JP7033195B2 - Dialogue device - Google Patents

Description

One aspect of the present invention relates to a dialogue device.

A mechanism for managing the recording of automatic dialogues performed with users is known. For example, in Patent Document 1, when an instruction to delete information used in a predetermined process is received, the information is deleted and an identifier related to the predetermined process using the deleted information is specified, and at least. Described is a dialogue history management device that deletes the content of the voice related to the response associated with the specified identifier from the dialogue history storage unit.

Japanese Unexamined Patent Publication No. 2015-169768

The apparatus described in Patent Document 1 does not execute the deletion process unless the deletion instruction is accepted. However, there may be confidential information in the spoken text that constitutes the dialogue, which should not be recorded from the beginning. Therefore, it is desired to ensure the security of the confidential information that appears in the dialogue.

The dialogue device according to one aspect of the present invention includes an acquisition unit for acquiring an utterance sentence constituting an automatic dialogue executed with a user, and at least a part of the utterance sentence in a state where the utterance sentence is not yet recorded in a log. It includes a concealment unit that executes a concealment process for concealing confidential information on the utterance text, and a recording unit that records the utterance text in which at least a part of the confidential information is concealed in a log.

In such an aspect, since at least a part of the confidential information in the spoken text is not recorded in the log from the beginning, the security of the confidential information appearing in the dialogue can be ensured more reliably.

According to one aspect of the present invention, it is possible to more reliably ensure the security of confidential information that appears in the dialogue.

It is a figure which shows an example of the functional structure of the dialogue apparatus which concerns on embodiment. It is a sequence diagram which shows an example of the operation of the dialogue apparatus which concerns on embodiment. It is a sequence diagram which shows an example of the operation of the dialogue apparatus which concerns on embodiment. It is a figure which shows some example of a log. It is a figure which shows an example of the hardware composition of the computer used for the dialogue apparatus which concerns on embodiment.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and duplicate description will be omitted.

A dialogue device is a computer that performs an automatic dialogue with a user. A user is a person who uses a dialogue device. Automatic dialogue is the exchange of conversations between a user and a computer (this computer is also commonly referred to as a "bot"), in which the computer automatically speaks in response to the user's speech. An utterance is a single utterance made by a user or computer. In the following, the utterance of the user is also referred to as "user utterance", and the utterance of the computer is also referred to as "system utterance".

The purpose of using the dialogue device is not limited. For example, the dialogue device may be used in an FAQ (Frequently Asked Questions) system that answers user's questions, or may be used in a chat system that talks about anything, not limited to FAQ. Alternatively, the dialogue device may be incorporated into a virtual assistant function that performs any task based on voice operation.

The dialogue device may be a part of a client-server system or a single device. In the present embodiment, it is assumed that the dialogue device is a computer that functions as a server. FIG. 1 is a diagram showing an example of the functional configuration of the dialogue device 10 according to the embodiment. The dialogue device 10 can be connected to at least one user terminal 90 via a communication network. The configuration of the communication network is not limited in any way, and may be configured using at least one of, for example, the Internet and an intranet.

The user terminal 90 is a computer (client terminal) operated by the user. The user terminal 90 has a function of transmitting an utterance (user utterance) input by the user to the dialogue device 10 and a function of outputting an utterance (system utterance) received from the dialogue device 10. The type of the user terminal 90 is not limited, and may be, for example, a stationary computer or a device, or a portable computer or a device. Specific examples of the user terminal 90 include, but are not limited to, smartphones, tablet terminals, wearable terminals, personal computers, smart speakers, smart TVs, and smart home appliances.

The dialogue device 10 records in the log 40 the utterance text constituting the automatic dialogue executed with the user terminal 90. The utterance sentence is a sentence indicating the utterance of the user or the bot, and can be expressed by a character string. A log is a permanent record of the history of spoken text. The log 40 is realized by a logical file of any format and is stored in any storage (storage device). One of the features of the dialogue device 10 is a method of recording an uttered sentence in a log. The features will be described in particular detail below.

As shown in FIG. 1, the dialogue device 10 includes, as functional elements, a front function 20 that comprehensively controls automatic dialogue, and one or more bot functions 30 that output system utterances related to a specific topic. The front function 20 determines a bot function 30 for processing a user utterance received from the user terminal 90, and transfers the user utterance to the bot function 30. After that, the front function 20 transmits the system utterance output from the bot function 30 to the user terminal 90 as a response. Further, the front function 20 records the user utterance and the system utterance in the log 40. Each bot function 30 refers to a scenario that is a dialogue rule (a rule that defines what kind of system utterance is output when what kind of user utterance is received). When the bot function 30 receives a user utterance from the front function 20, the bot function 30 determines a system utterance corresponding to the user utterance based on the scenario, and outputs the determined system utterance to the front function 20.

In the present embodiment, the front function 20 includes an acquisition unit 21, a concealment unit 22, and a recording unit 23. The acquisition unit 21 is a functional element for acquiring an uttered sentence constituting an automatic dialogue executed with a user. The acquisition unit 21 acquires an utterance sentence indicating a user utterance or a system utterance. The concealment unit 22 is a functional element that executes a concealment process for concealing at least a part of confidential information on the utterance sentence in a state where the utterance sentence is not yet recorded in the log 40. Confidential information is information that should not be notified to a third party (at least a person different from the user). What kind of information should be confidential information may be arbitrarily determined. For example, confidential information may include at least a portion of personal information or may include at least a portion of confidential company information. Concealment is a process that makes it impossible or difficult for a third party to identify the original information. The recording unit 23 is a functional element that records an utterance sentence in which at least a part of confidential information is concealed in the log 40.

The operation of the dialogue device 10 will be described with reference to FIGS. 2 to 4. 2 and 3 are sequence diagrams showing an example of the operation of the dialogue device 10. FIG. 4 is a diagram showing some examples of the log 40. For ease of understanding, FIGS. 2 and 3 show the front function 20 and the bot function 30 of the dialogue device 10 individually, and briefly show one or more bot functions 30 in one block.

In step S11, the user terminal 90 transmits a request to start an automatic dialogue to the dialogue device 10. When the dialogue device 10 receives and processes this start request, the user can perform an automatic dialogue using the user terminal 90.

In this embodiment, the start request is a data signal including an utterance attribute. The utterance attribute is information indicating a property or characteristic related to the user's utterance, and can be used in automatic dialogue. In this embodiment, the utterance attribute is provided from the user terminal 90 to the dialogue device 10 in the form included in the start request or together with the user utterance. The specific content of the utterance attribute is not limited. In the present embodiment, the utterance attribute includes a user attribute indicating the property or characteristic of the user who intends to use the automatic dialogue, and a terminal attribute indicating the property or characteristic of the user terminal 90. The type and number of data items indicating user attributes are not limited in any way. For example, the user attribute may be one selected from the name, gender, age, and address, or may be a combination of two or more items arbitrarily selected from the four items. Alternatively, the user attribute may include one or more other data items different from the four items. The type and number of data items indicating terminal attributes are also not limited. For example, the terminal attribute may be one selected from the terminal name, the operating system name, and the operation mode, or may be a combination of two or more items arbitrarily selected from the three items. Alternatively, the terminal attribute may include one or more other data items different from the three items. In any case, in the dialogue device 10, the acquisition unit 21 receives the start request.

In step S12, the concealment unit 22 determines the concealment level based on the utterance attribute of the start request. The concealment level is an index indicating at least one of a method of concealing confidential information (concealment method) and a data item of confidential information to be concealed.

The concealment method may be the deletion of at least a part of the confidential information, in which case the concealment level is the deletion level. In the case of the deletion level, the hidden secret information is excluded from the character string to be recorded in the log 40, so that it is not recorded in the log 40 from the beginning.

Alternatively, the concealment method may be a process of replacing at least a part of the secret information with one or more conceptual words, and in this case, the concealment level is the replacement level. A conceptual word is a phrase that abstracts the original information. Therefore, in the case of the replacement level, the hidden confidential information is replaced with another more ambiguous word and recorded in the log 40. The conceptual word may be a phrase indicating the category of the original information, or may be a variable name corresponding to the original information. Alternatively, the conceptual word may be an ambiguous expression that does not give any clue to the original information. For example, if the surname "Tanaka" is concealed at the substitution level, the string "Tanaka" is the conceptual word "% userInfo.surname%", "surname", "name", or "% variable_1%". May be replaced with.

The replacement level may be set in multiple steps. This means that multiple types of abstraction levels (abstraction levels) of certain confidential information are prepared. Two types of substitution levels may be prepared, and three or more kinds of substitution levels may be prepared. In any case, the concealment level in this case is a first substitution level that replaces at least a part of the secret information with the first concept word, and at least a part of the secret information is more abstract than the first concept word. It may include a second substitution level that replaces with a lower second concept word.

The first substitution level and the second substitution level are prepared in advance, and an example of hiding the two surnames "Tanaka" and "Suzuki" with the two substitution levels is shown. For example, at the first substitution level, both the two character strings "Tanaka" and "Suzuki" may be replaced with the first conceptual word "% userInfo.surname%". On the other hand, at the second substitution level, the character string "Tanaka" is replaced with the second conceptual word "% userInfo.surname1%", and the character string "Suzuki" is replaced with the second conceptual word "% userInfo.surname2%". May be done. In this example, the first substitution level is a process of replacing two surnames in an indistinguishable manner, whereas the second substitution level is a process of replacing two surnames in a distinctive manner. Therefore, the second conceptual word has a lower degree of abstraction than the first conceptual word.

Only one concealment method may be prepared, or two or more concealment methods may be prepared. When multiple concealment methods are provided, the concealment level may be selectable from multiple replacement levels, may be selectable from a deletion level and one replacement level, or may be a deletion level. And a plurality of substitution levels may be selectable.

The type of confidential information to be hidden may be set arbitrarily. For example, the concealment level may be set so as to conceal only one type of confidential information, or the concealment level may be set so as to conceal two or more types of confidential information. Alternatively, the concealment level may be set to conceal only or all of the assumed confidential information. As a more specific example, the concealment level may be set to conceal one or more data items selected by name, age, gender, and location. In any case, the concealment level is set to conceal at least some confidential information.

The concealment level may indicate both the concealment method and the type of confidential information to be concealed, or may indicate only one of them. The hiding level may be set for each individual user or may be common to all users. Alternatively, the concealment level may be set for each individual utterance attribute, for example, for each age group of the user. The concealment level of the utterance sentence and the concealment level of the utterance attribute may be the same or different from each other. In any case, the concealment level can be flexibly set in various ways.

The dialogue device 10 stores information about the concealment level in advance so that the concealment unit 22 can determine the concealment level. The method of describing the concealment level to be stored is not limited. For example, the hiding level may be represented by any of the following methods: configuration file, database, mapping table, algorithm, formula, and threshold, or a combination of two or more arbitrarily selected from these methods. You may. In this way, the concealment level can be set by various methods. In any case, the concealment unit 22 determines one of one or more concealment levels prepared in advance based on the utterance attribute included in the start request.

In step S13, the concealment unit 22 executes a concealment process for the start request based on the determined concealment level. The concealment unit 22 conceals the secret information (for example, at least a part of the user attribute) specified by the concealment level among the character strings indicating the start request to be recorded in the log 40 by the specified concealment method. do. For example, if the determined concealment level is the deletion level, the concealment unit 22 deletes the designated secret information from the character string. If the determined concealment level is the replacement level, the concealment unit 22 replaces the specified secret information in the character string with a conceptual word.

The method of specifying the confidential information to be hidden from the character string to be processed is not limited. For example, the concealment unit 22 may identify the secret information using at least one method selected from character string matching, machine learning, anaphora resolution, and named entity linking. When processing the start request, the utterance attribute is described in the start request according to a predetermined rule, so that the concealment unit 22 identifies the secret information to be concealed by character string matching and conceals the secret information. It may be processed based on the level.

In step S14, the recording unit 23 records the concealed start request in the log 40. The confidential information to be concealed is not written to the log 40 from the beginning because it has already been concealed (for example, deleted or replaced) at this point.

In step S15, an automatic dialogue is executed between the user terminal 90 and the dialogue device 10 triggered by the start request. In step S15, the front function 20 executes a process for starting an automatic dialogue, and then the user utterance and the system utterance are transmitted between the user terminal 90 and the dialogue device 10. The user can acquire and send desired information in this automatic dialogue.

FIG. 3 shows an example of recording the utterance data (in other words, in step S15) in the log during the automatic dialogue. In step S151, the user terminal 90 transmits the user utterance data to the dialogue device 10. The user utterance data is data including an utterance sentence representing a user utterance and an utterance attribute.

The method of acquiring the user's utterance (utterance sentence) in the user terminal 90 is not limited. For example, the user terminal 90 may acquire voice-input user utterances (that is, user utterances represented by voice data), or user utterances input by character strings (that is, user utterances represented by text data). May be obtained. Alternatively, the user terminal 90 may automatically generate the user utterance in the form of voice data or text data based on the user's instruction. The utterance attributes may be the same as those contained in the start request, or may differ from at least a portion of those contained in the start request. In any case, the utterance attribute is the data associated with the user's utterance (spoken sentence). The user terminal 90 generates user utterance data including the acquired user utterance and utterance attribute, and transmits the user utterance data. In the dialogue device 10, the front function 20 receives the user utterance data.

In step S152, the front function 20 determines the bot function 30 for processing the user utterance data, and transfers the user utterance data to the corresponding bot function 30.

In step S153, the concealment unit 22 determines the concealment level based on the utterance attribute of the user utterance data. The concealment unit 22 determines the concealment level in the same manner as in step S12.

In step S154, the concealment unit 22 executes a concealment process for the user utterance data based on the determined concealment level. The concealment unit 22 executes the concealment process in the same manner as in step S13. The utterance text of the user's utterance can be freely described. Therefore, when identifying the secret information to be concealed from the spoken text, the concealment unit 22 uses at least one method selected from character string matching, machine learning, anaphora analysis, and named entity extraction (entity linking). The confidential information may be specified from the spoken text. On the other hand, since the utterance attribute is described in the user utterance data according to a predetermined rule, the concealment unit 22 may specify the secret information to be concealed in the utterance attribute by character string matching.

In step S155, the recording unit 23 records the concealed user utterance data in the log 40. Similar to step S14, the user utterance data is recorded in the log 40 in such a manner that the confidential information to be concealed does not appear as it is.

How the utterance data is recorded in the log 40 depends on the concealment level. The relationship between the concealment level and the log 40 will be described with reference to FIG. In the example of FIG. 4, the dialogue device 10 hides the place name when recording the user's utterance (utterance sentence) "Tell me the weather in Akasaka, Minato-ku and Yokosuka City" in the log 40, and also in the speech attribute (clinentData). Hide the user attribute (userInfo) of. In this example, "Akasaka, Minato-ku" is assumed to be the user's place of work, and "Yokosuka City" is assumed to be the user's place of residence. Further, the deletion level, the first replacement level, and the second replacement level (processing of replacing with a second concept word having a lower abstraction level than the first concept word) are exemplified as the concealment level of the spoken sentence. The example of FIG. 4 shows data described by applying AIML (Artificial Intelligence Markup Language), but the method and rules for describing utterance data are not limited in any way.

When the concealment unit 22 selects the deletion level as the concealment level, the concealment unit 22 deletes those two place names from the spoken text. Therefore, the recording unit 23 records the character string "Tell me the weather of and" in the log 40. In addition, the concealment unit 22 deletes the name "tanaka" and the age "28" that constitute the user attribute.

When the concealment unit 22 selects the first replacement level as the concealment level, the concealment unit 22 replaces the two place names with a common character string. For example, the concealment unit 22 uses the variable name “% userInfo.place%” corresponding to the place name as the first conceptual word, and replaces both “Akasaka, Minato-ku” and “Yokosuka City” with this variable name. In addition, the concealment unit 22 deletes the name "tanaka" and the age "28" that constitute the user attribute. As described above, the concealment level may differ between the utterance sentence and the utterance attribute.

When the concealment unit 22 selects the second replacement level as the concealment level, the concealment unit 22 replaces the two place names with different character strings. For example, the concealment unit 22 replaces "Akasaka, Minato-ku" with the variable name "% userInfo.workplace%" which is the second conceptual word corresponding to the place of work. Further, the concealment unit 22 replaces "Yokosuka City" with the variable name "% userInfo.home%" which is the second concept word corresponding to the place of residence. In addition, the concealment unit 22 deletes the name "tanaka" and the age "28" that constitute the user attribute.

In FIG. 4, the method of recording the spoken text in the log differs between the three examples. When the concealment level is the deletion level, the secret information to be concealed is completely deleted from the spoken text, so that no clue regarding the place name is recorded in the log 40. Therefore, even if a third party other than the user (for example, the administrator of the dialogue device 10) reads the log 40, it cannot be specified what weather the user has told. For example, the blank of "Tell me the weather of to" can be filled with times such as "today" and "tomorrow". On the other hand, when the concealment level is the first concealment level, the first conceptual word "% userInfo.place%" is described in the portion corresponding to the confidential information on the log 40. Therefore, it can be inferred that the user has heard the weather in some place, but the third party cannot know exactly which place it is. When the concealment level is the second concealment level, the second conceptual words "% userInfo.workplace%" and "% userInfo.home%" are described on the log 40. Therefore, the third party can infer that the user has heard the weather in two places and that the place is related to the place of work and the place of residence, but cannot know the specific place. Therefore, in the example of FIG. 4, the abstraction level of the spoken sentence recorded in the log 40 is the highest at the deletion level, the lowest at the second substitution level, and the deletion level at the first substitution level. It can be said that it is a level between the second substitution level and the second substitution level.

In FIG. 4, the method of recording the utterance attribute in the log is the same in the three examples. Of course, the concealment unit 22 may replace at least a part of the secret information in the utterance attribute with a conceptual word.

Returning to FIG. 3, in step S156, the bot function 30 responds to the user's utterance and outputs the system utterance data to the front function 20. The bot function 30 receives user utterance data from the front function 20 and refers to a scenario based on the user utterance and utterance attributes included in the data, and is presumed to be appropriate as a response to the user utterance. Determine the utterance. Then, the bot function 30 outputs the system utterance data including the determined system utterance to the front function 20. The system utterance data is data including utterance sentences representing system utterances. Similar to user utterances, the method of expressing system utterances is not limited, and for example, system utterances can be expressed by voice or text.

In step S157, the front function 20 transmits the system utterance data to the user terminal 90. The front function 20 may transmit the system utterance data after designating the output format of the system utterance (that is, after shaping the system utterance). The user terminal 90 receives and outputs the system utterance data, whereby the user can recognize the reply of the bot to the user utterance.

In step S158, the concealment unit 22 determines the concealment level of the system utterance. Similar to step S153, the concealment unit 22 may determine the concealment level based on the utterance attribute included in the user utterance data.

In step S159, the concealment unit 22 executes concealment processing for the system utterance data based on the determined concealment level. If the system utterance contains a variable, the concealment unit 22 may specify the secret information to be concealed based on the variable. For example, if the system utterance output to the user terminal 90 is "Akasaka, Minato-ku and Yokosuka City are fine", this system utterance is the variable "% userInfo.workplace%" corresponding to "Akasaka, Minato-ku". It may include the variable "% userInfo.home%" corresponding to "Yokosuka City". In this case, the concealment unit 22 can determine to conceal these two place names based on the variable. Alternatively, the concealment unit 22 may specify the secret information by the same process as in step S154.

In step S160, the recording unit 23 records the concealed system utterance data in the log 40. Similar to step S155, the system utterance data is recorded in the log 40 in such a manner that the confidential information to be concealed does not appear as it is.

After that, further utterance exchanges may be executed between the user terminal 90 and the dialogue device 10. Therefore, the processes of steps S151 to S160 can be repeatedly executed. FIG. 4 shows the same processing as steps S151 and S152 as steps S161 and S162. User utterance data is recorded in the log 40 according to step S161. Further, the system utterance data is generated in accordance with step S162 and transmitted to the user terminal 90, and the system utterance data is recorded in the log 40.

In this way, the utterance sentence and the utterance attribute are recorded in the log 40 for the first time after the confidential information to be concealed is surely concealed by the cooperation of the acquisition unit 21, the concealment unit 22, and the recording unit 23. This process is completely different from the process of deleting the confidential information once recorded on the log 40 later.

The dialogue device 10 may execute the concealment process for the utterance sentence without performing the concealment process for the utterance attribute. That is, concealment of speech attributes is not essential.

The block diagram used in the description of the above embodiment shows a block of functional units. These functional blocks (components) are realized by any combination of hardware and / or software. Further, the means for realizing each functional block is not particularly limited. That is, each functional block may be realized by one physically and / or logically coupled device, or directly and / or indirectly by two or more physically and / or logically separated devices. It may be connected specifically (eg, wired and / or wireless) and realized by these plurality of devices.

For example, the dialogue device 10 in one embodiment of the present invention may function as a computer for processing the present embodiment. FIG. 5 is a diagram showing an example of the hardware configuration of the computer 100 that functions as the dialogue device 10. The computer 100 may physically include a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

In the following description, the word "device" can be read as a circuit, a device, a unit, or the like. The hardware configuration of the dialogue device 10 may be configured to include one or more of the devices shown in the figure, or may be configured not to include some of the devices.

For each function in the interactive device 10, the processor 1001 performs an operation by loading predetermined software (program) on hardware such as the processor 1001 and the memory 1002, and the communication device 1004 communicates with the memory 1002 and the storage 1003. It is realized by controlling the reading and / or writing of data in.

Processor 1001 operates, for example, an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with a peripheral device, a control device, an arithmetic unit, a register, and the like. For example, at least a part of the functional elements of the dialogue device 10 may be realized by the processor 1001.

Further, the processor 1001 reads a program (program code), a software module and data from the storage 1003 and / or the communication device 1004 into the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operations described in the above-described embodiment is used. For example, at least a part of the functional elements of the dialogue device 10 may be stored in the memory 1002 and realized by a control program operating in the processor 1001, and other functional blocks may be realized in the same manner. Although it has been described that the various processes described above are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. Processor 1001 may be mounted on one or more chips. The program may be transmitted from the network via a telecommunication line.

The memory 1002 is a computer-readable recording medium, and is composed of at least one such as a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), and a RAM (Random Access Memory). May be done. The memory 1002 may be referred to as a register, a cache, a main memory (main storage device), or the like. The memory 1002 can store a program (program code), a software module, or the like that can be executed to implement the wireless communication method according to the embodiment of the present invention.

The storage 1003 is a computer-readable recording medium, and is, for example, an optical disk such as a CDROM (Compact Disc ROM), a hard disk drive, a flexible disk, a photomagnetic disk (for example, a compact disk, a digital versatile disk, or a Blu-ray (registration)). It may consist of at least one such as a (trademark) disk), a smart card, a flash memory (eg, a card, stick, key drive), a floppy (registered trademark) disk, a magnetic strip, and the like. The storage 1003 may be referred to as an auxiliary storage device. The storage medium described above may be, for example, a table, server or other suitable medium containing memory 1002 and / or storage 1003.

The communication device 1004 is hardware (transmission / reception device) for communicating between computers via a wired and / or wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, or the like. For example, at least a part of the functional elements of the dialogue device 10 may be realized by the communication device 1004.

The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives an input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).

Further, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be composed of a single bus or may be composed of different buses between the devices.

Further, the computer 100 includes hardware such as a microprocessor, a digital signal processor (DSP: Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). The hardware may implement some or all of each functional block. For example, the processor 1001 may be implemented on at least one of these hardware.

As described above, the dialogue device according to one aspect of the present invention includes an acquisition unit that acquires an utterance sentence constituting an automatic dialogue executed with a user, and a state in which the utterance sentence is not yet recorded in the log. The present invention includes a concealing unit that executes a concealment process for concealing at least a part of the confidential information on the uttered text, and a recording unit that records the uttered text in which at least a part of the confidential information is concealed in a log.

In such an aspect, since at least a part of the confidential information in the spoken text is not recorded in the log from the beginning, the security of the confidential information appearing in the dialogue can be ensured more reliably. In addition, since it is not necessary to perform a process of hiding at least a part of confidential information from the log once recorded, the hardware resource usage of the interactive device (for example, processor load and memory consumption) is not required. Amount) can be suppressed.

In the dialogue device according to the other aspect, the concealment unit may execute the concealment process based on at least one concealment level selected from a plurality of predetermined concealment levels. By preparing a plurality of concealment levels as options in this way, the concealment process can be flexibly executed as needed. In other words, the abstraction level of the spoken text recorded in the log can be changed as needed.

In a dialogue device according to another aspect, the plurality of concealment levels may include at least a deletion level indicating deletion of at least a part of confidential information and a replacement level of replacing at least a part of confidential information with a conceptual word. In this case, you can choose to completely erase the information you are trying to hide or replace it with another phrase.

In a dialogue device according to another aspect, a plurality of concealment levels have a first substitution level that replaces at least a part of confidential information with a first conceptual word, and at least a part of confidential information is more than the first conceptual word. It may include at least a second substitution level that replaces a second conceptual word with a low degree of abstraction. By preparing a plurality of types of replacement methods in this way, the abstraction level of the spoken text recorded in the log can be changed as needed.

In the dialogue device according to the other aspect, the acquisition unit further acquires the utterance attribute associated with the utterance sentence, the concealment unit further executes the concealment process for the utterance attribute, and the recording unit performs at least a part of the utterance attribute. The utterance attribute with hidden confidential information may be further logged. By executing the concealment processing not only for the utterance text but also for the utterance attribute, the security of the confidential information can be ensured more reliably.

Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in the present specification. This embodiment can be implemented as an amendment or modification without departing from the spirit and scope of the present invention as determined by the description of the scope of claims. Therefore, the description herein is for purposes of illustration only and has no limiting implications for this embodiment.

Notification of information is not limited to the embodiments and embodiments described herein, and may be performed by other methods. For example, information notification includes physical layer signaling (eg, DCI (Downlink Control Information), UCI (Uplink Control Information)), higher layer signaling (eg, RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, etc. It may be carried out by broadcast information (MIB (Master Information Block), SIB (System Information Block)), other signals, or a combination thereof. Further, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

Each aspect / embodiment described herein includes LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA. (Registered Trademarks), GSM (Registered Trademarks), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-Wideband), It may be applied to Bluetooth®, other systems that utilize suitable systems and / or next-generation systems that are extended based on them.

The processing procedures, sequences, flowcharts, and the like of each aspect / embodiment described in the present specification may be rearranged in order as long as there is no contradiction. For example, the methods described herein present elements of various steps in an exemplary order and are not limited to the particular order presented.

Information and the like can be output from the upper layer (or lower layer) to the lower layer (or upper layer). Input / output may be performed via a plurality of network nodes.

The input / output information and the like may be stored in a specific place (for example, a memory) or may be managed by a management table. Information to be input / output may be overwritten, updated, or added. The output information and the like may be deleted. The input information or the like may be transmitted to another device.

The determination may be made by a value represented by one bit (0 or 1), by a true / false value (Boolean: true or false), or by comparing numerical values (for example, a predetermined value). It may be done by comparison with the value).

Each aspect / embodiment described in the present specification may be used alone, in combination, or may be switched and used according to the execution. Further, the notification of predetermined information (for example, the notification of "being X") is not limited to the explicit one, but is performed implicitly (for example, the notification of the predetermined information is not performed). May be good.

Software, whether referred to as software, firmware, middleware, microcode, hardware description language, or other names, is an instruction, instruction set, code, code segment, program code, program, subprogram, software module. , Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, features, etc. should be broadly interpreted.

Further, software, instructions, and the like may be transmitted and received via a transmission medium. For example, the software uses wired technology such as coaxial cables, fiber optic cables, twisted pair and digital subscriber lines (DSL) and / or wireless technologies such as infrared, wireless and microwave to websites, servers, or other When transmitted from a remote source, these wired and / or wireless technologies are included within the definition of transmission medium.

The information, signals, etc. described herein may be represented using any of a variety of different techniques. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description are voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these. It may be represented by a combination of.

The terms described herein and / or the terms necessary for understanding the present specification may be replaced with terms having the same or similar meanings.

The terms "system" and "network" used herein are used interchangeably.

Further, the information, parameters, etc. described in the present specification may be represented by an absolute value, a relative value from a predetermined value, or another corresponding information. .. For example, the radio resource may be indexed.

The names used for the parameters mentioned above are not limited in any way. Further, mathematical formulas and the like using these parameters may differ from those expressly disclosed herein. Since the various channels (eg, PUCCH, PDCCH, etc.) and information elements (eg, TPC, etc.) can be identified by any suitable name, the various names assigned to these various channels and information elements are in any respect. However, it is not limited.

User terminals and mobile communication terminals may be used by those skilled in the art as subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals, etc. It may also be referred to as a mobile device, wireless device, remote device, handset, user agent, mobile client, client, or some other suitable term.

As used herein, the terms "determining" and "determining" may include a wide variety of actions. “Judgment” and “decision” are, for example, judgment, calculation, computing, processing, deriving, investigating, and looking up (for example, a table). , Searching in a table or another data structure), ascertaining can be regarded as "judgment" or "decision". Further, "judgment" and "decision" are receiving (for example, receiving information), transmitting (for example, transmitting information), input (input), output (output), and access. (Accessing) (for example, accessing data in memory) may be regarded as "judgment" or "decision". In addition, "judgment" and "decision" are considered to be "judgment" and "decision" when they are resolved, selected, selected, established, and compared. Can include. That is, "judgment" and "decision" may include considering some action as "judgment" and "decision".

The terms "connected", "coupled", or any variation thereof, mean any direct or indirect connection or connection between two or more elements and each other. It can include the presence of one or more intermediate elements between two "connected" or "joined" elements. The connection or connection between the elements may be physical, logical, or a combination thereof. As used herein, the two elements are by using one or more wires, cables and / or printed electrical connections, and, as some non-limiting and non-comprehensive examples, radio frequencies. By using electromagnetic energies such as electromagnetic energies with wavelengths in the region, microwave region and light (both visible and invisible) regions, they can be considered to be "connected" or "coupled" to each other.

The phrase "based on" as used herein does not mean "based on" unless otherwise stated. In other words, the statement "based on" means both "based only" and "at least based on".

As used herein by designations such as "first", "second", etc., any reference to that element does not generally limit the quantity or order of those elements. These designations can be used herein as a convenient way to distinguish between two or more elements. Thus, references to the first and second elements do not mean that only two elements can be adopted there, or that the first element must somehow precede the second element.

As long as "include", "including", and variations thereof are used herein or within the scope of the claims, these terms are similar to the term "comprising". In addition, it is intended to be inclusive. Moreover, the term "or" as used herein or in the claims is intended to be non-exclusive.

In the present specification, a plurality of devices shall be included unless the device has only one device apparently in context or technically.

10 ... Dialogue device, 20 ... Front function, 21 ... Acquisition unit, 22 ... Concealment unit, 23 ... Recording unit, 30 ... Bot function, 90 ... User terminal, 40 ... Log.

Claims (4)

An acquisition unit that acquires utterance sentences that make up an automatic dialogue performed with the user,
A concealment unit that executes a concealment process for concealing at least a part of confidential information on the utterance sentence in a state where the utterance sentence has not been recorded in the log yet.
It is provided with a recording unit for recording the utterance sentence in which the at least a part of the confidential information is concealed in the log .
The acquisition unit further acquires the utterance attribute associated with the utterance sentence, and the acquisition unit further acquires the utterance attribute.
The concealment unit further executes the concealment process for the utterance attribute.
The recording unit further records the utterance attribute in which at least a part of confidential information is hidden in the log.
Dialogue device. The concealment unit executes the concealment process based on at least one concealment level selected from a plurality of predetermined concealment levels.
The dialogue device according to claim 1. The plurality of concealment levels include at least a deletion level indicating the deletion of at least a part of the confidential information and a replacement level for replacing the at least a part of the secret information with a conceptual word.
The dialogue device according to claim 2. A first substitution level in which the plurality of concealment levels replaces at least a part of the secret information with a first concept word, and a second level in which the at least a part of the secret information is less abstract than the first concept word. Includes at least a second substitution level to replace with a conceptual word,
The dialogue device according to claim 2 or 3.

Images