Psychological trait estimation system and method

Abstract

To estimate psychological characteristics of a user without requiring a user to perform an action different from an action induced by the information provided for a purpose different from psychological characteristic estimation.SOLUTION: A psychological characteristic estimation system provides information to induce a user to take an action for a purpose different from psychological characteristic estimation, receives measurement data on the action taken by the user induced by the provided information from a device having one or a plurality of sensors, and specifies data indicating designation of the user's intention and data indicating a related action on the basis of the measurement data. The action induced by the information includes the designation of the user's intention and the related actions, which are all or part of the actions excluding the designation of the user's intention. On the basis of data indicating the related action of one or each of a plurality of related actions, the system estimates psychological characteristics of the user and outputs data indicating the estimated psychological characteristics.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention generally relates to techniques for estimating psychological traits. [Background technology]

[0002] An example of a psychological characteristic is personality. Known personality estimation technologies include those disclosed in Patent Documents 1 and 2. The technology disclosed in Patent Document 1 estimates a user's personality based on the user's speech data. The technology disclosed in Patent Document 2 estimates a user's personality based on text data in addition to the user's speech data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] US2007 / 0271098 [Patent Document 2] US10,957,306 Summary of the Invention [Problem to be solved by the invention]

[0004] One possible approach is to build technology (for example, software or a system in which the software is implemented) that receives answer data representing answers to questions from one or more users and infers individual or organizational issues based on the answer data. To solve the inferred issues, users (individual users or users belonging to the organization whose issues have been inferred) must take the actions necessary to solve the issues. However, the user's personality influences whether or not they will take the necessary actions.

[0005] Therefore, it is conceivable to use the techniques disclosed in Patent Documents 1 and 2 to estimate the personality of a user.

[0006] However, in both of the techniques disclosed in Patent Documents 1 and 2, the user must respond to questions prepared for purposes other than personality estimation and must also take other actions, such as speaking, to estimate the personality. Not all users will necessarily take such other actions, and therefore the personalities of all users may not be estimated.

[0007] In addition to individual or organizational issues, there are also issues that require resolution or improvement through the actions of one or more users. Information inviting users to take action is provided, and issues are inferred based on user actions in response to the information (e.g., answers to questions). To resolve or improve the inferred issues, each user must take the necessary action. However, not all users will necessarily take an action other than the one they are invited to take. [Means for solving the problem]

[0008] A psychological trait estimation system is constructed. The system provides information inviting a user to take an action for a purpose other than psychological trait estimation, receives measurement data related to an action taken by the user in response to the provided information from a device having one or more sensors, and identifies user intention data and related action data based on the measurement data. The action invited by the information includes a designation of a user intention and a related action, which is all or part of the action excluding the designated user intention. The user intention data is data representing the designated user intention. The related action data is data representing the related action. The system estimates a user's psychological trait based on the related action data for each of one or more related actions, and outputs estimated psychological trait data, which is data representing the estimated psychological trait. [Effects of the Invention]

[0009] According to the present invention, it is possible to estimate a user's psychological characteristics without the user having to take any action other than the action prompted by information provided for a purpose other than psychological characteristic estimation. [Brief explanation of the drawings]

[0010] [Figure 1] 1 shows an example of the overall configuration of a system according to an embodiment. [Figure 2] The data stored in the storage device and the functions of the computing device are shown. [Figure 3] An example of the transition of the question and answer UI is shown below. [Figure 4] An example of calculation of an evaluation index is shown below. [Figure 5] 1 shows an example of a keyword table. [Figure 6] An example of a practical application of the psychological trait estimation system is shown. DETAILED DESCRIPTION OF THE INVENTION

[0011] In the following description, an "interface apparatus" may refer to one or more interface devices. The one or more interface devices may be at least one of the following: An I / O interface device is one or more I / O (Input / Output) interface devices. The I / O (Input / Output) interface devices are interface devices for at least one of an I / O device and a remote display computer. The I / O interface device for the display computer may be a communications interface device. The at least one I / O device may be a user interface device, for example, either an input device such as a keyboard and a pointing device, or an output device such as a display device. A communication interface apparatus that is one or more communication interface devices. The one or more communication interface devices may be one or more homogeneous communication interface devices (e.g., one or more NICs (Network Interface Cards)) or two or more heterogeneous communication interface devices (e.g., an NIC and an HBA (Host Bus Adapter)).

[0012] In the following description, "memory" refers to one or more memory devices, which are an example of one or more storage devices, and may typically be a primary storage device. At least one memory device in the memory may be a volatile memory device or a non-volatile memory device.

[0013] In the following description, a "persistent storage device" may refer to one or more persistent storage devices, which are an example of one or more storage devices. A persistent storage device may typically be a non-volatile storage device (e.g., an auxiliary storage device), and specifically may be, for example, a hard disk drive (HDD), a solid state drive (SSD), a non-volatile memory express (NVME) drive, or a storage class memory (SCM).

[0014] In the following description, the term "storage device" may refer to at least one of memory and persistent storage device.

[0015] Furthermore, in the following description, a "processor" may refer to one or more processor devices. The at least one processor device may typically be a microprocessor device such as a CPU (Central Processing Unit), but may also be another type of processor device such as a GPU (Graphics Processing Unit). The at least one processor device may be a single-core or multi-core. The at least one processor device may also be a processor core. The at least one processor device may also be a processor device in a broader sense, such as a circuit that is a collection of gate arrays written in a hardware description language that performs some or all of the processing (for example, an FPGA (Field-Programmable Gate Array), a CPLD (Complex Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit)).

[0016] In the following description, functions are sometimes described using the expression "yyy unit." However, the functions may be realized by one or more computer programs executed by a processor, by one or more hardware circuits (e.g., FPGAs or ASICs), or by a combination thereof. When a function is realized by a program executed by a processor, the specified processing is performed using a storage device and / or an interface device, etc., as appropriate, and therefore the function may be considered to be at least a part of the processor. Processing described using a function as the subject may be processing performed by a processor or a device having the processor. A program may be installed from a program source. The program source may be, for example, a program distribution computer or a computer-readable storage medium (e.g., a non-transitory storage medium). The description of each function is merely an example; multiple functions may be combined into one function, or one function may be divided into multiple functions.

[0017] In the following description, when elements of the same type are described without distinction, common reference symbols are used, and when elements of the same type are described with distinction, reference symbols are used.

[0018] An embodiment will be described below. In the following embodiment, personality may be used as an example of a psychological trait, but other types of psychological traits may also be used. Personality may have multiple personality components, such as neuroticism, openness, conscientiousness, extraversion, and agreeableness. Estimating the psychological trait may include calculating an evaluation value (score) for each personality component.

[0019] FIG. 1 shows an example of the overall configuration of a system according to an embodiment.

[0020] The psychological characteristic estimation system 100 communicates with the user device 130 and the administrator device 180 via a communication network 170. The communication network 170 is, for example, the Internet, a wide area network (WAN), or a local area network (LAN).

[0021] The user device 130 is an information processing terminal of the user 101, for example, a computer such as a personal computer or a smartphone. The user device 130 has one or more sensors that measure the actions of the user 101, and a display device 112. The one or more sensors are, for example, a camera 102 and a mouse 111. The mouse 111 is an example of a pointing device. The display device 112 may be a touch panel. The user 101 may also be a user who is a member of an organization.

[0022] The administrator device 180 is an information processing terminal of the administrator 151, for example, a computer such as a personal computer or a smartphone. The administrator device 180 has an input device 153 and a display device 152. The administrator 151 may be a member of the organization to which the user 101 belongs, and may be a person who formulates measures to solve organizational issues.

[0023] The psychological characteristic estimation system 100 includes an interface device 113, a storage device 114, and a computing device 115 connected thereto.

[0024] The interface device 113 communicates with the user device 130 and the administrator device 180 via a communication network 170. The storage device 114 stores computer programs executed by the arithmetic device 115 and data input and output by the arithmetic device 115. The arithmetic device 115 is a processor and executes computer programs.

[0025] The computing device 115 provides the user device 130 with information that invites the user 101 to take an action for a purpose other than psychological trait estimation. In other words, the "information" referred to here is information prepared for a purpose other than psychological trait estimation. In this embodiment, the information includes one (or more) questions and multiple options for answering the questions, and the information is provided by displaying the questions and the multiple options. The information may include a question but not multiple options, and the information may be provided by displaying a question (for example, the answer may be input by voice). Furthermore, the "question" provided in this embodiment is a question prepared for a purpose other than psychological trait estimation, such as a question prepared to estimate an organizational issue.

[0026] The computing device 115 receives measurement data from one or more sensors via the interface device 113 based on measurements by the one or more sensors related to actions taken by the user 101 prompted by the provided information. In this embodiment, examples of the one or more sensors are the mouse 111 and the camera 102. The measurement data includes measurement data from the mouse 111 and measurement data from the camera 102. In the following description, the measurement data from the mouse 111 is mainly taken as an example.

[0027] The computing device 115 identifies user intention data and related action data based on the measurement data. "Actions prompted by information" include a designation of a user intention and a related action, which is all or part of an action other than the designation of the user intention. In this embodiment, the designation of a user intention is answering a question (in other words, for example, an answer response to a digital questionnaire), but the designation of the user intention may vary depending on the information provided. In this embodiment, the related action is all or part of an action from when a question is provided to when the question is answered, but the related action may also vary depending on the designation of the user intention depending on the information provided. User intention data is data representing the designated user intention. Related action data is data representing a related action.

[0028] The arithmetic device 115 estimates the psychological characteristics of the user 101 based on the related action data for each of one or more related actions. Specifically, for example, each time a question is displayed, the user 101 answers the displayed question, and there is a related action for each pair of question and answer. There is related action data for each of the multiple related actions, and the arithmetic device 115 estimates the psychological characteristics of the user 101 based on the related action data for the multiple related actions.

[0029] The arithmetic device 115 outputs estimated psychological characteristic data, which is data representing the estimated psychological characteristic. For example, the arithmetic device 115 transmits the estimated psychological characteristic data to the administrator device 180, and the administrator device 180 displays the psychological characteristic represented by the estimated psychological characteristic data on the display device 152. In this way, the administrator 151 knows the estimated psychological characteristic of the user 101.

[0030] According to this embodiment, it is possible to estimate the psychological trait of the user 101 without the user 101 taking any action other than the action (for example, answering a question) that is prompted by information that has been prepared and provided for a purpose other than psychological trait estimation. Specifically, according to this embodiment, there is no need to prepare information such as a question dedicated to psychological trait estimation, and the user 101 does not need to take the above-mentioned "other action," for example, an action in response to information such as a question dedicated to psychological trait estimation.

[0031] The arithmetic device 115 may output the user intention data to a computer system that performs processing for its intended purpose (in other words, for a purpose other than psychological characteristic estimation) based on the user intention.

[0032] This embodiment will be described in detail below.

[0033] 2 shows the data stored in the storage device 114 and the functions of the arithmetic unit 115. In this embodiment, "DB" is an abbreviation for database. The data does not have to be structured data like a database.

[0034] The storage device 114 stores an answer DB 231, an estimation DB 232, a psychological characteristic DB 233, a provided information DB 234, and an integrated DB 235. The answer DB 231 is a DB that stores answer data (data representing answers to questions). The estimation DB 232 is a DB that stores data used to estimate psychological characteristics (for example, one or more models such as regression equations). The psychological characteristic DB 233 is a DB that stores estimated psychological characteristic data (data representing estimated psychological characteristics). The provided information DB 234 is a DB that stores provided information (in this embodiment, information including a question and multiple options). The integrated DB 235 is a DB that stores integrated data of answer data and estimated psychological characteristic data.

[0035] The calculation device 115 executes the computer program to realize an input unit 210, a calculation unit 220, and an output unit 240. The input unit 210 has a response input unit 211 and a setting input unit 212. The calculation unit 220 has a response data extraction unit 222, a related action data extraction unit 223, a psychological characteristic estimation unit 224, a psychological characteristic setting unit 225, an information setting unit 226, and an output calculation unit 227.

[0036] Below, an example of the functions realized by the arithmetic unit 115 and the processing performed in this embodiment will be described.

[0037] The setting input unit 212 receives setting data (data to be set) from the administrator device 180. The setting data includes setting data related to psychological characteristics (for example, data representing a plurality of personality components) and setting data related to information to be provided (for example, data including a question and a plurality of options for each question). The psychological characteristic setting unit 225 stores the setting data related to psychological characteristics in the psychological characteristic DB 233. The information setting unit 226 stores the setting data related to information to be provided in the provided information DB 234.

[0038] The output calculation unit 227 acquires information to be provided based on data in the provided information DB 234. For example, the output calculation unit 227 generates a question and answer user interface (UI) 112 illustrated in FIG. 3 based on data in the provided information DB 234. The output unit 240 provides the information to be provided (question and answer UI 112) to the user device 130. The information to be provided (question and answer UI 112) is displayed on the display device 112. The information to be provided may include, for example, a question ID, numbers of multiple options, and location information (e.g., coordinates) of each option.

[0039] The answer input unit 211 receives, from the user device 130, measurement data relating to actions taken by the user 101 in response to the information provided by the output unit 240. The measurement data includes answer data and related action data.

[0040] The answer data may include the ID of the question and the number of the option selected as the answer. The answer data extraction unit 222 extracts the answer data from the measurement data and stores the extracted answer data in the answer DB 231. Note that the answer data may be identified from the measurement data (for example, the answer may be identified from the relationship between cursor position information when the mouse cursor is pressed and position information of the option).

[0041] The related action may be an action leading to an answer to a question (an example of specifying a user's intention). Even if the answer is the same, the action leading to the answer is affected by the psychological characteristics of the user 101. Because related action data representing such actions is used for psychological characteristic estimation, it is expected that the psychological characteristics can be accurately estimated even without dedicated questions or user actions for psychological characteristic estimation. Specifically, for example, the related action data may include, for each of one or more action types, an action value representing the value of the action belonging to the action type. The one or more action values ​​included in the related action data may include at least one of the trajectory of the mouse cursor leading to the answer, coordinates, movement distance, number of selections of options, and time from the start of movement to the answer. Such action values ​​are considered to be affected by the psychological characteristics of the user 101, and therefore, it is expected that the psychological characteristics can be accurately estimated. Note that the sensor may be other types of sensors, such as a microphone or a motion sensor, instead of or in addition to at least one of the mouse 111 and the camera 102. In other words, the multiple sensors may be two or more of a pointing device, a touch panel, a camera, a microphone, and a wearable sensor. The measurement data is not limited to terminal operations such as mouse 111 and keyboard operations, but may also include at least some of log data related to touch panel operations, video and audio data during answering questions, and biological data such as electroencephalograms, cerebral blood flow, heart rate, and respiration. It is expected that the use of related action data identified based on the measurement data from the multiple sensors will enable more accurate estimation of psychological characteristics.

[0042] The related action data extraction unit 223 extracts related action data from the measurement data. The related action data may be identified from the measurement data (for example, the related action data may be generated based on various values ​​included in the measurement data). Furthermore, the related action data may be stored in the storage device 114 for each answer to a question.

[0043] The psychological characteristic estimation unit 224 estimates the psychological characteristic of the user 101 based on the associated action data for each of one or more associated actions, and stores estimated psychological characteristic data representing the estimated psychological characteristic in the psychological characteristic DB 233.

[0044] The output calculation unit 227 generates integrated data for the user 101 from the estimated psychological characteristic data in the psychological characteristic DB 233 and the answer data (answer data for each answer to a question) in the answer DB 231, and stores the integrated data in the integrated DB 235. The output unit 240 outputs the integrated data for the user 101 to the administrator device 180. The integrated data includes, for example, answer data for each answer to a question and estimated psychological characteristic data. The answers to each question and the estimated psychological characteristics are displayed on the display device 152.

[0045] The output data does not have to be integrated data. For example, the answer data (an example of user intention data) and the estimated psychological characteristic data may be output at different times. The output destination of the answer data and the output destination of the estimated psychological characteristic data may be the same or different. The estimated psychological characteristic data may be output to the user device 130 instead of or in addition to the administrator device 180. This allows the user 101 to know the estimated psychological characteristic of the user 101 by answering the question.

[0046] FIG. 3 shows an example of transition of the display on the user device 130.

[0047] A question and answer UI 112 is prepared for each question. The question and answer UI 112 is typically a GUI (Graphical User Interface) that displays one question and multiple options. The question and answer UI 112 also has a "Next" button 310 that specifies proceeding to the next question. The position of the "Next" button 310 corresponds to the start position of the mouse cursor 300. In other words, the following is performed for each question, from the first question to the last. (x1) The question and answer UI 112 is displayed, and the user 101 selects (clicks) a desired option from multiple options. The user 101 can select an option in place of the option he or she has selected (correct the selection) before pressing (clicking) the "Next" button 310. (x2) The user 101 presses the "Next" button 310. If there are still questions, the process returns to (x1).

[0048] 3, the following occurs: The user 101 moves the mouse cursor 300 to select the leftmost option on the question and answer UI 112A. A trajectory 320A of the mouse cursor 300 is measured on the user device 130. The user 101 selects the leftmost option on the question and answer UI 112A and presses the "Next" button 310. This causes the display to transition to the display of the next question, specifically, the question and answer UI 112B. The user 101 moves the mouse cursor 300 to select the rightmost option on the question and answer UI 112B. A trajectory 320B of the mouse cursor 300 is measured on the user device 130.

[0049] The prepared questions may all be unrelated to psychological traits, or may include questions related to psychological traits. In other words, regardless of the type of each of the multiple questions, the psychological traits of user 101 can be estimated from actions including answers to the questions.

[0050] The psychological characteristic estimation unit 224 calculates an evaluation value for each of one or more evaluation indexes and estimates the psychological characteristic of the user 101 based on the evaluation values ​​of the one or more evaluation indexes. For each of one or more evaluation indexes, the psychological characteristic estimation unit 224 calculates multiple parameter values ​​based on the related action data and calculates an evaluation value for the evaluation index based on the multiple parameter values. Perceptual and / or motor components are relatively reduced from the calculated multiple parameter values ​​based on information characteristics, which are characteristics of the provided information. This is expected to improve the accuracy of estimating the psychological characteristic. Note that, for example, at least one of the following may be used as the evaluation index: first reaction time (the time from when the question and answer UI 112 is displayed to when the mouse cursor 300 starts moving), answer time (the total time from when the question and answer UI 112 is displayed to when the answer is completed), cursor movement distance (the distance the mouse cursor 300 moves from the “Next” button 310 to when an option is selected), and number of answer selections (the total number of times an option is selected from when the question and answer UI 112 is displayed to when the “Next” button 310 is pressed).

[0051] The psychological trait estimation unit 224 may calculate an evaluation value for each of one or more evaluation indexes and calculate an evaluation value (score) for each of the multiple personality components based on the evaluation values ​​of the one or more evaluation indexes. Specifically, for example, one or more personality components may be associated with each evaluation index, and the evaluation value calculated for the evaluation index may be reflected in each of the one or more personality components associated with the evaluation index. The estimated psychological trait may include an evaluation value calculated for each of the multiple personality components. In other words, the estimated psychological trait may include one or both of a qualitative psychological trait and a quantitative psychological trait.

[0052] For each of the multiple evaluation indexes, the calculation of the evaluation index may be performed by a method appropriate to the evaluation index. For example, a model such as a regression equation (e.g., a machine learning model) may be prepared for each evaluation index, and the evaluation index may be calculated using the model.

[0053] FIG. 4 shows an example of calculation of one evaluation index.

[0054] In Figure 4, the evaluation index is the first reaction time. To calculate the evaluation value of the first reaction time, a model based on the answer response model of Miller et al. is adopted. In the model shown in Figure 4, R k is the evaluation value of the first reaction time. A is a parameter (component) related to perception. B is a parameter related to thinking. C is a parameter related to movement. X is a parameter related to error. Such a model may be prepared for each evaluation index.

[0055] The information characteristic includes the length of the question (an example of information). The "question length" may be the duration of the audio output when the question is output aloud, but in this embodiment, it is the number of characters that make up the question. Generally, the more characters there are, the longer it takes to understand the question, and therefore, it is thought that the first reaction time tends to be longer regardless of the psychological characteristic. The psychological characteristic estimation unit 224 determines the value of A (the value of a parameter related to perception) based on the length of the question. Specifically, for example, there is a first reaction time for each of multiple questions, and the psychological characteristic estimation unit 224 corrects each of the multiple first reaction times based on the number of characters in the question corresponding to that first reaction time (in other words, it reduces (e.g., removes) the influence of the number of characters from that first reaction time), and determines the value of A based on the multiple corrected first reaction times. This makes the value of A appropriate, and therefore, R, which is an element of psychological characteristic estimation, is k This improves the accuracy of the estimation of psychological characteristics, and is therefore expected to improve the accuracy of the estimation of psychological characteristics.

[0056] The value of B (parameter value related to thinking) is a parameter value based on the standard deviation of the action value corresponding to the parameter value after correction. Specifically, for example, the psychological characteristic estimation unit 224 sets the value of B to a value based on the result of removing the correlation between the average value and standard deviation of the first reaction time from the correlation between the average value and standard deviation of the first reaction time and the psychological characteristic. This makes the value of B appropriate, and therefore, R, which is an element of the psychological characteristic estimation, k This improves the accuracy of the estimation of psychological characteristics, and is therefore expected to improve the accuracy of the estimation of psychological characteristics.

[0057] The information characteristic includes the position of each of the multiple options. In general, it is considered that the farther the position of the selected option is from the "Next" button 310, the longer the first reaction time tends to be. The psychological characteristic estimation unit 224 determines the value of C (the value of a parameter related to movement) based on the position of the selected option. Specifically, for example, there is a first reaction time for each of the multiple questions, and the psychological characteristic estimation unit 224 corrects each of the multiple first reaction times based on the position of the option corresponding to that first reaction time (in other words, reduces (for example, removes) the influence of the option position from that first reaction time), and determines the value of C based on the multiple corrected first reaction times. This makes the value of C appropriate, and therefore, R, which is an element of psychological characteristic estimation, becomes k This improves the accuracy of the estimation of psychological characteristics, and is therefore expected to improve the accuracy of the estimation of psychological characteristics.

[0058] B Δ in the model shown in Figure 4 k The value of may be determined based on the personality component. For example, Δ k The value of may be determined based on the ratio of questions belonging to the personality component to the plurality of questions.

[0059] A "question belonging to a personality component" is, for example, a question including a keyword belonging to a personality component. Specifically, for example, as shown in FIG. 5, a keyword table in which keywords are registered for each personality component may be stored in advance in, for example, the estimation DB 232. The keyword table is an example of data representing keywords related to psychological traits, and represents keywords by personality component, for example. In estimating the psychological trait of the user 101, the psychological trait estimation unit 224 may assign a higher weight to questions including keywords related to psychological traits than to questions not including keywords related to psychological traits. For example, in estimating the psychological trait, the psychological trait estimation unit 224 may use related action data related to answers to questions including keywords related to psychological traits, but not use related action data related to answers to questions not including keywords related to psychological traits. This is expected to enable accurate estimation of psychological traits.

[0060] The process using the keyword table may be the following process instead of or in addition to the evaluation value calculation using the model illustrated in FIG. 4 . That is, the psychological characteristic estimation unit 224 may determine, for each of a plurality of questions represented by the provided information DB 234, whether the question includes a keyword represented by the keyword table, and classify the question based on the determination result. For example, if a question includes one or more keywords, the personality component to which the keywords belong may be associated with the question in the classification of the question. Multiple personality components may be associated with one question, or the personality component to which the most keywords belong among the keywords included in the question may be associated. A question associated with a personality component may be a question with a relatively high weight. When calculating an evaluation value for each personality component, the psychological characteristic estimation unit 224 may use related action data related to answers to questions associated with the personality component, and may not use related action data related to answers to questions not associated with the personality component. This is expected to allow for the calculation of an appropriate evaluation value for each personality component.

[0061] FIG. 6 shows an example of a practical application of the psychological characteristic estimation system 100.

[0062] A survey is conducted by each of multiple users belonging to the same organization. Specifically, for example, multiple users each answer a plurality of questions prepared for estimating organizational issues. Data representing each user's survey answer (data representing the answer for each question) is output by the output unit 240, and the data is input to an organizational issue estimation function (a function for estimating organizational issues). The organizational issue estimation function estimates organizational issues based on the data representing each user's survey answer, and outputs estimated organizational issue data, which is data representing the estimated organizational issue, to a policy planning function (a function for planning policies). At least one of the organizational issue estimation function and the policy planning function may be a function within the psychological trait estimation system 100, or may be a function outside the psychological trait estimation system 100 (for example, a physical computer system or a logical computer system such as a cloud computing service).

[0063] For each user, the related action data extraction unit 223 extracts related action data for each answer to a question from the measurement data regarding the survey answers (answers to each question), and the psychological trait estimation unit 224 estimates a psychological trait based on the related action data for each answer. The output unit 240 outputs the estimated psychological trait data for each user to the policy planning function.

[0064] The policy planning function plans policies to solve the estimated organizational issues based on the estimated organizational issue data. The policies include actions to be taken by users belonging to the organization. For each user belonging to the organization, the policy planning function generates a proposal for the user to implement the actions to be taken based on the psychological characteristics represented by the estimated psychological characteristic data corresponding to that user. The proposal is an example of content based on psychological characteristics. In other words, the policy planning function is an example of a function that determines content to be output based on psychological characteristics.

[0065] According to such a practical application, the possibility that each user will take action to solve organizational problems can be increased by the technical means of the psychological trait estimation system 100.

[0066] The psychological trait estimation system 100 can also be applied to other practical applications. For example, the psychological trait estimation system 100 may determine content to be output based on the estimated psychological trait, or may output estimated psychological trait data to a function that determines content to be output based on the psychological trait. This allows the user to receive content that matches the user's psychological trait.

[0067] Although one embodiment has been described above, this is merely an example for explaining the present invention, and the scope of the present invention is not limited to this embodiment. The present invention can be implemented in various other forms.

[0068] For example, the psychological trait estimation unit 224 may perform principal component analysis based on a plurality of action values ​​included in the related action data of the answers to each question, using components correlated with pre-specified psychological trait categories as principal components, and estimate the psychological trait of the user 101 based on the results of the principal component analysis. This is expected to result in a more accurate estimation of the psychological trait based on a higher correlation. Specifically, for example, the following may be performed.

[0069] That is, the psychological characteristic estimation unit 224 may extract multiple behavioral features based on multiple action values ​​of the action data related to answers to multiple questions. The multiple behavioral features may be at least some of the average and standard deviation of the answer time and answer confirmation time for each question, the answer time to the first question (time corrected for the length of the question), the average and standard deviation of the first answer time (time corrected for the length of the question and the distance between the answer options), the average and standard deviation of the cursor movement amount, or the movement amount to the first question. The multiple behavioral features may also include at least some of the evaluation values ​​of the above-mentioned multiple evaluation indexes.

[0070] The psychological characteristic estimation unit 224 may calculate the direction in which the variance from the mean value is maximum (first principal component), calculate the point orthogonal to the first principal component and where the variance is maximum (second principal component), and repeat the calculation of the point orthogonal to the previous principal component and where the variance is maximum for the number of data dimensions (nth principal component). i The vector w that has the maximum inner product with k The direction of maximum dispersion is w k=1 =argmax{Σ i (xi·w) 2}, t k(i) =xi·w k , well, vector t (i) =(t1,…,t k ) (i) can be the principal component scores. [Explanation of symbols]

[0071] 100: Psychological trait estimation system

Claims

1. an interface device connected to a user device, the user device being a device having one or more sensors; a computing device connected to the interface device; Equipped with the computing device provides, to the user device, information inviting the user to take an action for a purpose other than the psychological characteristic estimation; the computing device receives, from the user device through the interface device, measurement data based on measurements by the one or more sensors related to actions taken by the user in response to the provided information; The computing device identifies user intention data and related action data based on the measurement data, The action prompted by the information includes a designation of a user's intention and a related action that is all or part of the action excluding the designation of the user's intention; the user intention data is data representing the specified user intention, The related action data is data representing related actions, and includes, for each of one or more action types, an action value representing a value of an action belonging to the action type; the arithmetic device calculates a plurality of parameter values ​​for each of one or a plurality of evaluation indexes based on related action data for each of one or a plurality of related actions, calculates an evaluation value for the evaluation index based on the plurality of parameter values, and estimates a psychological characteristic of the user based on the evaluation value of the one or a plurality of evaluation indexes; the computing device outputs estimated psychological characteristic data that is data representing the estimated psychological characteristic; For each of the one or more evaluation indexes, The calculated parameter values ​​include a relative reduction in perception-related components relative to thought-related components based on information characteristics of the provided information, including the length of the information; and / or the information includes one or more questions and a plurality of answer options for each of the one or more questions, the provision of the information includes displaying the plurality of options, the designation of the user's intention is selection of at least one option from the plurality of options, and from the calculated plurality of parameter values, a component related to movement is reduced relatively to a component related to thought based on information characteristics that are characteristics of the provided information and include the position of each of the plurality of options; Psychological trait estimation system.

2. The related action is an action leading up to the designation of the user's intention. The psychological characteristic estimation system according to claim 1 .

3. providing the information is displaying the information; The one or more action values ​​included in the related action data include at least one of a trajectory of a cursor, coordinates, a moving distance, and a time from the start of the movement to the designation of the user's intention. The psychological characteristic estimation system according to claim 2 .

4. The plurality of sensors are two or more sensors selected from the group consisting of a pointing device, a touch panel, a camera, a microphone, and a wearable sensor. The psychological characteristic estimation system according to claim 1 .

5. Among the calculated parameter values, the parameter value related to thinking is a value based on a result of removing a correlation between an average value and a standard deviation of the first reaction time from a correlation between an average value and a standard deviation of the first reaction time and a psychological characteristic, for an action value related to the first reaction time as the action value. The psychological characteristic estimation system according to claim 1 .

6. The one or more action values ​​included in the related action data include at least one of a cursor trajectory, coordinates, movement distance, number of selections of options, and time from the start of movement to the designation of the user's intention. The psychological characteristic estimation system according to claim 1 .

7. the calculation device performs a principal component analysis based on a plurality of action values ​​included in the related action data, with components correlated with pre-specified psychological trait categories as principal components, and estimates the psychological trait of the user based on a result of the principal component analysis. The psychological characteristic estimation system according to claim 1 .

8. the information includes one or more questions; the computing device, in estimating the psychological characteristics of the user, weights a question including a keyword related to the psychological characteristics relatively higher than a question not including a keyword related to the psychological characteristics; The psychological characteristic estimation system according to claim 1 .

9. the computing device outputs the estimated psychological characteristic data to a function for determining content to be output based on the psychological characteristic; The psychological characteristic estimation system according to claim 1 .

10. The computer provides information inviting the user to take an action for a purpose other than the psychological characteristic estimation to a user device that is a device having one or more sensors; a computer receiving measurement data from the user device based on measurements by the one or more sensors related to actions taken by the user prompted by the provided information; The computer identifies the user intention data and the related action data based on the measurement data, The action prompted by the information includes a designation of a user's intention and a related action that is all or part of the action excluding the designation of the user's intention; the user intention data is data representing the specified user intention, The related action data is data representing related actions, and includes, for each of one or more action types, an action value representing a value of an action belonging to the action type; a computer calculates a plurality of parameter values ​​for each of one or a plurality of evaluation indexes based on related action data for each of one or a plurality of related actions, calculates an evaluation value for the evaluation index based on the plurality of parameter values, and estimates a psychological characteristic of the user based on the evaluation value of the one or a plurality of evaluation indexes; For each of the one or more evaluation indexes, The calculated parameter values ​​include a relative reduction in perception-related components relative to thought-related components based on information characteristics of the provided information, including the length of the information; and / or the information includes one or more questions and a plurality of answer options for each of the one or more questions, the provision of the information includes displaying the plurality of options, the designation of the user's intention is selection of at least one option from the plurality of options, and from the calculated plurality of parameter values, a component related to movement is reduced relatively to a component related to thought based on information characteristics that are characteristics of the provided information and include the position of each of the plurality of options, The computer outputs estimated psychological characteristic data, which is data representing the estimated psychological characteristic. Psychological characteristics estimation method.

11. providing information to a user device, which is a device having one or more sensors, that invites the user to take an action for a purpose other than the psychological characteristic estimation; receiving measurement data from the user device based on measurements by the one or more sensors related to actions taken by the user in response to the provided information; Based on the measurement data, user intention data and related action data are identified; The action prompted by the information includes a designation of a user's intention and a related action that is all or part of the action excluding the designation of the user's intention; the user intention data is data representing the specified user intention, The related action data is data representing related actions, and includes, for each of one or more action types, an action value representing a value of an action belonging to the action type; calculating a plurality of parameter values ​​for each of one or a plurality of evaluation indexes based on related action data for each of one or a plurality of related actions, calculating an evaluation value for the evaluation index based on the plurality of parameter values, and estimating psychological characteristics of the user based on the evaluation value of the one or a plurality of evaluation indexes; For each of the one or more evaluation indexes, The calculated parameter values ​​include a relative reduction in perception-related components relative to thought-related components based on information characteristics of the provided information, including the length of the information; and / or the information includes one or more questions and a plurality of answer options for each of the one or more questions, the provision of the information includes displaying the plurality of options, the designation of the user's intention is selection of at least one option from the plurality of options, and from the calculated plurality of parameter values, a component related to movement is reduced relatively to a component related to thought based on information characteristics that are characteristics of the provided information and include the position of each of the plurality of options, outputting estimated psychological characteristic data which is data representing the estimated psychological characteristic; A computer program that causes a computer to do something.

Images