the above-mentioned embodiment. The program only needs to include an instruction portion that calls appropriate functions (modules) in a controlled manner to obtain a desired result. How the computer system 300 operates is well known, and a detailed description will be omitted.

[0302] In addition, in the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmitting step (processing that is performed only by hardware).

[0303] The program may be executed by a single computer or a plurality of computers, that is, centralized processing or distributed processing may be performed.

[0304] Furthermore, in each of the above embodiments, it goes without saying that two or more communication means present in one device may be physically realized by one medium.

[0305] In each of the above embodiments, each process may be realized by centralized processing in a single device, or may be realized by distributed processing in a plurality of devices.

[0306] The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention. [Industrial Applicability]

[0307] As described above, the information processing device 1 according to the present invention has an effect of being able to appropriately propose information to be transmitted to members of an organization, and is useful as a server or the like that supports the development of an organization. [Explanation of symbols]

[0308] A. Information Systems 1. Information processing device 2 Terminal Equipment 11 Storage area 12 Reception 13 Processing section 14 Output section 21 Terminal storage section 22 Terminal Reception 23 Terminal Processing Section 24 Terminal transmitter 25 Terminal receiving section 26 Terminal Output Section 111 Questionnaire storage section 112 Transmission information storage section 113 Individual score table storage section 113 Organization Information Storage Section 114 Answer Storage Unit 115 Learning information storage unit 121 Information Reception Department 131 Statistical Processing Unit 132 Learning Department 133 Information Acquisition Department 141 Information output section

Claims

1. an information receiving unit that receives target organization responses having two or more member responses which are responses to a questionnaire given to target members belonging to the target organization; an information acquisition unit that acquires transmission information regarding information to be transmitted to the target member using learning information based on two or more teacher data including an organization response that is a collection of member responses that are responses to a questionnaire for two or more members belonging to an organization or a statistical result that is a result of statistical processing of the organization response, and new transmission information regarding information newly transmitted after the response to the questionnaire, and the target organization response; and an information output unit that outputs the transmitted information.

2. The method further includes an organization information storage unit in which organization information including transmission information regarding information transmitted in the past to the target members is stored in association with an organization identifier that identifies the target organization, The teacher data includes communication information including transmission information regarding information transmitted in the past to the two or more members belonging to the one organization, The information acquisition unit 2 . The information processing apparatus according to claim 1 , further comprising: acquiring the transmitted information using the learning information, the target organization's response, and communication information including transmitted information regarding information transmitted in the past to the target member.

3. The organizational information includes reaction information regarding reactions of the target members to the past transmissions, The information processing apparatus according to claim 2 , wherein the communication information includes reaction information regarding reactions of members to past communications.

4. a response storage unit for storing organizational responses having two or more member responses which are responses to the questionnaire by each member belonging to a single organization; A statistical processing unit that statistically processes the organizational responses and obtains statistical results, The teacher data includes a statistical result obtained by statistically processing the organizational responses of the one organization and the newly transmitted information, The information acquisition unit 2. The information processing apparatus according to claim 1, wherein the transmitted information is obtained by using a statistical result obtained by statistically processing the responses from the target organizations and the learning information.

5. The system further includes an organization information storage unit in which one or more pieces of organization information including business information related to the business of the organization or one or more organization attribute values ​​that are attribute values ​​of the organization are stored; The teacher data includes business information of the one organization or one or more organizational attribute values ​​of the one organization, The information acquisition unit 2 . The information processing apparatus according to claim 1 , further comprising: acquiring the transmitted information using business information of the target organization or one or more organizational attribute values ​​of the target organization, the target organization's response, and the learning information.

6. The learning information is a learning model acquired by performing a machine learning learning process using the two or more teacher data, The information acquisition unit The information processing device according to claim 1 , further comprising: a machine learning prediction process using the target organization response or the statistical result and the learning model, and acquiring the transmitted information.

7. The information acquisition unit An information processing device according to any one of claims 1 to 5, wherein the two or more teacher data are provided to a generative AI module, and the target organization responses or the statistical results are provided to the generative AI module to obtain the outgoing information.

8. The transmission information is a transmission identifier that identifies the transmission content or title information that is the title of the transmission content, The information acquisition unit Providing title information paired with the transmission identifier or the title information to a generation AI module, and acquiring transmission content information which is information indicating the transmission content; The information output unit is 8. The information processing apparatus according to claim 7, wherein said transmission content information is transmitted instead of said transmission information.

9. The teacher data is a vector having two or more pieces of information included in the organizational response or the statistical results as elements; The learning information is a correspondence table having two or more pieces of correspondence information indicating the correspondence between the vector and the newly transmitted information; The information acquisition unit 6. The information processing device according to claim 1, further comprising: determining from the correspondence table a vector that is most similar to a vector having as elements two or more pieces of information included in the target organization response received by the information receiving unit or the statistical result, which is a result of statistical processing of the target organization response, and acquiring the newly transmitted information that pairs with the vector.

10. The two or more teacher data are one or more positive examples that are training data corresponding to an improved organization in response to the new transmission; one or more negative examples that are training data corresponding to organizations that have not been improved in response to the new transmission; The information acquisition unit An information processing device as described in claim 1, which refers to an outgoing information storage unit in which two or more pieces of outgoing information are stored, and for each of the two or more pieces of outgoing information, obtains a flag indicating whether the organization will be improved or not using the outgoing information, the target organization's response or the statistical result, and the learning information, and obtains the outgoing information corresponding to the flag indicating that the organization will be improved.

11. Each of the two or more pieces of teacher data has the organizational response or the statistical result, the newly transmitted information, and a score indicating a degree to which the organization has improved in response to the newly transmitted information, The information acquisition unit An information processing device as described in claim 1, which refers to an outgoing information storage unit in which two or more pieces of outgoing information are stored, obtains a score for each of the two or more pieces of outgoing information using the outgoing information, the target organization's response or the statistical result, and the learning information, and obtains the outgoing information corresponding to the highest score.

12. Each of the two or more pieces of teacher data includes the organizational response or the statistical result, and the newly transmitted information when the organization is improved, The information acquisition unit The information processing apparatus according to claim 1 , further comprising: a processor for acquiring the transmitted information by using the target organization's response or the statistical result and the learning information.

13. An information processing method implemented by a learning information storage unit storing learning information based on two or more teacher data including organizational responses, which are a set of member responses based on responses to a questionnaire to two or more members belonging to an organization, or statistical results which are the results of statistical processing of the organizational responses, and newly transmitted information relating to information newly transmitted after the responses to the questionnaire, comprising: an information receiving unit; an information acquiring unit; and an information output unit, an information receiving step in which the information receiving unit receives a target organization response having two or more member responses which are responses to a questionnaire given to target members belonging to the target organization; an information acquisition step in which the information acquisition unit acquires transmission information using the target organization response and the learning information; and an information output step in which the information output unit outputs the transmission information.

14. a computer that can access a learning information storage unit that stores learning information based on two or more pieces of teacher data, the learning information having an organizational response that is a set of member responses based on responses to a questionnaire to two or more members belonging to an organization, or a statistical result that is a result of statistical processing of the organizational responses, and new transmission information regarding information newly transmitted after the responses to the questionnaire, an information receiving unit that receives target organization responses having two or more member responses which are responses to a questionnaire given to target members belonging to the target organization; an information acquisition unit that acquires transmission information using the target organization response and the learning information; A program for causing the information output unit to function as an information output unit for outputting the transmitted information.

Images