Character traits estimation system and method
The system estimates psychological characteristics by analyzing behavioral data from actions unrelated to estimation, enhancing features over time, addressing the limitations of existing methods by improving accuracy and efficiency.
Patent Information
- Application Number
- JP2023080980
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-16
- Publication Date
- 2024-11-28
AI Technical Summary
Existing methods for estimating psychological characteristics require subjects to perform additional actions beyond answering questions, leading to incomplete or time-consuming data collection.
A system that invites subjects to perform actions unrelated to psychological estimation, using sensors to capture behavioral data, which is analyzed to estimate psychological characteristics, enhancing features based on elapsed time and environmental adjustments.
Enables accurate estimation of psychological characteristics without dedicated actions, improving accuracy by leveraging enhanced behavioral features and time-sensitive responses.
Smart Images

Figure 2024165106000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates generally to techniques for estimating person characteristics. [Background technology]
[0002] One example of a person characteristic is a psychological characteristic (personality). As a technique for estimating a psychological characteristic, for example, a technique disclosed in Patent Document 1 is known. The technique disclosed in Patent Document 1 estimates a user's psychological characteristic based on text data in addition to speech data of the user.
[0003] A known technique for estimating a person's psychological state is disclosed in Patent Document 2. The technique disclosed in Patent Document 2 estimates a user's psychological state based on the user's vital sign data. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] US10,957,306 [Patent Document 2] JP 2022-179438 A Summary of the Invention [Problem to be solved by the invention]
[0005] In the technology disclosed in Patent Document 1, the subject must respond to questions prepared for a purpose other than psychological trait estimation and must take other actions such as speaking in order to estimate the psychological trait. The subject may not necessarily take such other actions, and therefore the psychological trait of the subject may not necessarily be estimated. Another problem is that it takes a lot of time to create text data as input.
[0006] The technique disclosed in Patent Document 2 is capable of estimating a temporary psychological state, but is unable to estimate a person's unique psychological characteristics. [Means for solving the problem]
[0007] The system provides the subject device, which is a device having one or more sensors, with provided information including invitation information inviting the subject to an action for a purpose other than psychological characteristic estimation. The system receives measurement data based on measurements by one or more sensors from the subject device related to an action taken by the subject invited by the provided invitation information, and identifies subject intention data and related behavior data based on the measurement data. The action invited by the invitation information includes a designation of the subject intention and a related behavior that is all or a part of the action excluding the designation of the subject intention. The subject intention data is data representing the designated subject intention. The related behavior data is data representing the related behavior. The system calculates one or more behavior feature amounts based on the related behavior data for each of the one or more related behaviors, estimates the psychological characteristic of the subject based on the one or more behavior feature amounts, and outputs data representing the estimated psychological characteristic. Each of the one or more behavior feature amounts used to estimate the psychological characteristic of the subject is at least a part of the adjusted information of the provided information, and / or a behavior feature amount enhanced according to the elapsed time for the behavior feature amount. Effect of the Invention
[0008] According to the present invention, it is possible to estimate a psychological characteristic of a subject without the subject performing a dedicated behavior for estimating the psychological characteristic. [Brief description of the drawings]
[0009] [Figure 1] 1 shows an example of the overall configuration of a system according to a first embodiment. [Diagram 2] 2 shows data and functions in the entire system according to the first embodiment. [Diagram 3] 2 shows an example of the flow of processing performed in the first embodiment. [Figure 4A] 4 shows examples of people positions in the camera frame. [Figure 4B] 4 shows examples of people positions in the camera frame. [Figure 4C] 4 shows examples of people positions in the camera frame. [Diagram 5] 13 shows an example of the relationship between feature amount categories, behavior feature amounts, and related behavior values. [Figure 6A] 1 shows an example of a screen with a first background luminance. [Figure 6B] 4 shows an example of a screen with a second background luminance. [Figure 7] 13 shows data and functions in the entire system according to the second embodiment. [Figure 8] 13 shows data and functions in the entire system according to the third embodiment. [Figure 9] 13 shows an example of a keyword table according to the fourth embodiment. [Figure 10] 1 shows an example of a practical application of the human characteristic estimating system according to the first to fourth embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0010] In the following description, an "interface unit" 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 apparatus which is one or more I / O (Input / Output) interface devices. The I / O (Input / Output) interface devices are interface devices to at least one of an I / O device and a remote display computer. The I / O interface device to 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 which 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., a NIC and an HBA (Host Bus Adapter)).
[0011] In the following description, a "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.
[0012] In the following description, a "persistent storage device" may be one or more persistent storage devices, which are an example of one or more persistent storage devices. A persistent storage device may typically be a non-volatile storage device (e.g., an auxiliary storage device), and more 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).
[0013] Also, in the following description, "storage device" may be at least memory, including memory and persistent storage device.
[0014] Furthermore, in the following description, a "processor" may be 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 other types of processor devices 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 be a processor core. The at least one processor device may also be a broader processor device such as a circuit that is a collection of gate arrays written in a hardware description language that performs part or all of the processing (e.g., an FPGA (Field-Programmable Gate Array), a CPLD (Complex Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit)).
[0015] In the following description, functions may be described using the expression "yyy unit", but the functions may be realized by one or more computer programs being executed by a processor, or by one or more hardware circuits (e.g., FPGA or ASIC), or by a combination thereof. When a function is realized by a program being executed by a processor, the function may be at least a part of the processor, since the specified processing is performed using a storage device and / or an interface device, etc., as appropriate. Processing described with 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 storage medium (e.g., a non-transitory storage medium) that can be read by a computer. The description of each function is an example, and multiple functions may be combined into one function, or one function may be divided into multiple functions.
[0016] In addition, in the following description, when describing elements of the same type without distinguishing between them, common reference symbols will be used, and when describing elements of the same type without distinguishing between them, reference symbols will be used.
[0017] Several embodiments will be described below. In the following embodiments, psychological characteristics are adopted as an example of personal characteristics, and the psychological characteristics are estimated. [First embodiment]
[0018] FIG. 1 shows an example of the overall configuration of a system according to the first embodiment.
[0019] The personal characteristic estimating system 100 communicates with the subject 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).
[0020] The subject device 130 is an information processing terminal of the subject 101, for example, a computer such as a personal computer or a smartphone. The subject device 130 has one or more sensors that measure the behavior of the subject 101, and a display device 112. The one or more sensors are, for example, a camera 102, an input device 111 (for example, a keyboard and a pointing device), and a microphone 11. Instead of or in addition to the input device 111, the display device 112 may be a touch panel. Furthermore, the subject 101 may be, for example, an applicant for an online interview.
[0021] 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, for example, an interviewer in an online interview.
[0022] The human characteristic estimating system 100 includes an interface device 113, a storage device 114, and a computing device 115 connected thereto.
[0023] The interface device 113 communicates with the subject 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.
[0024] The computing device 115 provides the subject device 130 with provision information, which is information including invitation information that invites the subject 101 to take action for a purpose other than psychological characteristic estimation. The invitation information may include a plurality of questions (or one). Specifically, for example, the invitation information may include a plurality of questions (or one) provided in voice and / or text by executing an AI (Artificial Intelligence) or other program as an interviewer, or content as a virtual robot such as an avatar that provides the questions. The content may include text expressing the questions and other types of information (e.g., figures). The "questions" provided in this embodiment may be general questions in an interview and may not include questions prepared for psychological characteristic estimation.
[0025] The computing device 115 receives measurement data from one or more sensors via the interface device 113, the measurement data being based on measurements by the one or more sensors relating to an action taken by the subject 101 in response to the invitation to provide information.
[0026] The computing device 115 identifies the target person's intention data and the related behavior data based on the measurement data. The "behavior invited by the invitation information" includes the designation of the target person's intention and the related behavior, which is all or a part of the behavior excluding the designation of the target person's intention. In this embodiment, the designation of the target person's intention is answering a question (for example, typing or voice input of the answer to the question), but the designation of the target person's intention may vary depending on the information provided. In this embodiment, the related behavior is all or a part of the behavior from when the question is provided to when the question is answered, but the related behavior may also vary depending on the designation of the target person's intention depending on the information provided. The target person's intention data is data representing the designated target person's intention. The related behavior data is data representing the related behavior.
[0027] The arithmetic device 115 calculates one or more behavioral feature amounts based on the associated behavior data for each of the one or more associated behaviors, and estimates the psychological characteristics of the subject 101 based on the one or more behavioral feature amounts. Specifically, for example, each time a question is displayed, the subject 101 answers the displayed question, and there is an associated behavior for each pair of question and answer. There is associated behavior data for each of the multiple associated behaviors, and the arithmetic device 115 calculates one or more behavioral feature amounts based on the associated behavior data for the multiple associated behaviors, and estimates the psychological characteristics of the subject 101 based on the one or more behavioral feature amounts.
[0028] 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 subject 101.
[0029] Each of the one or more behavioral features used to estimate the psychological characteristics of the subject 101 is adjusted information of at least a portion of the provided information and / or a behavioral feature that has been enhanced over time (examples of enhancement are described in detail later).
[0030] According to this embodiment, it is possible to estimate the psychological trait of the subject 101 without the subject 101 performing any other behavior than the behavior (e.g., answering a question) invited by the invitation information prepared and provided for a purpose other than psychological trait estimation, that is, without the subject 101 performing any behavior dedicated to estimating the psychological trait. Furthermore, according to this embodiment, one or more behavioral features used for estimating the psychological trait of the subject 101 are enhanced, so that it is expected that the estimation accuracy of the psychological trait will be improved.
[0031] The personal characteristic estimation system 100 may be a physical computer system (one or more physical computers) as illustrated in FIG. 1, or alternatively, a logical computer system based on a physical computer system (e.g., a cloud computing service).
[0032] Furthermore, the "psychological trait" may be composed of one or more psychological trait components, and the one or more psychological trait components may include at least one of temperament, character, personality, belief, values, mood, and emotion. Furthermore, the computing device 115 may estimate the psychological trait based on a part of the subject intention data. Furthermore, the computing device 115 may estimate the personal traits of the subject 101 (e.g., including at least one of name, gender, date of birth, age, motivation, desired occupation, career, grades, and possessed skills in addition to the psychological traits) based on the subject intention data (e.g., answer data including name, gender, etc.) in addition to the estimated psychological trait data.
[0033] The "related behavior" may be a behavior leading to an answer to a question (an example of specifying the subject's intention). For example, even if the answer is the same, the behavior leading to the answer is influenced by the psychological characteristics of the subject 101. Since related behavior data representing such behavior is used for psychological characteristic estimation, it is expected that the psychological characteristic can be estimated with high accuracy even if there are no questions or subject behaviors dedicated to psychological characteristic estimation.
[0034] This embodiment will be described in detail below.
[0035] 2 shows data and functions in the entire system according to the first embodiment. In this embodiment, "DB" is an abbreviation for database. The data does not have to be structured data like a database.
[0036] As described above, the subject device 130 has a sensor group 201 (one or more sensors) and a display device 112, and also has a control unit 202. The control unit 202 is realized by executing a program (e.g., an application program) in a calculation device (not shown) which is a processor of the subject device 130.
[0037] The control unit 202 transmits measurement data based on measurements by each sensor in the sensor group 201 to the personal characteristic estimating system 100. In addition, the control unit 202 outputs information provided by the personal characteristic estimating system 100 to the display device 112 and / or other output devices (e.g., speakers).
[0038] The storage device 114 stores an answer DB 230, an estimation DB 240, a psychological characteristic DB 250, and a provision DB 260. The answer DB 230 is a DB in which answer data (data representing answers to questions) is stored. The estimation DB 240 is a DB in which data used to estimate psychological characteristics (e.g., one or more models such as regression equations). The psychological characteristic DB 250 is a DB in which estimated psychological characteristic data (data representing estimated psychological characteristics) is stored. The provision DB 260 is a DB in which provided information (e.g., the content itself such as a question) and information related to that information (e.g., metadata such as the brightness of the content) are stored.
[0039] The calculation device 115 executes the computer program to realize a response analysis unit 210 that analyzes responses from the subject 101 and a response control unit 220 that controls responses to the subject 101. The response analysis unit 210 has a response extraction unit 211 that extracts responses, a behavior feature generation unit 212 that generates behavior feature amounts, and a psychological characteristic estimation unit 213 that estimates psychological characteristics.
[0040] Below, an example of the functions realized by the arithmetic unit 115 and the processing performed in this embodiment will be described.
[0041] FIG. 3 shows an example of the flow of processing performed in the first embodiment.
[0042] The response analysis unit 210 receives data of a video captured by the camera 102 in the sensor group 201 from the control unit 202 of the subject device 130. The response analysis unit 210 starts recording the video (S301). The recorded data (video data) may be at least a part of the measurement data, and is stored in the storage device 114 by the response analysis unit 210. The response control unit 220 transmits a notification of the start of recording to the control unit 202 of the subject device 130, and the control unit 202 may output the notification via the display device 112 or another output device.
[0043] The response control unit 220 provides guidance to the subject 101, and the response analysis unit 210 monitors the subject 101 who has received the guidance (S302). Specifically, the invitation information transmitted by the response control unit 220 to the subject device 130 includes information representing a guide to the subject 101. The guide may be a guide that contributes to enhancing the behavioral feature. For example, when the response analysis unit 210 determines from the recorded data that the position of the subject 101 is not appropriate for the angle of view (frame) of the camera 102 (or regardless of whether the position is appropriate or not), the response control unit 220 may transmit invitation information including information representing a guide for superimposing the position of the subject 101 on an appropriate position for the angle of view (frame) of the camera 102 to the subject device 130. As a result, for example, subject 101 who is in an inappropriate position (an inappropriate position in the camera frame) as illustrated in FIG. 4A or FIG. 4B is moved to an appropriate position as illustrated in FIG. 4C, which is expected to improve the accuracy of the behavioral features generated thereafter, and therefore the accuracy of the estimation of psychological characteristics is expected to improve.
[0044] The guide may include, instead of or in addition to the position guide relative to the angle of view of the camera 102, other guides that contribute to enhancing the behavioral features, such as guides for increasing the probability of accurately detecting the subject's 101 vocalizations (e.g., guides for adjusting microphone settings or adjusting the distance between the microphone and the subject 101).
[0045] The response analysis unit 210, in monitoring, identifies the behavior (an example of related behavior) of the target person 101 in response to the invitation information including the information representing such a guide from the recorded data, and the behavior feature generation unit 212 generates behavior feature related to the behavior. The generated behavior feature may be stored in the storage device 114.
[0046] Note that the behavior feature extracted from the behavior (particularly related behavior) of the subject 101 does not need to be limited to one, and various ones can be integrated to estimate psychological characteristics. For example, the related behavior data specified by the behavior feature generation unit 212 based on the video recording data may be data representing at least one of head movement (head movement of the subject 101), facial expression (facial expression of the subject 101), eye movement (eye movement of the subject 101), posture (posture of the subject 101), body movement (body movement of the subject 101), sound (sound of the subject 101's vocalization), vital signs (vital signs of the subject 101), time (time taken for the subject 101 to respond), and device operation (operation of the subject device 130 by the subject 101). The behavior feature generation unit 212 may generate behavior feature from such related behavior data. This allows the psychological characteristics of the subject 101 to be estimated from at least one of various viewpoints.
[0047] An example of the relationship between the feature amount categories (head movement, facial expression, eye movement, posture, body movement, sound, vitals, time, and device operation), the behavior feature amount, and the related behavior value is as shown in FIG. 5. The "related behavior value" is a value (value representing related behavior) identified from the related behavior data. For example, the related behavior data identified from the video recording data includes related behavior data related to head movement, and related behavior values such as the maximum and minimum values of the head velocity of the subject 101 are obtained from the time series of such related behavior data. There are one or more behavior feature amounts for each feature amount category, and there are one or more related behavior values for each behavior feature amount that are elements for calculating the behavior feature amount. The behavior feature amount generating unit 212 can generate the behavior feature amount by a predetermined generation model (for example, a regression equation or other model) using one or more related behavior values. The generation model for generating the behavior feature amount may be different for each behavior feature amount. In addition, the generation model for each behavior feature amount may be stored in the storage device 114 (for example, the estimation DB 240) and may be identified from the storage device 114.
[0048] After the above-mentioned guidance and monitoring (after S302), the response control unit 220 identifies one or more questions to be provided from the provision DB 260, and provides information to be provided including information representing the identified one or more questions to the subject device 130 (S303). The questions may be provided all at once, or may be provided sequentially (the next question is provided after each answer).
[0049] The response analysis unit 210 may set a time limit for answering one or more provided questions, and notify the subject 101 of the time limit. For example, there may not necessarily be a time limit for answering, but if a time limit is associated with one or more provided questions in the provision DB 260, the response analysis unit 210 may set a time limit.
[0050] For example, the response analysis unit 210 judges whether or not the time limit has passed (S304). If an answer is given within the time limit (S304: YES, S305: YES), the answer extraction unit 211 of the response analysis unit 210 extracts an answer from the measurement data (data including data representing an answer input via the input device 111) from the subject device 130, and stores the data representing the extracted answer in the storage device 114. In parallel, the behavior feature amount generation unit 212 identifies related behavior data from the measurement data, and stores the identified related behavior data in the storage device 114 (S306).
[0051] If there is a next question (S307: YES), the process returns to S304. If all questions have been answered and there is no next question (S307: NO), or if the time limit has expired (S304: NO), the response analysis unit 210 ends the recording (S308). The response control unit 220 transmits a notification of the end of recording to the control unit 202 of the subject device 130, and the control unit 202 may output the notification via the display device 112 or another output device.
[0052] The answer extraction unit 211 acquires the answer data stored in the storage device 114, and outputs (stores) the acquired answer data in the answer DB 230 (S309). The answer extraction unit 211 may output the acquired answer data to the administrator device 180.
[0053] The behavior feature generation unit 212 calculates a related behavior value for each related behavior from the related behavior data for each related behavior stored in the storage device 114, and generates a plurality of (or one) behavior feature amounts using the calculated plurality of (or one) related behavior values (S310).
[0054] The psychological characteristic estimation unit 213 estimates the psychological characteristic of the subject 101 using the model represented by the estimation DB 240 based on the generated multiple (or one) behavioral features, and outputs (stores) the estimated psychological characteristic data in the psychological characteristic DB 250 (S311). The psychological characteristic estimation unit 213 outputs the estimated psychological characteristic data to the administrator device 180 in S311 or after S311.
[0055] Instead of outputting the answer data (an example of subject intention data) and the estimated psychological characteristic data at different times, integrated data of these data may be output. Furthermore, the output destination of the answer data and the output destination of the estimated psychological characteristic data may be the same or different. Furthermore, the estimated psychological characteristic data may be output to the subject device 130 instead of or in addition to the administrator device 180. This allows the subject 101 to know the estimated psychological characteristic of the subject 101 by answering the questions.
[0056] 3, the measurement data from the subject device 130 includes video data representing a video in which the subject 101 is captured by the camera 102, and the behavior feature amount generation unit 212 specifies related behavior data for each of one or more related behaviors based on the video data (recorded data). Since various related behavior data can be obtained from the video data, it is expected that the estimation accuracy of psychological characteristics will be improved.
[0057] In addition, in the process described with reference to FIG. 3, the response control unit 220 may notify the subject 101 of the time limit for answering one or more questions. In general, in an interview or survey, the manager 151 (e.g., an interviewer, a supervisor, or an instructor) can adjust the time while watching the situation of the subject 101 and guide the subject 101 to complete the survey of the personality characteristics within the set time. However, in an automated interview or survey, the manager 151 is absent (the subject 101 is talking to a computer, not the manager 151). For this reason, it is practical to proceed with the interview and the survey with a time limit set for the questions and responses. Such differences in sensitivity to time limits due to personality are expressed as behavioral feature values with different values related to personality, and as a result, it is expected that the estimation accuracy of psychological characteristics will be improved.
[0058] Moreover, in the process described with reference to FIG. 3, each of the one or more behavioral features used to estimate the psychological characteristics of the subject 101 is at least a part of the adjusted information provided and / or a behavioral feature enhanced according to the elapsed time for the behavioral feature. For example, the provision of the above-mentioned guide contributes to the enhancement of the behavioral feature. This is because it is expected that more accurate behavioral features will be generated. "Enhancing" a behavioral feature may mean either increasing or decreasing the behavioral feature.
[0059] In addition, the following example may be adopted as another example of enhancing behavioral features. That is, as the related behavioral data, there is vital data identified from the video of the subject 101 appearing in the video represented by the video data. The adjusted information of at least a part of the provided information is information in which the brightness of both the content displayed on the subject device 130 and the background of the content is adjusted. Such information may be displayed at any timing from the start to the end of recording (for example, at least one of S302 and S303). The behavioral feature generating unit 212 estimates vital data from the face of the subject 101 represented by the video data. For example, vital data representing minute color changes in the face that change due to blood flow is estimated. In order to improve the S / N ratio and improve the estimation accuracy of the vital data, in other words, for enhancing the behavioral features based on the vital data, it is desirable that the face is sufficiently illuminated. Therefore, the display device 112 of the subject device 130 is utilized as lighting that illuminates the face of the subject 101. The information in which the luminance of both the content and the background of the content is adjusted may be prepared in advance in the provision DB 260, or may be dynamically adjusted by the response control unit 220. When the area of the background is larger than the area of the content (for example, the text of a question or the avatar providing the question) in the entire screen, the background luminance is brighter than the content luminance in the information (screen information) having such content and background. That is, in such a case, the display on the display device 112 is not the display illustrated in FIG. 6A, but the display illustrated in FIG. 6B. On the other hand, when the area of the background is smaller than the area of the content in the entire screen, the background luminance is darker than the content luminance in the information (screen information) having such content and background. Note that, since it is common to extract color changes from red to green in vital signs estimation, the wavelength range from red to green may be adopted for the background or the content that has the greater luminance (brighter).
[0060] As another example of enhancing behavioral features, the following example may be adopted.
[0061] That is, for example, in S311, the psychological characteristic estimation unit 213 may enhance one or more behavioral feature amounts according to the elapsed time for the behavioral feature amount. The psychological characteristic estimation unit 213 may estimate the psychological characteristic of the subject 101 based on one or more behavioral feature amounts including one or more enhanced behavioral feature amounts. In an interview or survey, the subject 101 may change the behavioral characteristics of the subject 101 due to the subject 101 getting used to the atmosphere of the interview or survey (for example, the voice may gradually become quieter or louder, the respiratory rate or the speed of convergence of vital signs may change, gestures and hand movements may increase or decrease, facial expressions may change, etc.). Therefore, by using the behavioral feature amount enhanced according to the passage of time (for example, the degree of adaptation according to the elapsed time) for estimating the psychological characteristic (for example, by taking into account the change in the behavioral feature amount over the elapsed time), it is expected that the estimation accuracy of the psychological characteristic may be improved. In addition, the degree of appearance of the behavior feature with respect to the time limit can also be reflected in the estimation of the psychological characteristic, and thus the estimation accuracy of the psychological characteristic is expected to be improved. In this paragraph, some or all of the "one or more behavior features" may be enhanced behavior features, in other words, the "one or more behavior features" may be a mixture of enhanced and non-enhanced behavior features.
[0062] At least one of the following first to third estimation models may be stored as the estimation model stored in the estimation DB 240. All of the estimation models are multiple regression models, but the estimation model stored in the estimation DB 240 may be another model instead of or in addition to at least one of the first to third estimation models. First estimation model: y=∫(a(t)+b1(t)x1(t)+b2(t)x2(t)+b3(t)x3(t)+···+b n (t)x n (t))dt Second estimation model: y=a+b1x1+b2x2+b3x3+···+b n x n , and b p x p =f(c p1[T1] x p[T1] ,cp2[T2] x p[T2] ,···,c pm[Tm] x p[Tm] ) Third estimation model: y=a+b1x1+b2x2+b3x3+···+b n x n
[0063] The variables in the above estimation are as follows: ·y is the psychological characteristic component (dependent variable). · a is a constant. ·bx is an explanatory variable. x (e.g., x1, x2, , x n Each of these is a behavior feature. b (e.g., b1, b2, , b n ) and c (e.g., c p1 ,c p2 ,···,c pm Each of these is a weighting coefficient. Each of n and m is an integer of 1 or more. Both n and m may vary depending on the psychological characteristic component. For example, n may vary depending on the psychological characteristic component, such as n=5 for one psychological characteristic component and n=3 for another psychological characteristic component. The same may be true for m. t is the elapsed time. ·T(T1, T2, . . . , Tm) is a time slot (an example of elapsed time). p is an arbitrary integer from 1 to n.
[0064] Each of the first to third estimation models may be prepared for each psychological characteristic component. The same estimation model may be used for all of the psychological characteristic components (values substituted for explanatory variables may differ depending on the psychological characteristic component), or one of the first to third estimation models may be used for a certain psychological characteristic component, and another one of the first to third estimation models may be used for another psychological characteristic component.
[0065] The psychological characteristic estimation unit 213 may estimate at least one psychological characteristic component using a first estimation model. The first estimation model includes a multiple regression model for each elapsed time. The multiple regression model for each elapsed time includes n explanatory variables that correspond 1:1 to n behavioral features (n is an integer equal to or greater than 1, and a value corresponding to the psychological characteristic component corresponding to the multiple regression model), and a weighting coefficient determined by the elapsed time for each of the n explanatory variables. According to the first estimation model, it is possible to estimate the psychological characteristic from the entire interview time frame while constantly changing the weighting coefficient with respect to the passage of time, that is, to expect a highly accurate estimation of the psychological characteristic. For example, the first elapsed time may be a first time range from the start of the interview to a first time for a certain behavioral feature, and the second elapsed time may be a second time range from k minutes after the start of the interview to a second time for another behavioral feature. The time interval between the first elapsed time and the time interval between the second elapsed time may be continuous, discrete, or overlapping. The start and end of each elapsed time may be dynamically determined based on the behavioral feature amount or other factors. In addition, since the elapsed time is typically dynamic, the length or number of elapsed times may be different when the first estimation model is used to estimate a certain psychological characteristic component and when the first estimation model is used to estimate another psychological characteristic component.
[0066] The psychological characteristic estimation unit 213 may estimate at least one psychological characteristic component using a second estimation model. The second estimation model includes n multiple regression models (n is an integer of 1 or more) corresponding to n behavioral features on a 1:1 basis. For each of the n multiple regression models, the multiple regression model includes m weighting coefficients corresponding to m time slots (m is an integer of 2 or more) constituting a time (e.g., the time to be evaluated such as the interview time) on a 1:1 basis, and an explanatory variable that is a behavioral feature corresponding to the multiple regression model for each of the m weighting coefficients. This enables psychological characteristic estimation that takes elapsed time into consideration with fewer calculation resources (small calculation load for the computing device 115) than the first estimation model. Note that, for example, for one psychological characteristic component, the length of the m time slots may be the same or different. Furthermore, the length of each of the m time slots may be common to all psychological characteristic components or may differ depending on the psychological characteristic component (in the latter case, it is desirable that the length of each time slot is an appropriate length depending on the behavioral feature as the explained variable). In addition, in the estimation using the second estimation model for a certain psychological characteristic component, a certain explanatory variable is b p x p =c p1[T1] x p[T1] +c p2[T2] x p[T2] +···+c pm[Tm] x p[Tm] and different explanatory variables may be used in different equations.
[0067] The psychological characteristic estimation unit 213 may select which of the first estimation model and the second estimation model to use for the estimation of at least one psychological characteristic component for which it is preferable to consider the elapsed time, based on a model selection policy (e.g., which of the computational load and the estimation accuracy is to be prioritized) including a relationship (typically a magnitude relationship) between the computational load (e.g., processor usage rate) of the computing device 115 and a threshold of the computational load. For example, when the computational load of the computing device 115 is less than the threshold, the psychological characteristic estimation unit 213 may select the first estimation model that requires more computational resources but is expected to have higher estimation accuracy, and estimate the psychological characteristic component using the first estimation model. On the other hand, when the computational load of the computing device 115 is equal to or greater than the threshold, the psychological characteristic estimation unit 213 may select the second estimation model that requires less computational resources, and estimate the psychological characteristic component using the second estimation model. In this way, the optimal estimation model can be selected according to the computation situation, and it is expected that estimation according to the computation situation will be performed.
[0068] The above is a description of the first embodiment. In the first embodiment, at least one of the following may be adopted. The behavioral feature generated based on the video data may be at least one of eye movement, eyebrow movement, mouth movement, nose movement, and facial color change. The behavioral feature generated based on the video data may be at least one of pupil fluctuation, gaze fluctuation, degree of gaze, and fixational eye movement. The behavior feature generated based on the video data may be at least one of head movement, body movement, shoulder movement, arm movement, hand movement, and the position of the subject 101 relative to the angle of view of the camera 102. The behavioral feature generated based on the video data may be at least one of pulse rate, stress level, and respiratory rate estimated from changes in facial color between video frames in the video data. [Second embodiment]
[0069] The second embodiment will be described. In this regard, differences from the first embodiment will be mainly described, and descriptions of commonalities with the first embodiment will be omitted or simplified (this also applies to the third and fourth embodiments).
[0070] FIG. 7 shows data and functions in the entire system according to the second embodiment.
[0071] Each of the multiple questions for the subject 101 may be classified into one of the multiple groups according to the attribute of the question. Data indicating the relationship between the question and the group may be stored in the provision DB 260.
[0072] The response analysis unit 210 includes a group classification unit 700. For example, an estimation model may be stored in the estimation DB 240 for each group.
[0073] The group classification unit 700 classifies, for each of a plurality of questions, related behavioral data related to the answer to the question into a group to which the question belongs. The behavior feature generation unit 212 generates behavior features for each of a plurality of groups based on the related behavioral data classified into the group. For example, the behavior feature generation unit 212 may aggregate (e.g., calculate an average value) behavior-related values for each group and calculate behavior features from the aggregated behavior-related values. The psychological characteristic estimation unit 213 estimates the psychological characteristic of the subject 101 based on the calculated behavior feature for each of the plurality of groups. This is expected to enable efficient and accurate psychological characteristic estimation. [Third embodiment]
[0074] FIG. 8 shows data and functions in the entire system according to the third embodiment.
[0075] The response analysis unit 210 includes a digest generation unit 800. The storage device 114 stores a digest DB 810 in which digest data is stored.
[0076] The digest generation unit 800 acquires a behavioral digest video, which is a video of a time period associated with a relatively large behavioral feature or an enhanced behavioral feature, from among the videos represented by the video data, and outputs data representing the behavioral digest video (for example, stores in the digest DB 810). For example, the digest generation unit 800 may generate an answer digest video made up of answer scenes to one or more questions for which digest generation is specified in advance, from the recorded data, and store data of the generated answer digest video in the digest DB 810. The digest generation unit 800 may also generate a behavioral digest video made up of main behavioral feature scenes when estimating a psychological characteristic, from the recorded data, and store data of the generated behavioral digest video in the digest DB 810.
[0077] In this way, digest video data for confirming the key points of an automatically conducted interview is automatically constructed and stored, which is convenient for the administrator 151 to confirm the key points at a later date and to check the validity of the estimated psychological characteristics. [Fourth embodiment]
[0078] FIG. 9 shows an example of a keyword table according to the fourth embodiment.
[0079] The plurality of questions may include questions belonging to psychological trait components. A "question belonging to a psychological trait component" is, for example, a question including a keyword belonging to a psychological trait component. Specifically, for example, as shown in FIG. 9, components such as neuroticism, openness, conscientiousness, extraversion, and agreeableness may be adopted as a plurality of psychological trait components constituting a psychological trait, and one or more keywords of questions may be associated with each psychological trait component.
[0080] A keyword table in which a keyword is registered for each psychological characteristic component, that is, a keyword table exemplified in FIG. 9, may be stored in advance in the estimation DB 240, for example. The keyword table may be an example of data representing keywords related to psychological characteristics. In estimating the psychological characteristics of the subject 101, the psychological characteristic estimation unit 213 may weight a question including a keyword related to psychological characteristics relatively higher than a question not including a keyword related to psychological characteristics. For example, the psychological characteristic estimation unit 213 may use a behavior feature generated from related behavior data related to a response to a question including a keyword related to psychological characteristics, and not use a behavior feature generated from related behavior data related to a response to a question not including a keyword related to psychological characteristics, in estimating the psychological characteristics. This is expected to estimate the psychological characteristics with high accuracy.
[0081] Although several embodiments have been described above, these are merely examples for explaining the present invention, and the scope of the present invention is not limited to these embodiments. The present invention can be implemented in various other forms.
[0082] For example, any two or more of the above-described embodiments may be combined.
[0083] In addition, in any of the embodiments, behavioral features are generated from relevant behavioral data of the subject 101 that changes within a limited time such as an interview, and psychological characteristics are estimated based on the generated behavioral features, thereby making it possible to realize automated objective and highly accurate estimation of psychological characteristics within a limited time.
[0084] In addition, in at least one of the first to fourth embodiments, the practical application illustrated in FIG. 10 may be adopted. That is, a person evaluation system may exist. The person evaluation system performs a person evaluation of the subject (for example, a decision on whether to employ the subject) based on the subject's answer data and the subject's estimated psychological characteristic data. The person evaluation system may be a function within the person characteristic estimation system 100, or may be a function outside the person characteristic estimation system 100 (for example, a physical computer system or a logical computer system such as a cloud computing service). The person characteristic estimation system 100 may extract related behavior data for each answer to a question from the measurement data for each subject, and output answer data representing the answer to each question and estimated psychological characteristic data representing the psychological characteristic estimated based on the related behavior data for each answer to the person evaluation system. According to such a practical application, the feasibility of automating the person evaluation of each subject can be increased by the technical means of the person characteristic estimation system 100. [Explanation of symbols]
[0085] 100: Personality trait estimation system
Claims
1. an interface device connected to a subject device, the subject device being a device having one or more sensors; a computing device connected to the interface device; Equipped with the computing device provides the subject device with provision information including invitation information that invites the subject to take action for a purpose other than the psychological characteristic estimation; the computing device receives, via the interface device, measurement data related to an action taken by the subject in response to the provided invitation information and based on measurements by the one or more sensors from the subject device; The arithmetic device identifies subject intention data and related behavior data based on the measurement data, The action invited by the invitation information includes a designation of a target person's intention and a related action which is all or a part of the action excluding the designation of the target person's intention, The subject intention data is data representing the designated subject intention, The related behavior data is data representing a related behavior, the computing device calculates one or more behavioral feature amounts based on associated behavior data for each of the one or more associated behaviors, and estimates a psychological characteristic of the subject based on the one or more behavioral feature amounts; The arithmetic device outputs estimated psychological characteristic data which is data representing the estimated psychological characteristic; Each of the one or more behavioral features used to estimate the psychological characteristic of the subject is adjusted information of at least a part of the provided information and / or a behavioral feature enhanced over time with respect to the behavioral feature. Personality trait estimation system.
2. The computing device includes: For each of the one or more behavioral features, enhancing the behavioral feature in accordance with an elapsed time for the behavioral feature; Estimating psychological characteristics of the subject based on one or more behavioral features including the one or more enhanced behavioral features. The person characteristic estimation system according to claim 1 .
3. The arithmetic device estimates at least one psychological characteristic component of the one or more psychological characteristic components of the psychological characteristic of the subject using a first estimation model; the first estimation model includes a multiple regression model for each elapsed time, The multiple regression model for each elapsed time is n explanatory variables that correspond one-to-one to the n behavioral features (n is an integer equal to or greater than 1); For each of the n explanatory variables, a weighting coefficient determined by the elapsed time is Including, The person characteristic estimation system according to claim 2 .
4. The arithmetic device performs the following for at least one psychological characteristic component of the one or more psychological characteristic components of the psychological characteristic of the subject: selecting one of the first estimation model and the second estimation model based on a model selection policy including a relationship between a computation load of the computing device and a threshold value of the computation load; The psychological characteristic component is estimated using the selected estimation model; the second estimation model is a multiple regression model including n multiple regression models each corresponding one-to-one to n behavioral feature quantities (n is an integer equal to or greater than 1); For each of the n multiple regression models, the multiple regression model is m weighting coefficients corresponding one-to-one to m time slots (m is an integer equal to or greater than 2) constituting the time; For each of the m weighting coefficients, an explanatory variable which is a behavioral feature corresponding to the multiple regression model is Including, The person characteristic estimation system according to claim 3 .
5. The arithmetic device estimates at least one psychological characteristic component of the one or more psychological characteristic components of the psychological characteristic of the subject using a multiple regression model; For each of the one or more psychological characteristic components, the multiple regression model includes n multiple regression models corresponding one-to-one to n behavioral feature quantities (n is an integer equal to or greater than 1); For each of the n multiple regression models, the multiple regression model is m weighting coefficients corresponding one-to-one to m time slots (m is an integer equal to or greater than 2) constituting the time; For each of the m weighting coefficients, an explanatory variable which is a behavioral feature corresponding to the multiple regression model is Including, The person characteristic estimation system according to claim 2 .
6. the one or more sensors include a camera; The measurement data includes video data that is data representing a video captured by the camera and showing the subject, the computing device identifies related behavior data for each of one or more related behaviors based on the video data; The person characteristic estimation system according to claim 1 .
7. The related behavior data includes vital data identified from a video of the subject appearing in the video represented by the video data, The adjusted information of at least a part of the provided information is information in which the brightness of both the content and the background of the content displayed on the subject device is adjusted. The person characteristic estimating system according to claim 6 .
8. the computing device acquires a behavioral digest video, which is a video of a time period associated with a relatively large behavioral feature or an enhanced behavioral feature, from among the videos represented by the video data, and outputs data representing the behavioral digest video; The person characteristic estimating system according to claim 6 .
9. The computing device determines that the related behavior data identified based on the video data represents at least one of the following: a head movement of the subject, a facial expression of the subject, an eye movement of the subject, a posture of the subject, a body movement of the subject, an audio of the subject's vocalization, a vital sign of the subject, a time taken for the subject to respond, and an operation of the subject's device by the subject. The person characteristic estimating system according to claim 6 .
10. The invitation information includes information representing a guide to the target person, The related behavioral data includes data representative of behavior by the subject receiving a guide. The person characteristic estimation system according to claim 1 .
11. The provided information includes information representing one or more questions for the subject, the computing device notifies the subject of a time limit for answering the one or more questions; The person characteristic estimation system according to claim 1 .
12. the provided information includes information representing a plurality of questions for the subject, each of the plurality of questions is classified into one of a plurality of groups according to an attribute of the question; the subject intention data includes data representing an answer to each of the plurality of questions, The computing device includes: classifying, for each of the plurality of questions, related behavior data related to an answer to the question into a group to which the question belongs; Calculating a behavior feature amount for each of the plurality of groups based on the related behavior data classified into the group; estimating a psychological characteristic of the subject based on the calculated behavioral feature amount for each of the plurality of groups. The person characteristic estimation system according to claim 1 .
13. The provided information includes information representing one or more questions for the subject, the computing device outputs answer data representing answers to the one or more questions and the estimated psychological characteristic data to a function for evaluating a person based on the answer data and the psychological characteristic data; The person characteristic estimation system according to claim 1 .
14. The computer provides provision information including invitation information that invites the subject to take action for a purpose other than the psychological characteristic estimation to a subject device, which is a device having one or more sensors; a computer receives measurement data from the subject device based on measurements by the one or more sensors relating to an action taken by the subject in response to the provided invitation information; The computer identifies the subject's intention data and related behavior data based on the measurement data, The action invited by the invitation information includes a designation of a target person's intention and a related action which is all or a part of the action excluding the designation of the target person's intention, The subject intention data is data representing the designated subject intention, The related behavior data is data representing a related behavior, a computer calculates one or more behavioral feature amounts based on related behavior data for each of the one or more related behaviors, and estimates a psychological characteristic of the subject based on the one or more behavioral feature amounts; Each of the one or more behavioral features used for estimating the psychological characteristic of the subject is adjusted information of at least a part of the provided information and / or a behavioral feature enhanced over time with respect to the behavioral feature, The computer outputs estimated psychological characteristic data which is data representing the estimated psychological characteristic. A method for estimating human characteristics.
15. providing provision information including invitation information inviting the subject to take action for a purpose other than the psychological characteristic estimation to a subject device which is a device having one or more sensors; receiving measurement data from the subject device based on measurements by the one or more sensors relating to an action taken by the subject in response to the provided invitation information; Based on the measurement data, subject intention data and related behavior data are identified; The action invited by the invitation information includes a designation of a target person's intention and a related action which is all or a part of the action excluding the designation of the target person's intention, The subject intention data is data representing the designated subject intention, The related behavior data is data representing a related behavior, Calculating one or more behavioral features based on related behavior data for each of the one or more related behaviors, and estimating a psychological characteristic of the subject based on the one or more behavioral features; Each of the one or more behavioral features used for estimating the psychological characteristic of the subject is adjusted information of at least a part of the provided information and / or a behavioral feature enhanced over time with respect to the behavioral feature, outputting estimated psychological characteristic data which is data representing the estimated psychological characteristic; A computer program that causes a computer to do something.
Citation Information
Patent Citations
Non-contact type state detection device and non-contact type state detection program
JP2022179438A
US10,957,306
Cited By
Psychological characteristic estimation device, psychological characteristic estimation system, and psychological characteristic estimation method
WO2026163569A1
