JP2021086549A - Interactive type information acquisition apparatus, interactive type information acquisition method, program and recording medium - Google Patents

Abstract

To provide an interactive type information acquisition apparatus that can easily acquire information while interacting.SOLUTION: In an interactive type information acquisition apparatus 10 according to the present invention, general question presentation means 11 presents general questions to a user, general answer acquisition means 12 acquires general answers of the user for the general questions, clarity degree calculation means 13 calculates a clarity degree from the general answers, awareness degree calculation means 14 calculates an awareness degree for each attribute of the questions using a question attribute and the clarity degree set for the presented general questions, implication ratio calculation means 15 calculates an implication ratio in the general question for each question attribute from the awareness degree, determination means 15 determines whether or not the implication ratio satisfies a threshold value, objective question presentation means 16 presents an objective question associated with the question attribute to the user when the threshold value is satisfied, and objective answer acquisition means 17 acquires objective answers of the user for the objective questions, and stores the answer in an intention database.SELECTED DRAWING: Figure 1

Description

The present invention relates to an interactive information acquisition device, an interactive information acquisition method, a program, and a recording medium.

Conventionally, a technique for causing a user to perform a pseudo dialogue on a computer has been proposed (for example, Patent Document 1).

In addition, in fields such as medical care and long-term care, it is necessary to present to users (patients, etc.) questions such as the presence or absence of life-prolonging treatment and matters related to personal care, and to obtain information such as the intention of the user in advance. ..

Japanese Unexamined Patent Publication No. 2004-178299

However, users feel psychological resistance to thinking and answering questions such as the presence or absence of life-prolonging treatment and matters related to personal care. Therefore, it is difficult for the questioner (for example, the staff of a hospital or a long-term care facility) to obtain information from the user. Further, when the question is presented to the user through the technology such as Patent Document 1, the user feels psychological resistance, so that it is difficult for the questioner to obtain information from the user. Is.

Therefore, an object of the present invention is to provide an interactive information acquisition device, an interactive information acquisition method, a program, and a recording medium capable of easily acquiring information.

In order to achieve the above object, the interactive information acquisition device of the present invention can be used.
Includes general question presentation means, general answer acquisition means, clarity calculation means, consciousness calculation means, implication ratio calculation means, judgment means, purpose question presentation means, and purpose answer acquisition means.
The general question presenting means refers to the general question database and presents the general question to the user.
The general question database is a database that stores general questions for each preset question attribute.
The general answer acquisition means acquires the user's general answer to the general question, and obtains the general answer.
The clarity calculation means calculates the clarity from the general answer, and then
The clarity is a value indicating the degree of motivation of the user to interact with the question attribute.
The consciousness calculation means calculates the consciousness for each question attribute by using the question attribute set for the presented general question and the clarity.
The degree of consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute.
The implication ratio calculation means calculates the implication ratio in the presented general question for each question attribute from the degree of consciousness.
The determination means refers to the purpose question database and determines whether or not the implication ratio satisfies the threshold value.
The purpose question database is a database that stores the purpose question and the threshold value of the implication ratio.
The purpose question is associated with the general question by the question attribute.
When the above threshold is satisfied
The purpose question presenting means refers to the purpose question database and presents the purpose question associated with the set question attribute to the user.
The purpose answer acquisition means acquires the user's purpose answer to the purpose question, and stores the acquired answer in the will database.
The intention database is a device that is a database that stores a user's purpose answer to the purpose question.

The interactive information acquisition method of the present invention
Includes general question presentation process, general answer acquisition process, clarity calculation process, awareness calculation process, implication ratio calculation process, judgment process, purpose question presentation process, and purpose answer acquisition process.
In the general question presentation process, the general question is presented to the user with reference to the general question database.
The general question database is a database that stores general questions for each preset question attribute.
In the general answer acquisition process, the user's general answer to the general question is acquired, and the general answer is acquired.
In the clarity calculation step, the clarity is calculated from the general answer, and the clarity is calculated.
The clarity is a value indicating the degree of motivation of the user to interact with the question attribute.
In the consciousness calculation step, the consciousness is calculated for each question attribute using the question attribute set for the presented general question and the clarity.
The degree of consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute.
In the implication ratio calculation step, the implication ratio for each question attribute in the general question is calculated from the degree of consciousness.
In the determination step, it is determined whether or not the implication ratio satisfies the threshold value with reference to the purpose question database.
The purpose question database is a database that stores the purpose question and the threshold value of the implication ratio.
The purpose question is associated with the general question by the question attribute.
When the above threshold is satisfied
The purpose question presenting step refers to the purpose question database and presents the purpose question associated with the extracted question attribute to the user.
In the purpose answer acquisition process, the user's purpose answer to the purpose question is acquired, and the acquired answer is stored in the will database.
The will database is a method that is a database that stores a user's purpose answer to the purpose question.

According to the present invention, for example, information can be easily obtained.

FIG. 1 is a block diagram showing a configuration of an example of the device of the first embodiment. FIG. 2 is a block diagram showing an example of the hardware configuration of the apparatus of the first embodiment. FIG. 3 is a flowchart showing an example of processing in the apparatus of the first embodiment. FIG. 4 is a schematic diagram showing an example of a dialogue between the device of the first embodiment and the user. FIG. 5 is a schematic diagram showing an example of a dialogue between the device of the first embodiment and the user. FIG. 6 is a block diagram showing a configuration of an example of the device of the second embodiment. FIG. 7 is a block diagram showing an example of the hardware configuration of the apparatus of the second embodiment. FIG. 8 is a flowchart showing an example of processing in the apparatus of the second embodiment. FIG. 9 is a block diagram showing a configuration of an example of the device of the third embodiment. FIG. 10 is a block diagram showing an example of the hardware configuration of the apparatus of the third embodiment. FIG. 11 is a flowchart showing an example of processing in the apparatus of the third embodiment. FIG. 12 is a schematic diagram showing an example of a calculation formula for calculating the degree of clarity, the degree of consciousness, and the implication ratio. FIG. 13 is a schematic diagram showing an example of a calculation formula for calculating the degree of clarity, the degree of consciousness, and the implication ratio.

In the interactive information acquisition device of the present invention, when the threshold value is satisfied, the clarity calculation means further calculates the clarity from the purpose answer, and the purpose answer acquisition means further calculates the purpose answer and the purpose answer. It may be a mode in which the clarity of the target answer is stored in association with the above-mentioned clarity.

The interactive information acquisition device of the present invention further includes a machine learning means, and the machine learning means from the clarity of the purpose answer to the presentation of the general question to the presentation of the purpose question by machine learning. It may be an aspect of generating scenario data obtained by converting a scenario into data. In the above aspect, the machine learning means may generate the shortest scenario data from the degree of consciousness to the presentation of the target question by machine learning.

In the interactive information acquisition device of the present invention, if the threshold value is not satisfied, the general question presenting means may present a general question different from the presented general question.

In the interactive information acquisition device of the present invention, a plurality of the question attributes are associated with one purpose question and a general question, and the purpose question presenting means sets a plurality of question attributes of the presented general question. It may be in the form of presenting a purpose question including all.

The interactive information acquisition device of the present invention further includes a degree of attention calculation means, the degree of attention calculation means calculates the degree of attention indicating the number of times the question attribute is used, and the means for calculating the implication ratio is the above. A value obtained by multiplying the degree of consciousness and the degree of attention may be calculated as an implication ratio.

The interactive information acquisition device of the present invention further includes an attribute information acquisition means, the attribute information acquisition means acquires the attribute information of the user, and the target question includes a condition of a respondent for each of the target questions. The purpose question presenting means may be in the form of presenting the purpose question satisfying the condition of the respondent to the user based on the attribute information.

The interactive information acquisition device of the present invention further includes a voice input / output means, and the voice input / output means outputs each of the presentations in the general question presenting means and the purpose question presenting means as voice data, and The mode may be such that each of the acquisitions in the general response acquisition means and the purpose response acquisition means is input as voice data.

The interactive information acquisition device of the present invention further includes a purpose answer updating means, and the purpose answer acquisition means further stores the time information in which the purpose answer is stored in the intention database in association with the purpose answer. The purpose response updating means may be in a mode of updating at least one of the stored purpose response and the time information when a preset period elapses from the time information. In the above aspect, the purpose answer updating means may extend the period of the purpose question in which the purpose answer is updated infrequently.

The intelligibility calculation device of the present invention includes an intelligibility calculation means, an answer time calculation means, and an intelligibility calculation means, and the intelligibility calculation means answers from a user's answer to at least one of a general question and a purpose question. The intelligibility indicating the degree of intelligibility is calculated, the answer time calculating means calculates the length of time until the answer is obtained, and the intelligibility calculating means calculates the intelligibility and the length of the time. Is used to calculate the intelligibility, and the intelligibility is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question.

In the intelligibility calculation device of the present invention, the intelligibility calculation means calculates the intelligibility using an if-else type source code, and the if sentence is a condition for associating an arbitrary intelligibility with each arbitrary word. It may be a sentence, and the else sentence may be a conditional sentence that associates an arbitrary intelligibility with a word other than the arbitrary word.

In the clarity calculation device of the present invention, the response time calculation means may be in an aspect of calculating the length of the time by using the following (Equation 1).

tt = t / t'(Equation 1)

tt: The length of the time calculated by the answer time calculation means t: The length of the time required to obtain the answer t': The average value of the length of the time required to obtain the answer

In the clarity calculation device of the present invention, the clarity calculation means may be in an embodiment of calculating the clarity using the following (Equation 2).

Cl = 1 / (amb × tt) (Equation 2)

Cl: Clarity amb: Clarity calculated by the clarity calculation means tt: Length of time calculated by the response time calculation means

The clarity calculation device of the present invention may be used as the clarity calculation means in the interactive information acquisition device of the present invention.

The consciousness calculation device of the present invention includes a clarity calculation means, a likelihood setting means, and a consciousness calculation means, and the clarity calculation means calculates the clarity from the user's answer to at least one of a general question and a purpose question. The calculated clarity is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question, and the likelihood setting means has an arbitrary likelihood for each question attribute. The consciousness calculation means calculates the consciousness using the clarity and the likelihood, and the consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute. , A device.

In the consciousness calculation device of the present invention, the consciousness calculation means may be in the form of calculating the consciousness using the following (Equation 3).

int _n = Fv1 + (cl-Fv2) × x _n (Equation 3)

int _n : Consciousness degree in question attribute n Fv1: First fixed value Fv2 set in advance: Second fixed value set in advance cl: Clarity calculated by the clarity calculation means x _n : Set by the likelihood setting means Likelihood at the question attribute n

In the embodiment using the above (Equation 3), in the consciousness calculation device of the present invention, the consciousness calculation means may set the consciousness calculated in the first i-1st time (i ≧ 2) as the Fv1.

In the consciousness calculation device of the present invention, the clarity calculation means may be an aspect of calculating the clarity using the clarity calculation device of the present invention.

The consciousness calculation device of the present invention may be used as the consciousness calculation means in the interactive information acquisition device of the present invention.

In the interactive information acquisition method of the present invention, when the threshold value is satisfied, the clarity calculation step further calculates the clarity from the purpose answer, and the purpose answer acquisition step further calculates the purpose answer and the purpose answer. It may be a mode in which the clarity of the target answer is stored in association with the above-mentioned clarity.

The interactive information acquisition method of the present invention further includes a machine learning step, in which the machine learning step is from the clarity of the purpose answer to the presentation of the general question to the presentation of the purpose question by machine learning. It may be an aspect of generating scenario data obtained by converting a scenario into data. In the above aspect, the machine learning step may be an aspect in which the shortest scenario data from the degree of consciousness to the presentation of the target question is generated by machine learning.

In the interactive information acquisition method of the present invention, if the threshold value is not satisfied, the general question presenting step may present a general question different from the presented general question.

In the interactive information acquisition method of the present invention, a plurality of the question attributes are associated with one purpose question and a general question, and the purpose question presenting process sets a plurality of question attributes of the presented general question. It may be in the form of presenting a purpose question including all.

The interactive information acquisition method of the present invention further includes a attention level calculation step, the attention level calculation step calculates the attention level indicating the number of times the question attribute is used, and the implication ratio calculation step is the above. The mode may be such that a value obtained by multiplying the degree of consciousness and the degree of attention is calculated as an implication ratio.

The interactive information acquisition method of the present invention further includes an attribute information acquisition step, the attribute information acquisition step acquires user attribute information, and the target question includes a condition of a respondent for each of the target questions. The purpose question presenting step may be in a mode of presenting a purpose question satisfying the conditions of the respondent to the user based on the attribute information.

The interactive information acquisition method of the present invention further includes a voice input / output step, in which the voice input / output step outputs each of the presentations in the general question presentation step and the purpose question presentation step as voice data, and The mode may be such that each of the acquisitions in the general response acquisition step and the purpose response acquisition step is input as voice data.

The interactive information acquisition method of the present invention further includes a purpose response updating step, and the purpose response acquisition step further stores the time information in which the purpose answer is stored in the intention database in association with the purpose response. The purpose response updating step may be in a mode of updating at least one of the stored purpose response and the time information when the time information elapses in a preset period. In the above aspect, the objective answer updating step may be an embodiment in which the period of the objective question in which the update frequency of the objective answer is low is extended.

The intelligibility calculation method of the present invention includes an intelligibility calculation step, an answer time calculation step, and an intelligibility calculation step, and the intelligibility calculation step is an answer from a user's answer to at least one of a general question and a purpose question. The intelligibility indicating the degree of intelligibility is calculated, the answer time calculation step calculates the length of time until the answer is obtained, and the intelligibility calculation step is the intelligibility and the length of time. Is used to calculate the intelligibility, and the intelligibility is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question.

In the intelligibility calculation method of the present invention, the intelligibility calculation step calculates the intelligibility using an if-else type source code, and the if sentence is a condition for associating an arbitrary intelligibility with each arbitrary word. It may be a sentence, and the else sentence may be a conditional sentence that associates an arbitrary intelligibility with a word other than the arbitrary word.

In the clarity calculation method of the present invention, the response time calculation step may be an embodiment in which the length of the time is calculated using the following (Equation 1).

tt = t / t'(Equation 1)

tt: The length of the time calculated by the answer time calculation step t: The length of the time required to obtain the answer t': The average value of the length of the time required to obtain the answer

In the clarity calculation method of the present invention, the clarity calculation step may be an embodiment in which the clarity is calculated using the following (Equation 2).

Cl = 1 / (amb × tt) (Equation 2)

Cl: Clarity amb: Clarity calculated by the clarity calculation step tt: Length of time calculated by the response time calculation step

The clarity calculation method of the present invention may be used in the clarity calculation step of the interactive information acquisition method of the present invention.

The consciousness calculation method of the present invention includes a clarity calculation step, a likelihood setting step, and a consciousness calculation step, and the clarity calculation step calculates the clarity from the user's answer to at least one of a general question and a purpose question. The calculated clarity is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question, and the likelihood setting step is an arbitrary likelihood for each question attribute. Is set, and the consciousness calculation step calculates the consciousness using the clarity and the likelihood, and the consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute. , The method.

In the consciousness calculation method of the present invention, the consciousness calculation step may be in the form of calculating the consciousness using the following (Equation 3).

int _n = Fv1 + (cl-Fv2) × x _n (Equation 3)

int _n : Consciousness degree in question attribute n Fv1: First fixed value Fv2 set in advance: Second fixed value set in advance cl: Clarity calculated by the clarity calculation step x _n : Set by the likelihood setting step Likelihood at the question attribute n

In the aspect using the above (Equation 3), in the consciousness calculation method of the present invention, the consciousness calculated in the first i-1st time (i ≧ 2) may be set as Fv1 in the consciousness calculation step.

In the consciousness calculation method of the present invention, the clarity calculation step may be an aspect of calculating the clarity using the clarity calculation method of the present invention.

The consciousness calculation method of the present invention may be used in the consciousness calculation step in the interactive information acquisition method of the present invention.

The program of the present invention is a program capable of executing at least one of the interactive information acquisition method, the clarity calculation method, and the consciousness calculation method of the present invention on a computer.

The recording medium of the present invention is a computer-readable recording medium on which the program of the present invention is recorded.

In the present invention, the "user" is a user who answers a presented question (general question and purpose question), and is also referred to as a respondent. Further, in the present invention, the "dialogue" may be, for example, a dialogue between the user and the interactive information acquisition device of the present invention via a conversational interface (for example, LINE (registered trademark)). However, it may be a dialogue via an audio input / output device such as a speaker or a microphone.

The field of application of the present invention is not limited to the fields of medical treatment and long-term care, but can be applied to various fields in which information needs to be obtained from a specific person. Specifically, for example, it is in the fields of medical care, long-term care, education, counseling, and the like.

An embodiment of the present invention will be described with reference to the drawings. The present invention is not limited to the following embodiments. In each of the following figures, the same parts are designated by the same reference numerals. Further, the explanations of the respective embodiments can be referred to each other unless otherwise specified, and the configurations of the respective embodiments can be combined unless otherwise specified.

[Embodiment 1]
FIG. 1 is a block diagram showing a configuration of an example of the interactive information acquisition device 10 of the present embodiment. As shown in FIG. 1, the apparatus 10 includes a general question presenting means 11, a general answer acquiring means 12, a clarity calculation means 13, a consciousness calculation means 14, an implication ratio calculation means 15, a determination means 16, and a purpose question presentation means. 17 and the purpose answer acquisition means 18 are included. Further, the apparatus 10 may further include, for example, a machine learning means, a degree of attention calculation means, an attribute information acquisition means, a voice input / output means, a purpose answer update means, and the like.

The device 10 may be, for example, one device including the above-mentioned parts, or a device in which the above-mentioned parts can be connected via the communication network 3. Further, the present device 10 can be connected to an external device described later via the communication network. The communication network 3 is not particularly limited, and a known network can be used. For example, the communication network 3 may be wired or wireless. Examples of the communication network 3 include an Internet line, WWW (World Wide Web), a telephone line, LAN (Local Area Network), SAN (Storage Area Network), DTN (Delay Tolerant Networking), and the like. Examples of wireless communication include WiFi (Wireless Fidelity) and Bluetooth (registered trademark). The wireless communication may be either a form in which each device directly communicates (Ad Hoc communication) or an indirect communication via an access point. The apparatus 10 may be incorporated in the server as a system, for example. Further, the apparatus 10 may be, for example, a personal computer (PC, for example, a desktop type, a notebook type), a smartphone, a tablet terminal, or the like in which the program of the present invention is installed.

FIG. 2 illustrates a block diagram of the hardware configuration of the present device 10. The apparatus 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, a storage device 104, an input device 105, a display device 106, a communication device 107, and the like. Each part of the hardware configuration of the present apparatus 10 is connected to each other via the bus 103 by each interface (I / F).

The central processing unit (central processing unit) 101 is responsible for overall control of the apparatus 10. In the present device 10, for example, the program of the present invention and other programs are executed by the central processing unit 101, and various information is read and written. Specifically, for example, the central processing unit 101 presents the general question presenting means 11, the general answer acquiring means 12, the clarity calculation means 13, the consciousness calculation means 14, the implication ratio calculation means 15, the determination means 16, and the purpose question presentation. It functions as a means 17 and a purpose answer acquisition means 18. Further, when the present device 10 further includes a machine learning means, a degree of attention calculation means, an attribute information acquisition means, a voice input / output means, and a purpose answer update means, the central processing unit 101 may be, for example, the machine learning means. It functions as the attention degree calculating means, the attribute information acquiring means, the voice input / output means, and the purpose answer updating means.

The bus 103 can also be connected to, for example, an external device. The external device includes, for example, an external database (for example, a general question database 40 described later, a purpose question database 50, an intention database 60, etc.), a printer, a clarity calculation device 20 described later, an awareness calculation device 30 described later, and the like. Can be given. The device 10 can be connected to the communication network 3 by, for example, a communication device 107 connected to the bus 103, and can also be connected to an external device via the communication network 3.

Examples of the memory 102 include a main memory (main storage device). When the central processing unit 101 performs processing, for example, the memory 102 reads various operation programs such as the program of the present invention stored in the storage device 104 described later, and the central processing unit 101 reads from the memory 102. Receive the data and run the program. The main memory is, for example, a RAM (random access memory). Further, the memory 102 may be, for example, a ROM (read-only memory).

The storage device 104 is also referred to as a so-called auxiliary storage device with respect to the main memory (main storage device), for example. As described above, the storage device 104 stores an operation program including the program of the present invention. The storage device 104 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited, and may be an internal type or an external type, and examples thereof include HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, and memory card. Be done. The storage device 104 may be, for example, a hard disk drive (HDD) in which a recording medium and a drive are integrated, and a solid state drive (SSD).

In the apparatus 10, the memory 102 and the storage device 104 can also store access information and log information from the administrator, and information acquired from an external database (not shown).

The device 10 further includes, for example, an input device 105 and a display device 106. The input device 105 is, for example, a touch panel, a keyboard, a mouse, or the like. Examples of the display device 106 include an LED display and a liquid crystal display.

As described above, the apparatus 10 can communicate with the general question database 40, the purpose question database 50, and the intention database 60 via the communication network 3 by the communication device 107. Further, the general question database 40, the purpose question database 50, and the intention database 60 may each be able to communicate with each other via the communication network 3.

Next, an example of the interactive information acquisition method of the present embodiment will be described based on the flowchart of FIG. The interactive information acquisition method of the present embodiment is implemented as follows, for example, by using the interactive information acquisition device 10 of FIG. The interactive information acquisition method of the present embodiment is not limited to the use of the interactive information acquisition device 10 of FIG.

First, the general question presenting means 11 refers to the general question database 40 and presents the general question to the user (S1). The general question database 40 is a database that stores general questions for each preset question attribute. The general question is a question that is not a purpose question described later, and is not particularly limited. For example, a question having the same question attribute as the purpose question described later. In addition, the general question database 40 may further include chats such as aizuchi and greetings. Then, the general question presenting means 11 may present the chat and the general question together. The question attribute is not particularly limited, and can be arbitrarily set by, for example, the questioner or the administrator of the present device 10. A plurality of the question attributes may be associated with, for example, one general question and a target question described later. The format of the presentation is not particularly limited, and for example, the general question may be presented to the user as text data by a conversational interface. Further, when the apparatus 10 further includes, for example, the voice input / output means, the general question may be presented to the user as voice data as described later.

Next, the general answer acquisition means 12 acquires the user's general answer to the general question (S2). The format of the acquisition is not particularly limited, and for example, the general answer may be acquired from the user as text data by using a conversational interface. Further, when the apparatus 10 further includes the voice input / output means, for example, the general answer may be obtained from the user as voice data as described later.

Next, the clarity calculation means 13 calculates the clarity from the general answer (S3). The clarity is a value indicating the degree of motivation of the user to interact with the question attribute. Specifically, for example, the clarity can be calculated using a clarity calculation device described later.

Next, the consciousness calculation means 14 calculates the consciousness for each question attribute using the question attribute set for the presented general question and the clarity (S4). The degree of consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute. Specifically, for example, the consciousness level can be calculated using a consciousness level calculation device described later. The degree of consciousness may be stored in the general question database 40 in association with the general question, for example.

Next, the implication ratio calculation means 15 calculates the implication ratio in the presented general question for each question attribute from the degree of consciousness (S5). The implication ratio is a value indicating the implication ratio of the question attribute in the presented general question.

Next, the determination means 16 refers to the target question database 50 to determine whether or not the implication ratio satisfies the threshold value (S6). The purpose question database 50 is a database that stores the purpose question and the threshold value of the implication ratio. The threshold value is not particularly limited, and can be arbitrarily set by, for example, a questioner, an administrator of the present device 10, or the like. The purpose question is associated with the general question by the question attribute. The purpose question is a question that the questioner wants to ask the user, and is not particularly limited. It is preferable that the question is a question in which the user feels psychological resistance to answer. In addition, the purpose question database 50 may further include chats such as aizuchi and greetings. Then, the purpose question presenting means 17, which will be described later, may present the chat and the general question together.

When the threshold value is satisfied (YES), the target question presenting means 17 refers to the target question database 50 and presents the target question associated with the set question attribute to the user (S7). For example, when the question attribute is a plurality, the purpose question presenting means 17 may present a purpose question including all of the plurality of question attributes of the general question. Specifically, for example, if the question attribute of the general question presented is (meal, family), the purpose question is linked to the question attribute (meal, family), question attribute (meal, family, housework), etc. Present the given purpose question. The format of the presentation is not particularly limited, and for example, the target question may be presented to the user as text data by a conversational interface. Further, when the apparatus 10 further includes the voice input / output means, for example, the target question may be presented to the user as voice data as described later.

Next, the purpose answer acquisition means 18 acquires the user's purpose answer to the purpose question (S8). Then, the purpose answer acquisition means 18 stores the acquired answer in the intention database 60 (S9) and ends (END). The intention database 60 is a database that stores a user's purpose answer to the purpose question. The format of the acquisition is not particularly limited, and for example, the target answer may be acquired from the user as text data by using a conversational interface. Further, for example, when the present device 10 further includes the voice input / output means, the target answer may be acquired from the user as voice data as described later.

Further, the apparatus 10 may further calculate the clarity from the purpose answer by the clarity calculation means 13 after the step (S8) and before the step (S9), for example. Then, the purpose answer acquisition means 18 may further store the purpose answer and the clarity of the purpose answer in association with each other. When calculating the clarity for the purpose answer, the apparatus 10 may further include, for example, machine learning means. The machine learning means generates scenario data obtained by digitizing a scenario from the clarity of the purpose answer to the presentation of the general question to the presentation of the purpose question by machine learning. The machine learning is not particularly limited, and for example, a known technique can be used. The scenario will be described in detail later. As a result, the present device 10 can generate, for example, scenario data in which the clarity of the target question tends to be high. Further, the machine learning means may generate the shortest scenario data from the degree of consciousness to the presentation of the target question by machine learning. As a result, the present device 10 can reduce the number of general questions asked until the target question is presented, for example, and can reduce the annoyance for the user.

On the other hand, if the threshold value is not satisfied (NO), for example, the process may be terminated as it is (END). If the threshold value is not satisfied, (NO), for example, the process may be returned to the step (S1) and repeated processing may be performed. The step (S1) of the iterative process presents, for example, a general question different from the general question presented. As the different general question, for example, it is preferable that the target answer has not been obtained by the past processing and the general question has the highest degree of consciousness other than the presented general question.

The apparatus 10 may further include, for example, a degree of attention calculation means. The attention level calculating means calculates, for example, the attention level indicating the number of times the question attribute is used before the step (S5). That is, as the number of times increases, the degree of attention also increases. In this case, the implication ratio calculating means 15 calculates the value obtained by multiplying the degree of consciousness and the degree of attention as the implication ratio.

The apparatus 10 may further include, for example, an attribute information acquisition means. In this case, the apparatus 10 acquires the user's attribute information by the attribute information acquisition means, for example, before the step (S7). The attribute information is not particularly limited, and is, for example, information such as age, gender, nationality, occupation, hobbies, family structure, friendship, medical history, work history, and educational background. The attribute information may be one or two or more. The attribute information can be acquired via, for example, an input device 105, a communication device 107, or the like. Then, the purpose question includes, for example, the condition of the respondent for each purpose question. The respondent is a user who answers each question presented by the apparatus 10. The conditions of the respondent are not particularly limited, and can be arbitrarily set by, for example, the questioner, the administrator of the apparatus 10, and the like. Specifically, for example, conditions such as age, gender, nationality, occupation, hobbies, family structure, friendship, medical history, work history, and educational background. These conditions may be one or a combination. Then, in this case, the purpose question presenting means 17 presents the purpose question satisfying the condition of the respondent to the user based on the attribute information. That is, if the attribute information is, for example, "65 years old, male, with children", the purpose question presenting means 17 has answer conditions of "60 to 70 years old", "60 to 70 years old, male", "60". It is possible to present purpose questions such as "~ 70 years old, male, with children".

The apparatus 10 may further include, for example, audio input / output means. The voice input / output means outputs each of the presentations in the general question presenting means 11 and the purpose question presenting means 17 as voice data. Further, each of the above acquisitions by the general answer acquisition means 12 and the purpose answer acquisition means 18 is input as voice data.

The apparatus 10 may further include, for example, the above-mentioned purpose answer updating means. In this case, the purpose answer acquisition means further stores the time information in which the purpose answer is stored in the intention database 60 in association with the purpose answer. Then, when a preset period (for example, every 6 months or the like) elapses from the stored time information, the purpose response updating means updates at least one of the stored purpose response and the time information. Specifically, for example, by re-presenting the general question and the purpose question with reference to the scenario data when the purpose answer is obtained for the purpose answer after a preset period has passed. The update may be performed. Further, for the purpose answer after the preset period has passed, only the purpose question when the purpose answer is obtained may be re-presented. As a result, the apparatus 10 can confirm the intention of the user (respondent) on a regular basis, for example.

The purpose answer updating means may further extend the period of the purpose question in which the purpose answer is updated infrequently. The update frequency can be calculated from, for example, the log data of the purpose response stored in the intention database 60. Specifically, for example, depending on the update frequency, if the purpose answer acquired two times before, the purpose answer acquired last time, and the purpose answer acquired this time have the same contents, the purpose answer acquired next time may also be obtained. It can be predicted that the contents are the same. That is, the present device 10 can read the change tendency of the user's intention (purpose answer) by, for example, the purpose answer updating means. As a result, the present device 10 can save the trouble and trouble for the user by extending the re-presentation period of the purpose question, for example, in which the user's intention is firm (that is, the update frequency is low).

Here, FIG. 4 shows an example in which the present invention is applied to a user. In FIG. 4, the apparatus 10 is illustrated as a chatbot 1 in which the program of the present invention is installed, but is an example and is not limited thereto. In FIG. 4, the left side shows an example of a dialogue between the chatbot 1 and the user 2, and the right side shows an example of the processing result in the chatbot 1 in the dialogue. As shown in FIG. 4, the chatbot 1 first presents question A to user 2 as a general question. Next, the user 2 speaks the answer A to the chatbot 1 as an answer to the question A. The chatbot 1 acquires the answer A as a general answer. The question A and the answer A are collectively referred to as a dialogue A. Then, the chatbot 1 calculates the clarity level, the consciousness level, and the implication ratio from the answer A, respectively. The specific calculation method will be described later. Then, as shown in FIG. 4, as a result of each of the calculations, it was determined by the chatbot 1 that the dialogue A did not satisfy the threshold value of the implication ratio. Therefore, the chatbot 1 presents the question B to the user as the next general question, and obtains the answer B in the same manner as the dialogue A (dialogue B). Then, similarly to the dialogue A, it was determined that the dialogue B does not satisfy the threshold value of the implication ratio. Therefore, the chatbot 1 presents the question C to the user as the next general question, and obtains the answer C in the same manner as the dialogue A (dialogue C). Then, as a result of each of the calculations, the dialogue C is determined by the chatbot 1 to satisfy the threshold value of the implication ratio, and the objective question database 50 is referred to, and the objective question "In the future, one's own meal assistance is required." What if? " In FIG. 4, the chatbot 1 communicates with another chatbot. Then, the machine learning means modifies the context of the objective question so that the objective answer with high clarity can be easily obtained, and presents the modified objective question to the user 2 (question D). Then, the chatbot 1 acquires the answer D from the user 2 and executes each calculation from the answer D. Here, in the present invention, the scenario means, for example, a series of flows from the dialogue A in which the first general question is presented to the dialogue D in which the target question is presented, as shown in FIG.

FIG. 5 shows another example in which the present invention is applied to a user. FIG. 5 is the same as the example shown in FIG. 4, except that the contents of the dialogues A to D and the processing results are different.

According to the present embodiment, since the general question is presented and then the target question is presented, for example, information can be easily acquired while having a dialogue. In addition, the general question and the purpose question are linked by the question attribute. Therefore, even if the purpose question has psychological resistance to be answered, the user can easily think about and answer the purpose question as the general question with low psychological resistance is answered. ..

[Embodiment 2]
FIG. 6 is a block diagram showing a configuration of an example of the clarity calculation device 20 of the present embodiment. As shown in FIG. 6, the present device 20 includes an intelligibility calculation means 21, a response time calculation means 22, and an intelligibility calculation means 23. The device 20 can be used, for example, as the clarity calculation means 13 in the interactive information acquisition device 10 of the first embodiment.

The device 20 may be, for example, one device including the above-mentioned parts, or a device in which the above-mentioned parts can be connected via a communication network. Although not shown, the device 20 can be connected to an external device described later via the communication network. The communication network is not particularly limited, and a known network can be used. For example, it may be wired or wireless. The communication network is, for example, the same as described above. The apparatus 20 may be incorporated in the server as a system, for example. Further, the device 20 may be, for example, a personal computer (PC, for example, a desktop type, a notebook type), a smartphone, a tablet terminal, or the like in which the program of the present invention is installed.

FIG. 7 illustrates a block diagram of the hardware configuration of the present device 20. The device 20 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, a storage device 104, an input device 105, a display device (display) 106, a communication device 107, and the like. Each part of the hardware configuration of the apparatus 20 is connected to each other via the bus 103 by each interface (I / F). Unless otherwise specified, the description of each part of the hardware configuration of the present device 20 can be referred to, for example, the description of each part of the hardware configuration in the interactive information acquisition device 10 of the first embodiment.

The central processing unit (central processing unit) 101 functions as, for example, the clarity calculation means 21, the response time calculation means 22, and the clarity calculation means 23.

Next, an example of the clarity calculation method of the present embodiment will be described based on the flowchart of FIG. The clarity calculation method of the present embodiment is carried out as follows, for example, by using the clarity calculation device 20 of FIG. The clarity calculation method of the present embodiment is not limited to the use of the clarity calculation device 20 of FIG.

First, the intelligibility calculating means 21 calculates the intelligibility indicating the degree of intelligibility of the answer from the user's answer to at least one of the general question and the purpose question (S1). The general question and the purpose question are, for example, the same as described above. The intelligibility calculation means 21 may calculate the intelligibility using, for example, an if-else type source code. In this case, the if sentence is a conditional sentence that associates an arbitrary intelligibility with each arbitrary word, and the else sentence is a conditional sentence that associates an arbitrary intelligibility with a word other than the arbitrary word. Each word in the if statement is, for example, a word included in a dictionary. Specifically, for example, the intelligibility (amb) can be set using the following source code. The following source code is an example and is not limited thereto. Further, in the if sentence of the following source code, a plurality of words are associated with arbitrary intelligibility between the words "yes" and the words "er". In the following source code, the arbitrary intelligibility is evaluated on a scale of 10 by giving a smaller number to a word having higher intelligibility, but it is an example and is not limited thereto. Further, in the following source code, the arbitrary intelligibility in the else statement is set to "2". For example, the intelligibility calculation means 21 refers to the following source code "um: 10" from the answer B "Well, not so much. I don't have a chance." Shown in FIG. 4, and sets the intelligibility of the answer B to 10. Calculate as. That is, it can be said that the intelligibility of the answer B is low.

amb = if (yes :: 1, ... um: 10) else 2

Next, the response time calculation means 22 calculates the length of time until the answer is obtained (S2). The unit of time is not particularly limited, and includes, for example, hours, minutes, seconds, and the like, preferably seconds. Specifically, for example, it may be calculated as the total length of time from presenting at least one of the general question and the purpose question to the user until an answer is obtained. Further, when the user uses the apparatus 20 a plurality of times, for example, the length of the time may be calculated using the following (Equation 1). The calculated length of time may be stored in the storage device 104, for example. The step (S2) may be processed before, for example, the step (S1), or may be processed in parallel with the step (S1).


tt = t / t'(Equation 1)

tt: The length of time calculated by the response time calculation means 22 t: The length of time required to obtain the answer t': The average value of the length of time required to obtain the answer

The t'may be an average value based on a specific user, or may be an average value based on a plurality of users. When the t'is shorter than the t, it means that the user was able to answer with less trouble than usual, for example. When the t'is shorter than the t, the calculated value of the tt is, for example, 0 or more and 1 or less. Therefore, when the apparatus 20 calculates the intelligibility (cl) using (Equation 2) described later, for example, the value obtained by multiplying the intelligibility (amb) by the tt becomes small, and the intelligibility cl becomes small. growing.

Then, the clarity calculation means 23 calculates the clarity using the clarity and the length of the time (S3), and ends (END). The clarity is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question, as described above. Specifically, for example, the clarity may be calculated using the following (Equation 2).

Cl = 1 / (amb × tt) (Equation 2)

Cl: Clarity amb: The intelligibility calculated by the intelligibility calculating means 21 tt: The length of the time calculated by the answering time calculating means 22

According to this embodiment, the degree of motivation of the user to interact can be quantified. As a result, the interactive information acquisition device including the present device 20 can ask the highly motivated question, so that it is easy to obtain an answer from the user and the information can be easily acquired. The interactive information acquisition device is not particularly limited, but is preferably the interactive information acquisition device of the present invention.

[Embodiment 3]
FIG. 9 is a block diagram showing a configuration of an example of the consciousness calculation device 30 of the present embodiment. As shown in FIG. 9, the present device 30 includes a clarity calculation means 31, a likelihood setting means 32, and a consciousness calculation means 33. The device 30 can be used, for example, as the consciousness calculation means 14 in the interactive information acquisition device 10 of the first embodiment.

The device 30 may be, for example, one device including the above-mentioned parts, or a device in which the above-mentioned parts can be connected via a communication network. Further, although not shown, the present device 30 can be connected to an external device described later via the communication network. The communication network is not particularly limited, and a known network can be used. For example, it may be wired or wireless. The communication network is, for example, the same as described above. The device 30 may be incorporated in the server as a system, for example. Further, the device 30 may be, for example, a personal computer (PC, for example, a desktop type, a notebook type), a smartphone, a tablet terminal, or the like in which the program of the present invention is installed.

FIG. 10 illustrates a block diagram of the hardware configuration of the present device 30. The device 30 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, a storage device 104, an input device 105, a display device (display) 106, a communication device 107, and the like. Each part of the hardware configuration of the apparatus 30 is connected to each other via the bus 103 by each interface (I / F). Unless otherwise specified, the description of each part of the hardware configuration of the present device 30 can be referred to, for example, the description of each part of the hardware configuration in the interactive information acquisition device 10 of the first embodiment.

The central processing unit (central processing unit) 101 functions as, for example, the clarity calculation means 31, the likelihood setting means 32, and the consciousness calculation means 33.

Next, an example of the consciousness calculation method of the present embodiment will be described based on the flowchart of FIG. The consciousness calculation method of the present embodiment is carried out as follows, for example, using the consciousness calculation device 30 of FIG. The clarity calculation method of the present embodiment is not limited to the use of the consciousness calculation device 30 of FIG.

First, the clarity calculation means 31 calculates the clarity from the user's answers to at least one of the general question and the purpose question (S1). The clarity is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question, as described above. The clarity calculation means 31 may calculate the clarity using, for example, the clarity calculation device of the second embodiment.

Next, the likelihood setting means 32 sets an arbitrary likelihood for each of the question attributes (S2). The likelihood setting means 32 may set an arbitrary likelihood according to the number of times the general question is presented, for example. Further, different likelihoods may be set for the general question and the purpose question. The step (S2) may be processed before, for example, the step (S1), or may be processed in parallel with the step (S1).

Then, the consciousness calculation means 33 calculates the consciousness using the clarity and the likelihood (S3), and ends (END). The degree of consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute, as described above. The consciousness calculation means 33 may calculate the consciousness using, for example, the following (Equation 3).

int _n = Fv1 + (cl-Fv2) × x _n (Equation 3)

int _n : Consciousness degree in question attribute n Fv1: First fixed value Fv2 set in advance: Second fixed value set in advance cl: Clarity calculated by the clarity calculation means x _n : Set by the likelihood setting means Likelihood at the question attribute n

Any value can be set for the Fv1 and the Fv2. Further, in the consciousness calculation means 33, for example, when the consciousness is calculated for the second time or later, the consciousness calculated in the i-1st time (i ≧ 2) may be the Fv1. In this case, Fv1 in the first calculation of the degree of consciousness is also referred to as, for example, an initial value. If the initial value is set high, for example, when the apparatus 30 is used as the consciousness calculation means 14 in the interactive information acquisition apparatus 10 of the first embodiment, the objective answer can be acquired at an early stage.

According to this embodiment, the degree of consciousness of the user to think about the question attribute can be quantified. As a result, the interactive information acquisition device including the present device 30 can ask the highly conscious question, so that it is easy to obtain an answer from the user and the information can be easily acquired. The interactive information acquisition device is not particularly limited, but is preferably the interactive information acquisition device of the present invention.

[Embodiment 4]
Next, a specific example of calculating the clarity, the consciousness, and the implication ratio will be shown with reference to FIGS. 4 and 5, and FIGS. 12 and 13.

The question attribute of question A in FIG. 4 is, for example, "meal (question attribute 1), family (question attribute 2), housework (question attribute 3)". Hereinafter, the question attribute “meal (question attribute 1)” will be described as a representative example with reference to FIG. First, the calculation of the clarity (cl) will be described. In answer A, in the above (formula 2), for example, the intelligibility (amb) is set to 5, and the length of time (tt) is set to 0.25 (seconds). Then, when these values are substituted into the above (Equation 2), “cl = 1 / (5 × 0.25)” is obtained, and the clarity (cl) of the “meal (question attribute 1)” of the answer A is 0. It becomes 8.8. Next, the calculation of the degree of consciousness (int ₁ ) using the calculated degree of clarity (cl) will be described. In answer A, in the above (formula 3), for example, Fv1 (initial value) is 15, Fv2 is 0.5, and the likelihood (x ₁ ) is 50. Then, when these values are substituted into the above (Equation 3), “int ₁ = 15 + (0.8-0.5) × 50” is obtained, and the degree of consciousness of “meal (question attribute 1)” of the answer A (question attribute 1) ( int ₁ ) is 30. Next, the calculation of the implication ratio (th _{1 ) using the calculated consciousness degree (int 1} ) will be described. The degree of attention (Fr ₁ ) is, for example, one time of "breakfast" in question A, which is a word related (similar) to the question attribute "meal (question attribute 1)". Then, when the calculated consciousness level (int ₁ ) is multiplied by the attention level, “th ₁ = 30 × 1” is obtained, and the implication ratio (th ₁ ) of the “meal (question attribute 1)” of the answer A is. , 30%. The determination means 16 of the interactive information acquisition device 10 determines whether or not the calculated implication ratio (30%) exceeds a preset threshold value (for example, 50%). In the case of FIG. 4, since the threshold value is not exceeded, the process proceeds to the dialogue B. Similarly, each calculation formula and result in dialogue B to dialogue D are shown in FIG.

The question attribute of question A in FIG. 5 is, for example, "family (question attribute 1), long-term care (question attribute 2), will (question attribute 3)". Hereinafter, the question attribute “family (question attribute 1)” will be described as a representative example with reference to FIG. First, the calculation of the clarity (cl) will be described. In answer A, in the above (formula 2), for example, the intelligibility (amb) is set to 5, and the length of time (tt) is set to 0.25 (seconds). Then, when these values are substituted into the above (Equation 2), “cl = 1 / (5 × 0.25)”, and the clarity (cl) of the “family (question attribute 1)” of the answer A is 0. It becomes 8.8. Next, the calculation of the degree of consciousness (int ₁ ) using the calculated degree of clarity (cl) will be described. In answer A, for example, in the above (formula 3), Fv1 (initial value) is 15, Fv2 is 0.5, and the likelihood (x ₁ ) is 100. Then, when these values are substituted into the above (Equation 3), “int ₁ = 15 + (0.8-0.5) × 100” is obtained, and the degree of consciousness of the “family (question attribute 1)” of the answer A (question attribute 1) ( int ₁ ) is 45. Next, the calculation of the implication ratio (th _{1 ) using the calculated consciousness degree (int 1} ) will be described. The degree of attention (Fr ₁ ) is, for example, one time of "family" in question A, which is the same word as the question attribute "family (question attribute 1)". Then, when the calculated consciousness level (int ₁ ) is multiplied by the attention level, “th ₁ = 45 × 1” is obtained, and the implication ratio (th ₁ ) of the “family (question attribute 1)” in the answer A is. , 45%. The determination means 16 of the interactive information acquisition device 10 determines whether or not the calculated implication ratio (45%) exceeds a preset threshold value (for example, 50%). In the case of FIG. 5, since the threshold value is not exceeded, the process proceeds to the dialogue B. Similarly, each calculation formula and result in dialogue B to dialogue D are shown in FIG.

[Embodiment 5]
The program of this embodiment is a program that can execute the method of each of the above-described embodiments on a computer. Further, the program of the present embodiment may be recorded on a computer-readable recording medium, for example. The recording medium is not particularly limited, and examples thereof include HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, and memory card.

Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the structure and details of the present invention within the scope of the present invention.

<Additional notes>
Some or all of the above embodiments may be described as, but not limited to, the following appendices.
(Appendix 1)
Includes general question presentation means, general answer acquisition means, clarity calculation means, consciousness calculation means, implication ratio calculation means, judgment means, purpose question presentation means, and purpose answer acquisition means.
The general question presenting means refers to the general question database and presents the general question to the user.
The general question database is a database that stores general questions for each preset question attribute.
The general answer acquisition means acquires the user's general answer to the general question, and obtains the general answer.
The clarity calculation means calculates the clarity from the general answer, and then
The clarity is a value indicating the degree of motivation of the user to interact with the question attribute.
The consciousness calculation means calculates the consciousness for each question attribute by using the question attribute set for the presented general question and the clarity.
The degree of consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute.
The implication ratio calculation means calculates the implication ratio in the presented general question for each question attribute from the degree of consciousness.
The determination means refers to the purpose question database and determines whether or not the implication ratio satisfies the threshold value.
The purpose question database is a database that stores the purpose question and the threshold value of the implication ratio.
The purpose question is associated with the general question by the question attribute.
When the above threshold is satisfied
The purpose question presenting means refers to the purpose question database and presents the purpose question associated with the set question attribute to the user.
The purpose answer acquisition means acquires the user's purpose answer to the purpose question, and stores the acquired answer in the intention database.
The intention database is an interactive information acquisition device that is a database that stores a user's purpose answer to the purpose question.
(Appendix 2)
When the above threshold is satisfied
The clarity calculation means further calculates the clarity from the purpose response.
The interactive information acquisition device according to Appendix 1, wherein the object response acquisition means further stores the object answer and the clarity of the object answer in association with each other.
(Appendix 3)
In addition, it includes machine learning means
The interactive information according to Appendix 2, wherein the machine learning means generates scenario data obtained by digitizing a scenario from the clarity of the purpose answer to the presentation of the general question to the presentation of the purpose question by machine learning. Acquisition device.
(Appendix 4)
The interactive information acquisition device according to Appendix 3, wherein the machine learning means generates the shortest scenario data from the degree of consciousness to the presentation of the target question by machine learning.
(Appendix 5)
If the threshold is not met,
The interactive information acquisition device according to any one of Supplementary note 1 to 4, wherein the general question presenting means presents a general question different from the presented general question.
(Appendix 6)
A plurality of the question attributes are associated with one purpose question and a general question.
The interactive information acquisition device according to any one of Supplementary note 1 to 5, wherein the purpose question presenting means presents a purpose question including all of a plurality of question attributes of the presented general question.
(Appendix 7)
In addition, it includes a means of calculating attention.
The attention degree calculating means calculates the attention degree indicating the number of times the question attribute is used, and calculates the attention degree.
The interactive information acquisition device according to any one of Supplementary note 1 to 6, wherein the implication ratio calculating means calculates a value obtained by multiplying the degree of consciousness and the degree of attention as an implication ratio.
(Appendix 8)
Furthermore, including the attribute information acquisition means,
The attribute information acquisition means acquires the attribute information of the user and obtains the attribute information of the user.
The purpose question includes the conditions of the respondent for each purpose question.
The interactive information acquisition device according to any one of Supplementary note 1 to 7, wherein the purpose question presenting means presents a purpose question satisfying the conditions of the respondent to the user based on the attribute information.
(Appendix 9)
In addition, it includes audio input / output means
The voice input / output means outputs each of the presentations in the general question presenting means and the purpose question presenting means as voice data.
The interactive information acquisition device according to any one of Appendix 1 to 8, wherein each of the acquisitions by the general answer acquisition means and the purpose answer acquisition means is input as voice data.
(Appendix 10)
In addition, including means for updating purpose answers,
The purpose answer acquisition means further stores the time information in which the purpose answer is stored in the intention database in association with the purpose answer.
The interactive information acquisition according to any one of Appendix 1 to 9, wherein the purpose response updating means updates at least one of the stored purpose response and the time information when a preset period elapses from the time information. apparatus.
(Appendix 11)
The interactive information acquisition device according to Appendix 10, wherein the purpose answer updating means extends the period for a purpose question in which the purpose answer is updated infrequently.
(Appendix 12)
Including intelligibility calculation means, response time calculation means, and intelligibility calculation means,
The intelligibility calculation means calculates the intelligibility indicating the degree of intelligibility of the answer from the user's answer to at least one of the general question and the purpose question.
The answer time calculation means calculates the length of time until the answer is obtained, and obtains the answer.
The clarity calculation means calculates the clarity by using the clarity and the length of time.
The clarity calculation device is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question.
(Appendix 13)
The intelligibility calculation means calculates the intelligibility using an if-else type source code.
The if sentence is a conditional sentence that associates an arbitrary intelligibility with each arbitrary word.
The clarity calculation device according to Appendix 12, wherein the else sentence is a conditional sentence that associates an arbitrary clarity with a word other than the arbitrary word.
(Appendix 14)
The clarity calculation device according to Appendix 12 or 13, wherein the response time calculation means calculates the length of the time using the following (Equation 1).

tt = t / t'(Equation 1)

tt: The length of the time calculated by the answer time calculation means t: The length of the time required to obtain the answer t': The average value of the length of the time required to obtain the answer


(Appendix 15)
The clarity calculation device according to any one of Appendix 12 to 14, wherein the clarity calculation means calculates the clarity using the following (Equation 2).

Cl = 1 / (amb × tt) (Equation 2)

Cl: Clarity amb: Clarity calculated by the clarity calculation means tt: Length of time calculated by the response time calculation means

(Appendix 16)
The clarity calculation device according to any one of Supplements 12 to 15, which is used for the clarity calculation means in the interactive information acquisition device according to any one of Supplements 1 to 11.
(Appendix 17)
Includes clarity calculation means, likelihood setting means, and consciousness calculation means
The clarity calculation means calculates the clarity from the user's answers to at least one of the general question and the purpose question.
The clarity is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question.
The likelihood setting means sets an arbitrary likelihood for each question attribute, and sets an arbitrary likelihood.
The consciousness calculation means calculates the consciousness using the clarity and the likelihood.
The consciousness level is a value indicating the degree of consciousness that the user thinks about the question attribute, which is a consciousness level calculation device.
(Appendix 18)
The consciousness calculation device according to Appendix 17, wherein the consciousness calculation means calculates the consciousness using the following (Equation 3).

int _n = Fv1 + (cl-Fv2) × x _n (Equation 3)

int _n : Consciousness degree in question attribute n Fv1: First fixed value Fv2 set in advance: Second fixed value set in advance cl: Clarity calculated by the clarity calculation means x _n : Set by the likelihood setting means Likelihood at the question attribute n

(Appendix 19)
The consciousness calculation device according to Appendix 18, wherein the consciousness calculation means sets the consciousness calculated in the first i-1st time (i ≧ 2) as the Fv1.
(Appendix 20)
The consciousness calculation device according to any one of Appendix 17 to 19, wherein the clarity calculation means calculates the clarity using the clarity calculation device according to any one of Supplements 12 to 16.
(Appendix 21)
The consciousness calculation device according to any one of Supplements 17 to 20, which is used for the consciousness calculation means in the interactive information acquisition device according to any one of Supplements 1 to 11.
(Appendix 22)
Includes general question presentation process, general answer acquisition process, clarity calculation process, awareness calculation process, implication ratio calculation process, judgment process, purpose question presentation process, and purpose answer acquisition process.
In the general question presentation process, the general question is presented to the user with reference to the general question database.
The general question database is a database that stores general questions for each preset question attribute.
In the general answer acquisition process, the user's general answer to the general question is acquired, and the general answer is acquired.
In the clarity calculation step, the clarity is calculated from the general answer, and the clarity is calculated.
The clarity is a value indicating the degree of motivation of the user to interact with the question attribute.
In the consciousness calculation step, the consciousness is calculated for each question attribute using the question attribute set for the presented general question and the clarity.
The degree of consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute.
In the implication ratio calculation step, the implication ratio for each question attribute in the general question is calculated from the degree of consciousness.
In the determination step, it is determined whether or not the implication ratio satisfies the threshold value with reference to the purpose question database.
The purpose question database is a database that stores the purpose question and the threshold value of the implication ratio.
The purpose question is associated with the general question by the question attribute.
When the above threshold is satisfied
The purpose question presenting step refers to the purpose question database and presents the purpose question associated with the extracted question attribute to the user.
In the purpose answer acquisition process, the user's purpose answer to the purpose question is acquired, and the acquired answer is stored in the intention database.
The intention database is an interactive information acquisition method, which is a database for storing a user's purpose answer to the purpose question.
(Appendix 23)
When the above threshold is satisfied
In the clarity calculation step, the clarity is further calculated from the purpose response, and the clarity is calculated.
The interactive information acquisition method according to Appendix 22, wherein the object response acquisition step further stores the object answer and the clarity of the object answer in association with each other.
(Appendix 24)
In addition, it includes a machine learning process
The interactive information according to Appendix 23, wherein the machine learning process generates scenario data obtained by digitizing a scenario from the clarity of the purpose answer to the presentation of the general question to the presentation of the purpose question by machine learning. Acquisition method.
(Appendix 25)
The interactive information acquisition method according to Appendix 24, wherein the machine learning step generates the shortest scenario data from the degree of consciousness to the presentation of the target question by machine learning.
(Appendix 26)
If the threshold is not met,
The interactive information acquisition method according to any one of Supplementary note 22 to 25, wherein the general question presenting step presents a general question different from the presented general question.
(Appendix 27)
A plurality of the question attributes are associated with one purpose question and a general question.
The interactive information acquisition method according to any one of Supplementary note 22 to 26, wherein the purpose question presenting step presents a purpose question including all of a plurality of question attributes of the presented general question.
(Appendix 28)
In addition, it includes a attention calculation process.
In the attention level calculation step, the attention level indicating the number of times the question attribute is used is calculated.
The interactive information acquisition method according to any one of Supplementary note 22 to 27, wherein the implication ratio calculation step calculates a value obtained by multiplying the degree of consciousness and the degree of attention as an implication ratio.
(Appendix 29)
Furthermore, including the attribute information acquisition process,
In the attribute information acquisition process, the user's attribute information is acquired, and the user's attribute information is acquired.
The purpose question includes the conditions of the respondent for each purpose question.
The interactive information acquisition method according to any one of Supplementary note 22 to 28, wherein the purpose question presenting step presents a purpose question satisfying the conditions of the respondent to the user based on the attribute information.
(Appendix 30)
In addition, it includes a voice input / output process.
The voice input / output step outputs each of the presentations in the general question presentation step and the purpose question presentation step as voice data.
The interactive information acquisition method according to any one of Supplementary note 22 to 29, wherein each of the acquisitions in the general response acquisition step and the purpose response acquisition step is input as voice data.
(Appendix 31)
In addition, including the purpose response update process,
In the purpose answer acquisition process, the time information in which the purpose answer is stored is further associated with the purpose answer and stored in the intention database.
The interactive information acquisition according to any one of Appendix 22 to 30, wherein the purpose response updating step updates at least one of the stored purpose response and the time information when the time information elapses for a preset period. Method.
(Appendix 32)
The interactive information acquisition method according to Appendix 31, wherein the purpose answer updating step extends the period for a purpose question in which the purpose answer is updated infrequently.
(Appendix 33)
Including intelligibility calculation process, response time calculation process, and intelligibility calculation process
In the intelligibility calculation step, the intelligibility indicating the degree of intelligibility of the answer is calculated from the user's answer to at least one of the general question and the purpose question.
In the answer time calculation step, the length of time until the answer is obtained is calculated.
In the clarity calculation step, the clarity is calculated using the clarity and the length of time.
The clarity degree is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question.
(Appendix 34)
In the intelligibility calculation step, the intelligibility is calculated using an if-else type source code.
The if sentence is a conditional sentence that associates an arbitrary intelligibility with each arbitrary word.
The clarity calculation method according to Appendix 33, wherein the else sentence is a conditional sentence that associates an arbitrary clarity with a word other than the arbitrary word.
(Appendix 35)
The clarity calculation method according to Appendix 33 or 34, wherein the response time calculation step calculates the length of the time using the following (Equation 1).

tt = t / t'(Equation 1)

tt: The length of the time calculated by the answer time calculation step t: The length of the time required to obtain the answer t': The average value of the length of the time required to obtain the answer

(Appendix 36)
The clarity calculation method according to any one of Supplementary note 33 to 35, wherein the clarity calculation step calculates the clarity using the following (Equation 2).

Cl = 1 / (amb × tt) (Equation 2)

Cl: Clarity amb: Clarity calculated by the clarity calculation step tt: Length of time calculated by the response time calculation step

(Appendix 37)
The clarity calculation method according to any one of Supplements 33 to 36, which is used in the clarity calculation step in the interactive information acquisition method according to any one of Supplements 22 to 32.
(Appendix 38)
Includes clarity calculation process, likelihood setting process, and awareness calculation process
In the clarity calculation step, the clarity is calculated from the user's answers to at least one of the general question and the purpose question.
The clarity is a value indicating the degree of motivation of the user to interact with the question attribute of at least one of the general question and the purpose question.
In the likelihood setting step, an arbitrary likelihood is set for each question attribute, and an arbitrary likelihood is set.
In the consciousness calculation step, the consciousness is calculated using the clarity and the likelihood.
The consciousness level is a value indicating the degree of consciousness that the user thinks about the question attribute, which is a method of calculating the consciousness level.
(Appendix 39)
The consciousness calculation method according to Appendix 38, wherein the consciousness calculation step calculates the consciousness using the following (Equation 3).

int _n = Fv1 + (cl-Fv2) × x _n (Equation 3)

int _n : Consciousness degree in question attribute n Fv1: First fixed value Fv2 set in advance: Second fixed value set in advance cl: Clarity calculated by the clarity calculation step x _n : Set by the likelihood setting step Likelihood at the question attribute n

(Appendix 40)
The consciousness calculation method according to Appendix 39, wherein the consciousness calculation step sets the consciousness calculated in the first i-1st time (i ≧ 2) as the Fv1.
(Appendix 41)
The consciousness calculation method according to any one of Supplements 38 to 40, wherein the clarity calculation step calculates the clarity using the clarity calculation method according to any one of Supplements 33 to 37.
(Appendix 42)
The consciousness calculation method according to any one of Supplements 38 to 41, which is used in the consciousness calculation step in the interactive information acquisition method according to any one of Supplements 22 to 32.
(Appendix 43)
A program capable of executing the method according to any one of Appendix 22 to 33 on a computer.
(Appendix 44)
A computer-readable recording medium on which the program described in Appendix 43 is recorded.

According to the present invention, for example, information can be easily acquired while interacting with each other. Therefore, the present invention is particularly useful when, for example, asking a question in which the user feels psychological resistance to answering.

1 Chatbot 2 User 10 Interactive information acquisition device 11 General question presentation means 12 General answer acquisition means 13 Clarity calculation means 14 Consciousness calculation means 15 Implication ratio calculation means 16 Judgment means 17 Purpose question presentation means 18 Purpose answer acquisition means 20 Clarity calculation device 21 Clarity calculation means 22 Answer time calculation means 23 Clarity calculation means 30 Awareness calculation device 31 Clarity calculation means 32 Liability setting means 33 Awareness calculation means 40 General question database 50 Purpose question database 60 Intention database 101 Central computing device 102 Memory 103 Bus 104 Storage device 105 Input device 106 Display device 107 Communication device

Claims (10)

Includes general question presentation means, general answer acquisition means, clarity calculation means, consciousness calculation means, implication ratio calculation means, judgment means, purpose question presentation means, and purpose answer acquisition means.
The general question presenting means refers to the general question database and presents the general question to the user.
The general question database is a database that stores general questions for each preset question attribute.
The general answer acquisition means acquires the user's general answer to the general question, and obtains the general answer.
The clarity calculation means calculates the clarity from the general answer, and then
The clarity is a value indicating the degree of motivation of the user to interact with the question attribute.
The consciousness calculation means calculates the consciousness for each question attribute by using the question attribute set for the presented general question and the clarity.
The degree of consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute.
The implication ratio calculation means calculates the implication ratio in the presented general question for each question attribute from the degree of consciousness.
The determination means refers to the purpose question database and determines whether or not the implication ratio satisfies the threshold value.
The purpose question database is a database that stores the purpose question and the threshold value of the implication ratio.
The purpose question is associated with the general question by the question attribute.
When the above threshold is satisfied
The purpose question presenting means refers to the purpose question database and presents the purpose question associated with the set question attribute to the user.
The purpose answer acquisition means acquires the user's purpose answer to the purpose question, and stores the acquired answer in the intention database.
The intention database is an interactive information acquisition device that is a database that stores a user's purpose answer to the purpose question. When the above threshold is satisfied
The clarity calculation means further calculates the clarity from the purpose response.
The interactive information acquisition device according to claim 1, wherein the object response acquisition means further stores the object answer and the clarity of the object answer in association with each other. In addition, it includes machine learning means
The interactive type according to claim 2, wherein the machine learning means generates scenario data obtained by digitizing a scenario from the clarity of the purpose answer to the presentation of the general question to the presentation of the purpose question by machine learning. Information acquisition device. The interactive information acquisition device according to claim 3, wherein the machine learning means generates the shortest scenario data from the degree of consciousness to the presentation of the target question by machine learning. In addition, it includes a means of calculating attention.
The attention degree calculating means calculates the attention degree indicating the number of times the question attribute is used, and calculates the attention degree.
The interactive information acquisition device according to any one of claims 1 to 4, wherein the implication ratio calculating means calculates a value obtained by multiplying the degree of consciousness and the degree of attention as an implication ratio. Furthermore, including the attribute information acquisition means,
The attribute information acquisition means acquires the attribute information of the user and obtains the attribute information of the user.
The purpose question includes the conditions of the respondent for each purpose question.
The interactive information acquisition device according to any one of claims 1 to 5, wherein the purpose question presenting means presents a purpose question satisfying the conditions of the respondent to the user based on the attribute information. In addition, it includes audio input / output means
The voice input / output means outputs each of the presentations in the general question presenting means and the purpose question presenting means as voice data.
The interactive information acquisition device according to any one of claims 1 to 6, wherein each of the acquisitions by the general response acquisition means and the purpose response acquisition means is input as voice data. In addition, including means for updating purpose answers,
The purpose answer acquisition means further stores the time information in which the purpose answer is stored in the intention database in association with the purpose answer.
The dialogue according to any one of claims 1 to 7, wherein the purpose response updating means updates at least one of the stored purpose response and the time information when a preset period elapses from the time information. Type information acquisition device. Includes general question presentation process, general answer acquisition process, clarity calculation process, awareness calculation process, implication ratio calculation process, judgment process, purpose question presentation process, and purpose answer acquisition process.
In the general question presentation process, the general question is presented to the user with reference to the general question database.
The general question database is a database that stores general questions for each preset question attribute.
In the general answer acquisition process, the user's general answer to the general question is acquired, and the general answer is acquired.
In the clarity calculation step, the clarity is calculated from the general answer, and the clarity is calculated.
The clarity is a value indicating the degree of motivation of the user to interact with the question attribute.
In the consciousness calculation step, the consciousness is calculated for each question attribute using the question attribute set for the presented general question and the clarity.
The degree of consciousness is a value indicating the degree of consciousness that the user thinks about the question attribute.
In the implication ratio calculation step, the implication ratio for each question attribute in the general question is calculated from the degree of consciousness.
In the determination step, it is determined whether or not the implication ratio satisfies the threshold value with reference to the purpose question database.
The purpose question database is a database that stores the purpose question and the threshold value of the implication ratio.
The purpose question is associated with the general question by the question attribute.
When the above threshold is satisfied
The purpose question presenting step refers to the purpose question database and presents the purpose question associated with the extracted question attribute to the user.
In the purpose answer acquisition process, the user's purpose answer to the purpose question is acquired, and the acquired answer is stored in the intention database.
The intention database is an interactive information acquisition method, which is a database for storing a user's purpose answer to the purpose question. A program capable of executing the method according to claim 9 on a computer.

Images