Dialogue system, electronic device and method for controlling a dialogue system

Abstract

A dialog system is provided, the dialog system comprising a storage device configured to store relationship information; and an input processor configured to collect context information associated with the content of the message in response to receiving the content of the message including the utterance of the recipient and the input from the user. The dialog manager is configured to determine the relationship between the user and the recipient based on the relationship information, and generate a meaning representation for converting the context information into a sentence based on the relationship between the user and the recipient. Then, the result processor is configured to generate a message sent to the recipient based on the relationship between the user and the recipient, the content of the message, and the meaning representation.

Description

Technical Field

[0001] The present disclosure relates to a dialogue system, and an electronic device for conducting a dialogue with a user and a method for controlling the dialogue system. Background Art

[0002] The dialogue system recognizes the user's voice and provides a service corresponding to the recognized voice. One of the services provided by the dialogue system may be message transmission. When the user requests to send a message using voice, the dialogue system sends the message to the recipient according to the content of the user's voice. For example, if the situation or relationship between the user and the recipient is not considered when sending a message, an inappropriate message may be sent, or the message may not fully reflect the user's intention. Summary of the invention

[0003] The present disclosure provides a dialogue system, an electronic device, and a method for controlling the dialogue system, wherein the electronic device is used to send messages, wherein when a user requests to send a message, the user's intention fully reflects the emotional relationship between the user and the recipient, current context information, etc., as well as the social relationship between the user and the recipient.

[0004] According to one aspect of the present disclosure, a dialog system may include a storage device configured to store relationship information; an input processor configured to collect context information associated with the content of a message in response to receiving content including an utterance of a recipient and a message input from a user; a dialog manager configured to determine a relationship between a user and a recipient based on the relationship information, and generate a meaning representation for converting the context information into a sentence based on the relationship between the user and the recipient; and a result processor configured to generate a message sent to the recipient based on at least one or more of the relationship between the user and the recipient, the content of the message, and the meaning representation.

[0005] The relationship between the user and the recipient may include a social relationship and an emotional relationship. The storage device may be configured to store message features, wherein the features of the message sent by the user match the emotional relationship between the user and the recipient and the context. The dialogue manager may be configured to generate a meaning representation based on the message features. The features of the message may include at least one of a voice behavior and a voice intonation. The message features may be stored in a database.

[0006] The dialog manager may be configured to obtain an emotional state of the user and generate a meaning representation based on the relationship between the user and the recipient and the emotional state of the user. The storage device may be configured to store message characteristics, wherein the characteristics of the message sent by the user match the emotional relationship between the user and the recipient, the emotional state of the user, and the context, and the dialog manager is configured to generate the meaning representation based on the message characteristics. The relationship information may include at least one of the user's message history in social media, the user's call history, the user's contacts, and the user's writing history. The message characteristics may be stored in a database.

[0007] According to another aspect of the present disclosure, a method for controlling a dialogue system may include: receiving content including a recipient's utterance and a message from a user; collecting context information related to the content of the message; determining a relationship between the user and the recipient; generating a meaning representation for converting the context information into a sentence based on the relationship between the user and the recipient; and generating a message to be sent to the recipient based on the content of the message and the meaning representation.

[0008] Determining the relationship between the user and the recipient may include determining the social relationship and the emotional relationship based on relationship information including at least one of the user's message history, the user's call history, the user's contacts, and the user's writing history in social media. The method may also include matching the characteristics of the message sent by the user with the emotional relationship between the user and the recipient in context; and storing the characteristics of the message that matches the emotional relationship and the context.

[0009] Generating the meaning representation may include searching for message features that match the determined emotional relationship and the current context; and using the searched message features to generate the meaning representation. The method may also include obtaining the emotional state of the user. Generating the meaning representation may include generating the meaning representation for converting the context information into a sentence based on the relationship between the user and the recipient and the emotional state of the user.

[0010] The method may also include matching features of a message sent by a user with an emotional relationship between the user and the recipient, an emotional state of the user, and a context; and storing features of messages that match the emotional relationship and context. Generating a meaning representation may include searching for features of messages that match the determined emotional relationship, the emotional state of the user, and the current context; and generating a meaning representation using the features of the searched messages.

[0011] According to another aspect of the present disclosure, an electronic device may include: receiving content including an utterance of a recipient and a message from a user; collecting context information related to the content of the message; and determining a relationship between the user and the recipient. Furthermore, the electronic device may include: generating a meaning representation for converting the context information into a sentence based on the relationship between the user and the recipient; and generating a message sent to the recipient based on the content and the meaning representation of the message. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] These and / or other aspects of the present disclosure will become apparent and more readily understood from the following detailed description of embodiments in conjunction with the accompanying drawings, in which:

[0013] Figure 1 is a control block diagram illustrating a dialog system according to an exemplary embodiment of the present disclosure;

[0014] Figure 2 is a control block diagram illustrating components of an input processor of a dialog system according to an exemplary embodiment of the present disclosure;

[0015] Figure 3 is a control block diagram illustrating components of a dialog manager of a dialog system according to an exemplary embodiment of the present disclosure;

[0016] Figure 4 and Figure 5 is a view showing an example of features of a message stored in a storage device of a dialog system according to an exemplary embodiment of the present disclosure;

[0017] Figure 6 is a control block diagram illustrating components of a result processor of a dialog system according to an exemplary embodiment of the present disclosure;

[0018] Figure 7 is a diagram showing an example of a conversation conducted by a conversation system and a user according to an exemplary embodiment of the present disclosure;

[0019] Figure 8 is a diagram showing an example of a meaning representation generated by a meaning representation generator according to inputs such as a current location, traffic information, voice behavior, voice intonation, and estimated arrival time; and

[0020] Fig. 9 is a flowchart illustrating a method for controlling a dialog system according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention. As used herein, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms as well. It will also be understood that the terms "comprises" and / or "comprising" when used in this specification refer to the presence of the features, wholes, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, parts and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0022] It should be understood that the terms "vehicle" or "vehicular" or other similar terms used herein generally include motor vehicles, such as passenger cars including sport utility vehicles (SUVs), buses, trucks, various commercial vehicles; watercraft including various ships and vessels; aircraft, etc., and include hybrid vehicles, electric vehicles, combustion plug-in hybrid electric vehicles, hydrogen-powered vehicles, and other alternative fuel vehicles (e.g., fuels obtained from non-petroleum resources).

[0023] The exemplary embodiments disclosed in the specification and the configurations shown in the drawings are preferred examples of the disclosed invention. When submitting this application, there may be various modifications that can replace the exemplary embodiments and drawings of this specification. Moreover, the terms used herein are only for the purpose of describing specific embodiments and are not used to limit the disclosed invention. Unless there is a specific description to the contrary, singular expressions include plural expressions. As used herein, the terms "comprise", "include" or "have" are intended to indicate the presence of features, quantities, steps, operations, components, elements or combinations thereof described in the specification, without excluding any other features or quantities, steps, operations, components, parts or combinations thereof in advance.

[0024] In addition, terms such as "part", "unit", "block", "member", and "module" may refer to a unit for processing at least one function or operation. For example, these terms may refer to at least one hardware such as a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc., at least one program stored in a memory, or at least one process processed by a processor.

[0025] Although at least one exemplary embodiment is described as using multiple units to perform the exemplary process, it should be understood that the exemplary process can also be performed by one or more modules. In addition, it should be understood that the term controller / control unit refers to a hardware device including a memory and a processor. The memory is configured as a storage module, and the processor is specifically configured to perform one or more processes described further below.

[0026] The symbols attached to the steps are used to identify the steps. These symbols do not indicate the order between the steps. Unless the context clearly indicates a specific order, each step is performed in an order different from the order described.

[0027] At the same time, the disclosed exemplary embodiments can be implemented in the form of a recording medium for storing instructions that can be executed by a computer. The instructions can be stored in the form of program code, and when executed by a processor, a program module can be generated to perform the operation of the disclosed exemplary embodiments. The recording medium can be implemented as a non-transitory computer-readable recording medium. In addition, the control logic of the present invention can be implemented as a non-transitory computer-readable medium on a computer-readable medium containing executable program instructions executed by a processor, a controller / control unit, etc. Examples of computer-readable media include, but are not limited to, ROM, RAM, compact disc (CD) -ROM, magnetic tape, floppy disk, flash drive, smart card, and optical data storage device. The computer-readable recording medium can also be distributed in a networked computer system so that the computer-readable medium is stored and executed in a distributed manner, such as by a telematics server or a controller area network (CAN).

[0028] Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings.

[0029] The dialogue system according to an exemplary embodiment is a device configured to use the user's voice (i.e., speech or verbal communication) and non-voice input to recognize the user's intention and provide a service suitable for the user's intention. The dialogue system can also be configured to provide the service required by the user by determining the service by itself even without input from the user.

[0030] One of the services provided by the dialog system may be message transmission. Message transmission may include both text message transmission and voice message transmission, but in the exemplary embodiments described below, an example of text message transmission will be described in detail.

[0031] Figure 1 is a control block diagram showing a dialog system according to an exemplary embodiment of the present disclosure. Figure 1According to an exemplary embodiment, the dialogue system 100 may include a storage device 140 configured to store relationship information, the relationship information including at least one of a message history, a call history, a contact, and a writing history in a user's social media; and an input processor 110 configured to collect context information associated with the content of the message in response to receiving the content of the message including the utterance of the recipient and the input from the user. The dialogue manager 120 may be configured to determine the relationship between the user and the recipient based on the relationship information, and generate a meaning representation for converting the context information into a sentence based on the relationship between the user and the recipient, and the result processor 130 may be configured to generate a message sent to the recipient based on one or more of the relationship between the user and the recipient, the content of the message, and the meaning representation.

[0032] The storage device 140 may be configured to include at least one of non-volatile memories including flash memory, read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. In addition, the storage device 140 may be configured to include at least one of volatile memories including random access memory (RAM), static random access memory (S-RAM), dynamic random access memory (D-RAM), etc.

[0033] The input processor 110, the dialog manager 120, and the result processor 130 may be configured to include at least one memory configured to store a program including instructions for performing the above-mentioned operations and operations to be described later, and various types of data related to the operations; and at least one processor configured to execute the stored program. Therefore, any electronic device including at least one memory configured to store a program including instructions for performing the above-mentioned operations and operations to be described later; and at least one processor configured to execute the stored program may be included in the scope of the dialog system 100 according to the exemplary embodiment.

[0034] In addition, the input processor 110, the dialog manager 120, and the result processor 130 may be configured to share a memory or a processor. Otherwise, the input processor 110, the dialog manager 120, and the result processor 130 may be configured to use separate memories and separate processors, respectively. When the dialog system 100 includes multiple memories and multiple processors, they may be integrated on one chip, or may be physically separated from each other.

[0035] In addition, the input processor 110, the dialogue manager 120, the result processor 130, and the storage device 140 may be provided in a server of a service provider, or may be provided in a user terminal for providing a dialogue service, such as a vehicle, a home appliance, a smart phone, an artificial intelligence speaker, etc. In the former case, when a user's voice is input to a microphone provided in the user terminal, the user terminal converts the user's voice into a voice signal and transmits the voice signal to the server of the service provider.

[0036] In addition, some operations of the input processor 110, the dialog manager 120, and the result processor 130 may be performed at the user terminal, and some remaining operations may be performed on the server of the service provider based on the capacity of the memory and the processing power of the processor of the user terminal. In the following exemplary embodiments, the following case will be taken as an example: the user is a driver of a vehicle, and the user terminal is a vehicle or a mobile device, such as a smart phone connected to the vehicle.

[0037] Figure 2 is a control block diagram showing components of an input processor of a dialog system according to an exemplary embodiment. Figure 2 , the input processor 110 may be configured to include a voice input processor 111 configured to process voice input and a context information processor 112 configured to process context information. User voice input input via a microphone of the user terminal may be sent to the voice input processor 111, and context information obtained by a sensor of the user terminal or by communication with an external server may be sent to the context information processor 112.

[0038] The sound input processor 111 can be configured to include a speech recognizer configured to recognize the user's voice and output a text utterance corresponding to the user's voice; and a natural language understanding processor configured to determine the user's intention included in the utterance text by applying natural language understanding technology to the utterance. The speech recognizer can be configured to include a speech recognition engine, and the speech recognition engine can be configured to recognize the user's voice by applying a speech recognition algorithm and generate a recognition result. The utterance text as the recognition result can be input to the natural language understanding processor. The natural language understanding processor can be configured to determine the user's intention included in the utterance by applying natural language understanding technology.

[0039] First, the natural language understanding processor can be configured to perform morphological analysis on the utterance to convert the input string into a morpheme string. In addition, the natural language understanding processor can be configured to recognize entity names from the utterance. The entity name can be a proper noun (e.g., a person's name, a place name, an organization name, a time, a date, or a currency), and the entity name recognition can be configured to recognize the entity name in the sentence and determine the type of the recognized entity name. The natural language understanding processor can be configured to extract important keywords from the sentence using entity name recognition and recognize the meaning of the sentence.

[0040] The natural language understanding processor may be configured to extract a domain from an utterance. The domain may be used to identify the subject of the utterance. Domains indicating various subjects (e.g., messaging, navigation, schedule, weather, traffic, vehicle control) may be stored as a database in the storage device 140.

[0041] In addition, the natural language understanding processor can be configured to analyze the voice behavior contained in the utterance. Voice behavior analysis can include identifying the intent of the utterance, for example, whether the user is asking a question, whether the user is making a request, whether the user is responding, or whether the user is simply expressing emotion.

[0042] In addition, the natural language understanding processor can be configured to recognize the intention of speaking and extract the action corresponding to the speaking based on information (such as domain, entity name and voice behavior). The action can be defined by the object and the operator. The natural language understanding processor can be configured to extract factors related to the execution of the action. The factors related to the execution of the action can be valid factors directly required for the execution of the action, or can be invalid factors used to extract valid factors.

[0043] For example, when the speech recognizer outputs an utterance "Send a message to Gildong", the natural language understanding processor may be configured to determine "message" as the domain corresponding to the utterance, and to determine "send message" as the action corresponding to the utterance. The speech behavior may be a "request". [Gildong] as an entity name is [factor 1: recipient] related to the execution of the action. However, the actual message transmission also requires [factor 2: specific content of the message]. Specifically, the dialogue system 100 may be configured to output a system utterance, such as "Please tell me the content of the message you want to send", to obtain the specific content of the message from the user.

[0044] According to an exemplary embodiment, the dialogue system 100 may be configured to provide a service that fully reflects the user's intention by sending a message and context information based on the relationship between the user and the recipient, rather than simply sending the message content requested by the user as is. Therefore, the context information processor 112 may be configured to collect context information related to the content of the user's spoken message. For example, the context information related to the content of the user's spoken message may include traffic information, current location, arrival time, schedule, vehicle status, etc.

[0045] The storage device 140 may be configured to store data in the short-term memory 141 and the long-term memory 142, respectively, based on the importance or persistence of the date to be stored and the user's intention. The short-term memory 141 may be configured to store various sensor values ​​measured within a reference time period starting from the current time, the content of a conversation conducted within a reference time period starting from the current time point, information provided from an external server within a reference time period starting from the current time point, a schedule registered by the user, etc. The long-term memory 142 may be configured to store contacts, user preferences for specific topics, etc. In addition, information newly acquired by processing the data stored in the short-term memory 141 may be stored in the long-term memory 142.

[0046] Relationship information indicating a relationship between a user and another person, such as a message history, call history, and writing history of the user in social media, may be stored in the short-term memory 141 or may be stored in the long-term memory 142. For example, the message history, call history, and writing history in social media accumulated within a reference time period from the current time point may be stored in the short-term memory 141, and when the reference time period has passed, the stored history may be automatically deleted. Alternatively, the message history, call history, and writing history in social media may be stored in the long-term memory 142 regardless of the time point.

[0047] For example, when the content of the message determined by the voice input processor 111 indicates that the user is late for an appointment, the context information processor 112 may be configured to collect information such as the current location, traffic conditions, arrival time, vehicle status, etc. If the information is already stored in the short-term memory 141, the information may be obtained from the short-term memory 141, and if the information is not yet stored in the short-term memory 141, the information may be requested from an external server or a vehicle sensor.

[0048] As another example, when the message content determined by the voice input processor 111 is content for setting a new appointment, the context information processor 112 may be configured to collect information including the user's schedule, home address, recipient's home address, map information, points of interest (POI) near the user's preferred location, etc. If the information is already stored in the short-term memory 141, the information may be obtained from the short-term memory 141, and if the information is not yet stored in the short-term memory 141, the information may be requested from an external server.

[0049] The input processor 110 may be configured to send context information associated with the content of the message and results of natural language understanding (such as domains, actions, factors, etc.) to the dialog manager 120 .

[0050] Figure 3 is a control block diagram showing components of a dialog manager of a dialog system according to an exemplary embodiment of the present disclosure, and Figure 4 and Figure 5 is a view showing an example of features of a message stored in a storage device of a dialog system according to an exemplary embodiment of the present disclosure.

[0051] Reference Figure 3 , the dialogue manager 120 may be configured to include a dialogue flow manager 121 configured to manage the flow of a dialogue by generating, deleting, and updating dialogues or actions; a relationship analyzer 122 configured to analyze the relationship between a user and a recipient; and a meaning representation generator 123 configured to generate a meaning representation for converting context information into a sentence. The dialogue flow manager 121 may be configured to determine whether a dialogue task or an action task corresponding to an action sent from the input processor 110 has been generated. When a dialogue task or an action task corresponding to an action sent from the input processor 110 has been generated, the dialogue or action may be continued with reference to the dialogue or action performed in the task that has been generated. Alternatively, when a dialogue task or an action task corresponding to an action sent from the input processor 110 has not yet been generated, the dialogue flow manager 121 may be configured to regenerate the dialogue task or the action task.

[0052] The relationship analyzer 122 may be configured to analyze the relationship between the user and the recipient based on relationship information including at least one of message history, call history, contacts, and writing history in the user's social media stored in the storage device 140. The relationship between the user and the recipient may include a social relationship and an emotional relationship.

[0053] Social relationships may refer to relationships defined by occupation, kinship, education level, etc., such as friends, superiors, senior colleagues, junior colleagues, senior students, junior students, parents, grandparents, children, and relatives. Emotional relationships may refer to relationships defined by the degree of liking for or closeness to the other party. For example, when the recipient is "team leader", the social relationship may be "superior", and the emotional relationship may be "like & close", "dislike & close", "dislike & awkward", or "like & awkward".

[0054] The social relationship can be determined by the name of the recipient, or can be determined based on the contact. When the social relationship cannot be determined by the name or contact, the social relationship can be determined based on relationship information such as message history, call history, writing history, etc. in social media.

[0055] The emotional relationship may also be determined based on relationship information such as message history, call history, writing history, etc. in social media. For example, when the recipient is a "team leader" and her phone number is stored matching with "Witch Leader Kim", the emotional relationship with the recipient may be "dislike". In addition, whether the relationship between the user and the recipient is intimate or awkward may be determined by analyzing the message history or call history between the user and the recipient.

[0056] As another example, when the recipient is "Hong Gildong" and "Hong Gildong" is stored in the friend group of the contact, the recipient can be determined as a "friend" of the user. In addition, the system, device, processor, or component thereof can be configured to determine whether the relationship between the user and the recipient is close or awkward, like or dislike by analyzing the message history or call history between the user and the recipient. In addition, by analyzing the conversation history between the user and the recipient and the conversation history with other people, it can be determined whether the user and Hong Gildong are close or awkward, and whether the user's feelings towards Hong Gildong are like or dislike.

[0057] The meaning representation generator 123 may be configured to generate a meaning representation for converting context information into a sentence. The meaning representation in the dialogue processing may be the result of natural language understanding, or may be an input for natural language generation. For example, the input processor 110 may be configured to generate a meaning representation representing the user's intention by analyzing the user's utterance, and the dialogue manager 120 may be configured to generate a meaning representation corresponding to the next system utterance based on the dialogue flow and context. The result processor 130 may be configured to generate a sentence to be said by the system based on the meaning representation output from the dialogue manager 120.

[0058] The storage device 140 may be configured to match and store features of messages sent and received by the user for the corresponding context. This is called a message feature. The message feature may be stored in a database. The features of the message may include at least one of a conversation behavior and a tone. The tone may include whether a formal format or an informal manner is used; whether emoticons are used; whether characters or phrases representing formal or informal speech are used; whether formal language such as honorifics, Korean characters such as "○" which is a circular symbol, which can be used in Korean to represent a consonant of a vowel-initial syllable, or speaking in an intimate manner; whether onomatopoeia is used, etc.

[0059] For example, based on the user's conversation history, information may be stored as to whether the user used emoticons or onomatopeia when the user was late for an appointment and the user was stuck in traffic jam. Context refers to when a user sends or receives a message. Context may be determined by the content of the message, or may be determined by context information associated with the content of the message. In particular, the present disclosure is not limited to the above-mentioned intonation.

[0060] In addition, if Figure 4 As shown, the features of the message can be stored separately based on the user's emotional state and context. For example, even in the same context where the user is late for an appointment and is stuck in traffic, at least one different message feature can be stored based on whether the user's emotional state is angry, nervous, relaxed, sad, sorry, or pleasant.

[0061] As an example, in a situation where a traffic jam is indicated and the user is expected to arrive within 00 minutes, and the user's emotional state indicates that he / she feels sorry, the message format (including using a formal format without using emoticons, not using Korean characters such as "○" which is a circle symbol, and not using onomatopoeia) may match the user's context and emotional state.

[0062] The user's emotional state may be determined using an output value of a sensor measuring a user's biosignal, or may be determined by analyzing intonation, voice tone, content, etc. included in the user's speech. There is no limitation on how to determine the user's emotional state.

[0063] The meaning representation generator 123 may be configured to search for features of messages that match the current context and the current emotional state of the user, and use the features of the searched messages to generate a meaning representation for converting context information into a sentence. Figure 5 As shown, the features of the message can be stored separately based on the context and the emotional relationship between the user and the recipient. For example, in the context of a user being late for a date and being stuck in traffic, the tone of voice or whether to use emoticons can be stored differently based on the intimacy or liking between the user and the recipient.

[0064] As an example, in a situation where a traffic jam is indicated and the user is expected to arrive within 00 minutes, and the user's emotional state indicates that he / she feels sorry, the message format (including using a formal format without using emoticons, not using Korean characters such as "○" which is a circle symbol, and not using onomatopoeia) may match the user's context and emotional state.

[0065] The meaning representation generator 123 may be configured to search for features of messages that match the current context and the emotional relationship between the user and the recipient, and use the features of the searched messages to generate a meaning representation for converting context information into a sentence. In addition, the features of the message may also be stored after matching the context, the emotional relationship between the user and the recipient, and the emotional state of the user, respectively.

[0066] The characteristics of the message may be reflected in the sentence indicating the context information, and may also be reflected in the content of the message spoken by the user. For example, when the user speaks "send a message that I will be late", the characteristics of the above message may be reflected when a sentence including the meaning that the user will be late is generated. In addition, even when the user speaks "I will be late" in response to the system utterance inquiring about the content of the message, the dialogue system 100 may be configured to send a modified message reflecting the characteristics of the above message, rather than sending "I will be late" as it is.

[0067] At the same time, the output of the relationship analyzer 122 can also be considered as a meaning representation, so the meaning representation indicating the social relationship and emotional relationship between the user and the recipient, and the meaning representation which is the output of the meaning representation generator 123 and indicates the context information associated with the content of the message and the characteristics of the message can be sent to the result processor 130.

[0068] Figure 6 is a control block diagram showing components of a result processor of a dialog system according to an exemplary embodiment of the present disclosure. Figure 6 The result processor 130 can be configured to include a response generation manager 131, which is configured to manage the generation of a response required to perform an action input from the dialogue manager 120; a dialogue response generator 132, which is configured to generate a text response, an image response, or an audio response based on a request of the response generation manager 131; and a command generator 133, which is configured to generate a command for performing an action based on a request of the response generation manager 131.

[0069] When information related to an action is sent from the dialogue manager 120, for example, [action: send (operator)_message (object)], [action factor 1: recipient], [action factor 2: content of the message], and a meaning representation for converting the context information into a sentence, the dialogue response generator 132 can be configured to generate a message corresponding to the sent information, and the command generator 133 can be configured to generate a command for sending the message.

[0070] When the dialog response generator 132 generates a message, the dialog response generator 132 may refer to a response template, or the dialog response generator 132 may generate a message based on a rule stored in the storage device 140. In addition, the dialog response generator 132 may be configured to generate a dialog response to receive a confirmation from the user before sending the message. When the dialog response generator 132 generates a dialog response, the dialog response generator 132 may refer to a response template stored in the storage device 140, or the dialog response may be based on a rule.

[0071] Figure 7 is a view showing an example of a conversation conducted by a conversation system and a user according to an exemplary embodiment, and Figure 8 is a view showing an example of a meaning representation generated by a meaning representation generator.

[0072] Reference Figure 7 For example, when the user says "send message", the sound input processor 111 determines the utterance as [domain: message] and [action: send message] through the speech recognition engine and the natural language understanding processor. However, due to the lack of the recipient and the message content as necessary factors for performing the message transmission action, the dialogue response generator 132 can be configured to output a system utterance, for example, "Who would you like to send the message?" (or "To whom would you like to send the message?" or "Who would you like to send the message to?", etc.) in response to the user utterance to confirm the recipient. The system utterance can be sent to a suitable output device, such as a speaker S.

[0073] When the user speaks the name of the recipient, for example, “Gildong”, the relationship analyzer 122 may be configured to determine the social relationship and the emotional relationship between the user and Gildong based on the relationship information stored in the storage device 140 .

[0074] The dialogue response generator 132 can be configured to output the system utterance "Please tell me the content of the message" to obtain the content of the message. When the user says the message content "I may be late", the context information processor 112 can be configured to collect the current location, traffic conditions, arrival time, etc., which are context information associated with the content of the message. When the relationship analyzer 122 determines "friends" as the social relationship between the user and Gildong and determines "intimacy & likes" as the emotional relationship between the user and Gildong, and stores "using emoticons and using Korean characters "○" and informal ways of speaking" ("informal method" can be "informal way", etc.) as features of the message corresponding to the current context and emotional relationship, the meaning representation generator 123 can be configured to generate such as Figure 8 The meaning shown is indicated.

[0075] Reference Figure 8 , the meaning representation generated by the meaning representation generator 123 may be [Current location: near ○○], [Traffic information: congestion + minor car accident near xx intersection], [Voice behavior: provide information], [Estimated arrival time: within 20 minutes], [Voice intonation: use Korean character “○” and informal speaking style and use emoticons]. Please note that in Figure 8 "○○" indicates the current position, which is different from the above-mentioned Korean character "○" that can be used to indicate informal speech.

[0076] The dialog manager 120 may be configured to include [action: send message], [recipient: Gildong], [content of the message spoken by the user: I may be late], [social relationship: friend], [emotional relationship: intimacy & like], etc., and Figure 8 The meaning shown is sent to the result processor 130.

[0077] The dialogue response generator 131 of the result processor 130 can be configured to generate a message corresponding to the sent meaning expression based on a response template or rule. For example, the generated message can be "I am near ○○ now, and there is traffic congestion here due to a small car accident at the xx intersection. I may be late."

[0078] In addition, the dialogue response generator 132 may be configured to output "Do you want to send a message saying 'I am near ○○ now, and traffic is congested here due to a small car accident at the xx intersection. I may be late'?" as a system utterance to confirm whether to send the generated message. When the user says "Yes, I do" to confirm sending the generated message, the command generator 133 may be configured to generate a command to send the message "I am near ○○ now, and traffic is congested here due to a small car accident at the xx intersection. I may be late", and send the message based on the generated command.

[0079] Hereinafter, an exemplary embodiment of a method for controlling a dialogue system will be described below. When the method for controlling a dialogue system according to the exemplary embodiment is executed, the dialogue system 100 according to the above-described exemplary embodiment may be used. Therefore, even if not otherwise mentioned, the above reference to Figures 1 to 8 The description about the dialog system 100 described may also be applied to the method for controlling the dialog system. The method described below may be performed by a controller.

[0080] Fig. 9 is a flow chart showing a method for controlling a dialog system according to an exemplary embodiment of the present disclosure. Fig. 9 , a method for controlling a dialog system according to an exemplary embodiment may include: receiving a request for sending a message from a user (210); collecting context information related to the content of the message (211); determining a relationship between the user and a recipient (212); generating a meaning representation for converting the context information into a sentence (213); and generating a message to be sent to the recipient (214).

[0081] The user may input a speech requesting that a message be sent to a microphone provided in the user terminal. The speech requesting the message to be sent may include the recipient and the content of the message. The recipient and the content of the message may be sent at once, or may be sent step by step. The context information associated with the content of the message may include information such as the current location, traffic information, arrival time, vehicle condition, user's schedule, recipient's home address, map information, POI, etc. When such information has been obtained and stored in the short-term memory 141 or the long-term memory 142, the necessary information may be accessed from the short-term memory 141 or the long-term memory 142. Alternatively, when such information has not yet been obtained, the dialogue system 100 may be configured to request the necessary information from an external server, a vehicle sensor, etc.

[0082] The relationship between the user and the recipient may include a social relationship and an emotional relationship. The social relationship may be determined by the name used to refer to the recipient, or may be determined based on a contact. When the social relationship cannot be determined by the name or contact, the social relationship may be determined based on relationship information such as message history, call history, writing history, etc. in social media. The emotional relationship may also be determined based on relationship information such as contacts, message history, call history, writing history, etc. in social media.

[0083] Meanwhile, according to the method for controlling the dialogue system according to the exemplary embodiment, the features of the message sent or received by the user may be stored in the database for each context. The features of the message may be distinguished in the context and in the emotional relationship between the user and the recipient. Therefore, the method for controlling the dialogue system according to the exemplary embodiment may also include matching and storing the features of the message sent by the user for each emotional relationship between the user and the recipient and for each context.

[0084] The generation of the meaning representation (213) may include searching for features of the message that match the emotional relationship between the user and the recipient and the current context, and using the features of the searched message to generate a meaning representation for converting the context information into a sentence. In addition, when generating the meaning representation, the emotional state of the user may also be reflected. Therefore, the features of the message may be matched and stored for each emotional relationship between the user and the recipient, each emotional state of the user, and each context.

[0085] When the current emotional state of the user is obtained, the message features may be searched for features of the message that match the emotional relationship between the user and the recipient, the current context, and the current emotional state of the user determined in step 212, and the searched message features may be used to generate a meaning representation. The message features may be stored in a database.

[0086] According to the above-described dialogue system and control method thereof, advantages are achieved, namely, for example, when a user requests the dialogue system 100 to send a message, the message content spoken by the user and context information associated with the content of the message can be sent together. In addition, a natural message that fully reflects the user's intention can be sent based on the tone determined according to the social relationship and emotional relationship between the user and the recipient.

[0087] Although some exemplary embodiments of the present disclosure have been shown and described, it will be appreciated by those skilled in the art that changes may be made to these exemplary embodiments without departing from the principles and spirit of the present disclosure, the scope of which is defined in the claims and their equivalents.

[0088] The foregoing description has been directed to exemplary embodiments of the present disclosure. However, it will be apparent that other variations and modifications may be made to the described exemplary embodiments to obtain some or all of their advantages. Therefore, this description will be made by way of example only and does not otherwise limit the scope of the exemplary embodiments herein. Therefore, it is the intent of the appended claims to cover all such variations and modifications that fall within the true spirit and scope of the exemplary embodiments herein.

Claims

1. A dialogue system, comprising: A storage device configured to store relationship information between the user and the recipient; The input processor is configured as: receiving content including a recipient's utterance and a message input from said user, collecting context information associated with the content of the message, wherein the context information includes at least one of a traffic condition of a user, a current location of a user, an arrival time of a user, and a vehicle status of a user; a dialog manager configured to: determine a relationship between the user and the recipient based on the relationship information, and generate a meaning representation for converting the context information into a sentence based on the relationship between the user and the recipient, wherein the meaning representation is a result of natural language understanding or an input of natural language generation; as well as A result processor is configured to generate a message to be sent to the recipient based on: the relationship between the user and the recipient, the content of the message, and The meaning is expressed.

2. The dialogue system according to claim 1, wherein: The relationship between the user and the recipient includes a social relationship and an emotional relationship.

3. The dialogue system according to claim 2, wherein: The storage device is configured to: store message features of the message sent by the user, wherein the message features include at least one of voice behavior and voice intonation, and Wherein, the message characteristics match the following: the emotional relationship between the user and the recipient, and Context.

4. The dialogue system according to claim 3, wherein: The dialog manager is configured to generate the meaning representation based on the message characteristics.

5. The dialogue system according to claim 1, wherein: The dialog manager is configured to: determining an emotional state of the user, and The meaning representation is generated based on: the relationship between the user and the recipient, and The emotional state of the user.

6. The dialogue system according to claim 5, in, The storage device is configured to store a message feature of the message sent by the user, wherein the message feature includes at least one of a voice behavior and a voice intonation, wherein the message feature matches the following: the emotional relationship between the user and the recipient, the emotional state of the user, and context, and The dialog manager is configured to generate the meaning representation based on the message features.

7. The dialogue system according to claim 1, wherein: The relationship information includes at least one of a message history of the user in the user's social media, a call history of the user, contacts of the user, and a writing history of the user.

8. A method for controlling a dialog system, comprising the steps of: receiving, by a controller, content including an utterance of a recipient and a message from a user; collecting, by the controller, context information related to the content of the message, wherein the context information includes at least one of a traffic condition of a user, a current location of a user, an arrival time of a user, and a vehicle status of a user; determining, by the controller, a relationship between the user and the recipient; generating, by the controller, a meaning representation for converting the context information into a sentence based on a relationship between the user and the recipient, wherein the meaning representation is a result of natural language understanding or an input of natural language generation; as well as A message sent to the recipient is generated by the controller based on the relationship between the user and the recipient, the content of the message and the meaning representation.

9. The method according to claim 8, wherein: Determining the relationship between the user and the recipient includes: The controller determines the social relationship between the user and the recipient and the emotional relationship between the user and the recipient based on relationship information including at least one of the user's message history in social media, the user's call history, the user's contacts, and the user's writing history.

10. The method according to claim 9, further comprising: The controller matches a feature of the message sent by the user with the emotional relationship between the user and the recipient and the context, wherein the message feature includes at least one of a voice behavior and a voice intonation, and The features of the message that match the sentiment relationship and the context are stored by the controller.

11. The method according to claim 10, wherein: The generating the meaning representation comprises: The controller searches for the message feature that matches the determined emotional relationship and the current context; and The meaning representation is generated by the controller using the searched message features.

12. The method according to claim 8, further comprising the steps of: An emotional state of the user is determined by the controller.

13. The method according to claim 12, wherein: The generating the meaning representation comprises: The meaning representation for converting the context information into the sentence is generated by the controller based on: the relationship between the user and the recipient, and The emotional state of the user.

14. The method according to claim 13, further comprising: The controller matches the characteristics of the message sent by the user with the following: The emotional relationship between the user and the recipient, the emotional state of the user, and context, and The features of the message that match the sentiment relationship, the emotional state of the user, and the context are stored.

15. The method according to claim 14, wherein: The generating the meaning representation comprises: The controller searches for the characteristics of the message that match: the determined emotional relationship, the emotional state of the user, and the current context, and The meaning representation is generated using the features of the searched messages.

16. An electronic device, comprising: a memory configured to store program instructions; as well as A processor is configured to execute the program instructions, wherein the program instructions are configured to: receiving includes the receiver's utterance and the content of the message from the user; collecting context information related to the content of the message, wherein the context information includes at least one of a user's traffic conditions, a user's current location, a user's arrival time, and a user's vehicle status; determining a relationship between the user and the recipient; generating a meaning representation for converting the context information into a sentence based on the relationship between the user and the recipient, wherein the meaning representation is a result of natural language understanding or an input of natural language generation; as well as Based on the relationship between the user and the recipient, the content of the message and the meaning representation, a message is generated and sent to the recipient.

Images