KR102091441B1 - A collaborative personal assistant system for delegating providing of services supported by third party task providers and method therefor - Google Patents

Abstract

The present invention, in a server that performs service provision by third party providers, receives input from a first device and determines whether the input corresponds to a task executable by each of a plurality of second devices. Determine, and if the input corresponds to a task executable by each of the plurality of second devices, identify at least one pattern descriptor corresponding to the input among the plurality of pattern descriptors, wherein the plurality of pattern descriptors are serviced Includes natural language input patterns matching queries and the service queries, identifying at least one second device corresponding to the identified at least one pattern descriptor among the plurality of second devices, and identifying the A query request to at least one second device, and in response to the query request, the identified Even it receives from a second device a response including information about one or more actions of the at least one second device is associated with the task.

Description

A COLLABORATIVE PERSONAL ASSISTANT SYSTEM FOR DELEGATING PROVIDING OF SERVICES SUPPORTED BY THIRD PARTY TASK PROVIDERS AND METHOD THEREFOR}

The present invention relates to a cooperative personal assistant system (Agent Personal System) and a method according to the service provision of the third party task providers (third party task providers).

Generally, a virtual personal assistant (hereinafter referred to as 'PA') system understands a user's intention and learns user profile and context information. And performing tasks required by users by applying. The virtual PA system performs actions corresponding to the task by using natural language processing to respond to a user's query, making recommendations and acting on requests in an extended set of web services. do.

1 is a structural diagram of a typical virtual PA system.

Referring to FIG. 1, the virtual PA system includes a PA server (Server) 102, a network 104, a user device 106, and a third party task server 108. Here, the PA server 102, although not shown in the drawing, includes three technical components. The technical components include a conversational interface, a personal context awareness unit, and a service agency unit. The conversational interface is a dialogue-style natural language user interface that obtains natural language input from both a human speech or a text-type query typed by the user from the user. The PA server 102 recognizes personal contexts in advance. The personal contexts may include, for example, information about a place where the user is currently located, living or working. The PA server 102 acts as a user to provide services supported by the third party task server 108. Here, as an example, a case in which one third-party task server is shown is illustrated, but the PA server 102 may act to provide services supported by a plurality of third-party task servers. The provision of the services supported by the third party task server 108 may include, for example, small business / restaurants, local events and movie theaters, reservations at restaurants, etc. It corresponds to actions such as answering an answer.

A general virtual PA system 100 is composed of a PA application running on the PA server 102, a user device 106, and the third party server 108. The user device 106 is a personal digital assistant (PDA), an intelligent terminal that adds computer support functions such as Internet communication and information search to a mobile phone, for example, a smart phone (Samrt Phone), a tablet (tablet) ).

2 is a signal flow diagram of the operation of a typical virtual PA system.

Referring to FIG. 2, the virtual PA system includes a user device 200, a PA server 202, and an external third-party task server 204.

In step 206, the user device 200 receives a user input from the user. At this time, the user input may be input in the form of human speech (oral) or textual query. In addition, a mobile operating system (OS) or a PA application of the user device 200 will pre-process dormant speech dictated from text by applying speech to text technology.

In step 208, the PA application running on the user device 200 obtains a user request from the user input and transmits the user request to the PA server 202. The user request includes user queries and additional context information (eg, the location of the device), such as the location of the user device 200. At this time, the user query may be in the form of a textual query or a dictated query.

As an example, the following <Table 1> is a table showing the user request in the form of a message.

The user request received along with personal context information for identifying the domain to be analyzed is analyzed. At this time, artificial intelligence technologies such as 'ontology', 'inference' and 'pattern matching to support unified modeling, dictionaries and dialogue models' Use them.

Then, in step 214, the PA server 202 transmits an intermediate response to the user device 200 as a response of the PA application. The intermediate response is displayed to the user in the form of a text message or delivered in words. An example of this, intermediate response is "I'm looking for a Korean BBQ restaurant for your dinner today." Then, in step 216, the user device 200 displays the received intermediate response in the form of a message shown in Table 2 below.

Thereafter, the PA server 202 constructs a query to deliver the task requested by the user request to the external third-party task server 204, and in step 218, the configured query is external to the external server. 3rd party task server 204. Then, in step 220, the external third-party task server transmits a query response including the task corresponding to the query to the PA server 202. At this time, if there are a number of tasks provided by the external third-party task server 204 in response to the query, in step 224, the PA server 202 limits the items to be finally displayed to the user among the tasks. Priority is determined, a final response composed of selected items is determined based on the determined priority, and the final response is transmitted to the user device 200 in step 226. Then, in step 228, the user device 228 displays the final response on the screen of the user device 200.

The general virtual PA system as described above has inflexibility due to a limited number of third party providers to provide services to users. In addition, even if there are a number of actions or services that a third party provider can provide, the virtual PA system is unable to provide sets other than the set of actions or services requested by the user.

As an example, suppose a user requests a service provided by a music related site, a third party task server. At this time, the third-party server provides a variety of service sets, such as playing music using streaming, music download, or purchase service. However, a user using the virtual PA system can use only the services of the third party server that can be provided through the virtual PA system. For example, when the PA application provided by the virtual PA system supports an operation of performing a music play application on a user device or a library for playing music contents, the PA application is executed. The user cannot directly access (download or play) the contents.

If, among the actions provided by the third-party task server, temporary context information of a user is required. An example of the above actions may be a Euro service or a tarot point created based on the corresponding user information, a reservation service, etc., and the temporary context information includes location information or user profile information (phone number). The above-described virtual PA system was inconvenient to confirm whether the user can provide the temporary context information to the third-party task server to the user when temporary context information is requested.

The present invention proposes a cooperative PA system and method according to the service provision of third party task providers.

The present invention proposes an interface for a cooperative PA system to provide services provided by multiple third-party task servers.

The present invention provides additional services and actions that can be provided through a third party task server that provides tasks required by user input.

According to the present invention, the cooperative PA system delivers personal profiles required to perform a task corresponding to the user input of the user to the corresponding third party task server according to the user's permission.

An apparatus according to an exemplary embodiment of the present disclosure includes a server that provides services of third party providers, a server that provides services of third party providers, a transmitting and receiving unit; And a processor connected to the transceiver, the processor receiving an input from a first device, determining whether the input corresponds to a task executable by each of a plurality of second devices, and wherein the input is If it corresponds to a task executable by each of the plurality of second devices, identify at least one pattern descriptor corresponding to the input among the plurality of pattern descriptors, wherein the plurality of pattern descriptors are service queries and the service query And natural language input patterns matched to each other, identifying at least one second device corresponding to the identified at least one pattern descriptor among the plurality of second devices, and identifying the at least one second Sending a query request to a device, and in response to the query request, the identified at least one agent A response is received from two devices, including information about one or more actions of the at least one second device associated with the task.

A method according to an embodiment of the present disclosure, in a method of proxying service provision of third-party providers using a server, the process of receiving an input from a first device and the input by each of a plurality of second devices Determining whether the task corresponds to an executable task, and when the input corresponds to a task executable by each of the plurality of second devices, at least one pattern descriptor corresponding to the input among the plurality of pattern descriptors Identifying and the plurality of pattern descriptors includes service queries and natural language input patterns matching the service queries, corresponding to the identified at least one pattern descriptor of the plurality of second devices Identifying at least one second device, and requesting an inquiry to the identified at least one second device Transmitting, and in response to the query request, receiving a response including information on one or more actions of the at least one second device associated with the task from the identified at least one second device Includes.

In the present invention, a cooperative PA system that provides services of third party task providers includes a query in which the cooperative PA system provides a task required by the user input from a user input of a user and a query matching the task. By providing an interface for registering natural language input patterns to a third party task agency to help find commands, a third party task server that recognizes a user's user input more systematically and provides a task corresponding to the user input There is an effect that can be found more simply. In addition, the cooperative PA system provides additional services and actions that can be provided through a third-party task server that provides a task required by a user input regardless of a user's request, thereby providing a limited third-party task server. It is possible to overcome the limitations of non-linearity. Lastly, by obtaining the permission to use the user's personal profile information in advance and passing it to a third-party task server, when providing the task to the user, the process of requesting and obtaining the user's personal profile information is cumbersome. Loneliness is reduced.

1 is a structural diagram of a general virtual personal assistant system.
2 is a signal flow diagram for the operation of a typical virtual PA system.
3 is a block diagram of a cooperative PA system according to an embodiment of the present invention.
4A is a signal flow diagram of a cooperative PA system according to a first embodiment of the present invention.
4B is a diagram showing an example of a final response provided to a user according to the first embodiment of the present invention.
5A is an example of a signal flow diagram of a cooperative PA system according to a second embodiment of the present invention.
5B is a diagram showing an example of a screen of a user device on which a service proxy operation of a cooperative PA system according to a second embodiment of the present invention is displayed.
6A is an example of a signal flow diagram of a cooperative PA system according to a third embodiment of the present invention.
6B is a view showing an example of a screen of a user device on which a request for sharing a user profile is displayed according to a third embodiment of the present invention.
7 is an example of a signal flow diagram of a pre-processing procedure for user identification between a PA server and a third-party task server according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that in the following description, only parts necessary for understanding the operation according to the present invention are described, and descriptions of other parts will be omitted so as not to distract the subject matter of the present invention.

The present invention proposes a cooperative PA system and method according to the service provision of third party providers.

The cooperative PA system according to the first embodiment of the present invention provides an interface for proxying services provided by a plurality of third party task servers. The interface acts as a third-party task agent for natural language input patterns to help the collaborative PA system find a query command matching the task and a third-party task server that provides the task required by the user input from the user's user input. It is to register with the department. Accordingly, the cooperative PA system according to the present invention is formed to automatically generate a query for functions for performing the proxy operation of the third party task server through the interface.

The cooperative PA system according to the second embodiment of the present invention provides additional services and actions that can be provided through a third party task server that provides a task requested by a user input, regardless of a user request. Specifically, the cooperative PA system delivers an action service endpoint URL capable of receiving additional services other than the corresponding service through an additional action such as a user's touch or click on the user device. Accordingly, the cooperative PA system further includes a context inference unit capable of identifying an action indicated from a programming language such as play or download. The context inference unit stores content object meta data including natural language verb words that identify an action to be taken on the corresponding content object.

The cooperative PA system according to the third embodiment of the present invention provides a third-party task proxy for registering personal profiles required to perform a task corresponding to a user input of a corresponding user. The cooperative PA system obtains user permission to share personal profile information, such as the user's location or phone number, during the operation of retrieving results corresponding to the user input of the user. Then, the cooperative PA system transmits the personal profile information of the user to a third party task server that provides the task in order to process the task requested by the user.

3 is a block diagram of a cooperative PA system according to an embodiment of the present invention.

Referring to FIG. 3, the cooperative PA system 300 includes a PA server 310, a user device 320, a network 330 and a third party task server 340.

First, the PA server 310 includes a personal context database (DB: Data Base) 312, a chat robot 316, a task agency DB 317, and a natural language processor (NLP) 313 ), Contextual reasoned, task delegate agent 315. The user device 320 includes a personal assistant application and a mobile operating system (OS) 324. In addition, the third-party task server 340 includes a query processing unit 342 and an action processing unit 344. Here, the user device 320 and the third-party task server 340 are general user devices and third-party servers. Since it operates in the same way as the task server, its detailed description will be omitted here.

The context inference unit 314 analyzes the user input received together with the personal context information of the user in order to identify the domain of tasks that satisfy the user request. The context inference unit 314 performs pre-processing of user inputs dictated from text by applying a speech to text technique. The context inference unit 314 identifies a domain providing a task corresponding to the user input. Then, the task agent agent 315 performs a task embodied with the information extracted from the user input obtained using inference or conversation and the user's personal context. The task agency DB 317 stores registration information from a plurality of third-party task servers including the third-party task server 340 of FIG. 3, for example. The third-party task server 340 represents web service providers that supply application programming interfaces to supply domains that support specific services such as knowledge search engines, restaurant reservation / search, and the like.

Hereinafter, the operation according to the embodiments of the present invention will not be described by each of the detailed components constituting the PA server for convenience of description, but will be described as the operation of the PA server itself.

4A is a signal flow diagram of a cooperative PA system according to a first embodiment of the present invention. Here, user queries and corresponding tasks are provided through natural language input patterns registered in advance. Here, it is assumed that when a user input is requested through a PA application provided by the PA server 402, the third party task server 404 provides a task corresponding to the user input.

Referring to FIG. 4A, in step 406, the operator of the third-party task server 404 is a user input for queries provided by the third-party task server 404 for querying services provided by the third-party task server 404. The registration request of the pattern descriptor is transmitted to the PA server 402. The pattern descriptor for the query includes web service queries for proxy operation of the task agent agent (corresponding to 315 in FIG. 3) included in the PA server 402, and natural language input patterns mapped to the web service query. Includes. When the PA server matches one of the previously stored natural language input patterns with a user input, a third party supporting a task corresponding to a web service query mapped to the one input pattern and the natural language input pattern Perform the proxy operation of the task server. As an example, the pattern descriptors for the query are shown in <Table 3> and <Table 4> below. The pattern descriptor for the query includes a service category for the task and an end point uniform resource locator (URL) of a third-party task server to act.

Then, in step 408, the PA server 402 registers a descriptor for the query, and then transmits a registration response to the third-party task server 404.

In step 410, the user drives the PA application 400 on the user device to transmit the user input to the PA server 402. Here, the user input is transmitted in the form of words or text in the form of natural language. Then, in step 412, the PA server 402 checks whether the user input requests a proxy service of a third-party task server. As a result of the inspection, when the user input requests the agent service of the third-party task server, context inference is performed on the user input using a pattern descriptor based on the previously registered query. Specifically, when the PA server 402 matches a user input with one of the previously stored natural language input patterns, a task corresponding to a web service query mapped to the one input pattern and the input pattern is generated. Identifies the domain of the supported third-party task server. In step 414, the PA server 402, for example, transmits an interim response in the form of a message indicating that the user is searching for the identified domain through the PA application 400.

Thereafter, in step 416, the task agent agent of the PA server 402 configures the personal profile information for the user (eg, including query commands and parameters for requesting the user identifier) as a query request, and the third agent. Send to the party task server 404. Then, in step 418, the third-party task server 404 transmits a query response to the PA server 402. The query response includes an item object supporting a task requested by the user input and action sets allowed for each item object. For example, the query response is shown in the following <Table 5> to <Table 7>.

Then, in step 420, the PA server 402 transmits a final response to the user input through the PA application 400. The final response is shown as an example, as shown in FIG. 4B.

4B is an example of a final response provided to a user according to the first embodiment of the present invention.

Referring to FIG. 4B, 'what can I do for you?' Of reference number 430 represents an example of a query displayed on the user device by the PA application 400. 'Find cozy place for Korean BBQ' of reference numeral 435 corresponds to an example in which the user input 410 delivered to the PA server 402 in step 410 of FIG. 4A is shown in text form.

'Let me check the Korean ~' of reference number 440 represents an example of an intermediate response that the PA server 402 provides to the user through the PA application 400 in step 414 of FIG. 4A. Finally, reference numeral 445 denotes an example of a final response corresponding to step 420 of FIG. 4A. Specifically, two final responses to a user input requesting a place request for a Korean BBQ are displayed. In addition, action sets capable of performing additional actions for each of the two places, that is, call and reserve actions, are displayed together.

5A is an example of a signal flow diagram of a cooperative PA system according to a second embodiment of the present invention. Here, the PA server 502 provides the user with a set of additional services and actions that can be provided through a third-party task server that provides tasks requested by the user input. At this time, the PA server enables the user to perform the corresponding action by passing the service endpoint URL of the action that can receive additional services other than the corresponding service through an additional action such as a user's touch or click on the user device. In addition, the content object metadata stored in advance by the visitor inference unit includes natural language verb words. The words are for identifying an action that can be performed on the corresponding content object, and allow the PA server to interpret and identify the action in a programming language such as play, download, etc. through natural language context inference.

Referring to FIG. 5A, in operation 506, the user drives the PA application 500 on the user device to transmit the user input to the PA server 502. Here, the user input is transmitted in the form of words or text in the form of natural language. Then, in step 508, the PA server 502 checks whether the query requested by the corresponding user input requests the agent of the third-party task server. As a result of the check, if it corresponds to a query that requires the agent of the third-party task server, context inference on the user input is performed using the pattern descriptors for the query stored through the procedure described in FIG. 4A. Specifically, when the PA server 502 matches a user input with one of the previously stored natural language input patterns, a task corresponding to a web service query mapped to the one input pattern and the input pattern is generated. Identifies the domain of the supported third-party task server. Then, in step 510, the PA server 502, for example, transmits an interim response in the form of a message indicating that the user is searching for the identified domain through the PA application 500.

Thereafter, in step 512, the PA server 502 configures personal profile information for the user (eg, including query commands and parameters for requesting the user identifier) as a query request, and matches the query. It is delivered to the third party task server 504. At this time, the parameters are configured from the user input together with a personal context, a conversation context and an inferred context. At this time, the query request includes an example of the user's personal profile information, such as a user identifier, in order to identify the user and the action permission of the user subscribed to by the operator of the third-party task server. The third party task server 504 receiving the query request transmits a query response corresponding to the query request to the PA server 502 in step 514. Specifically, the third-party task server 504 supports' whether the user has subscribed to his server 'and' when the user is subscribed, the performance of the user device supports an object corresponding to the user input. If yes, the third party task server 504 then includes the list of actions allowed by the user's subscription in the query response. And, after the allowed actions are performed, further actions that the user can perform may be further included. An example of the additional actions includes an action to play music with natural language text that can be presented to the user through the PA server 502. As a specific example, assume that the user is not subscribed to a third party task provider, a music play site. In this case, the third-party task provider sends a list of actions, such as 'free listening for one minute' or 'subscribe' actions, which may be provided to the user to the PA server. And, if the user is subscribed to the 'Streaming Play' service but not the 'Download Service', the third-party task server transmits only the 'Play' action to the PA server. However, if the user is subscribed to both 'streaming play' and 'download service', the third party task server sends both the 'streaming play' and 'download service' actions to the PA server.

In step 514, the PA server 502 receives a query response from the third-party task server 504, and stores language keywords of actions provided by the query response in a personal context DB. The storing operation is to help understand a user input to be input later including the stored keyword.

In step 516, the PA server 502 determines the priority of items included in the query response and supports the corresponding task, and sends a final response composed of the determined items to the user through the PA application 500. To deliver. Then, in step 518, the PA application 500 may display the items obtained through the final response and actions allowed to the user for each item. Then, in step 520, the user inputs a second user input to select one of the displayed actions through the PA application 500. At this time, the input method corresponds to touch or click or speaking. In step 522, the PA server 502, which has received the second user input, interprets the second user input as 'music play' as an example using the stored personal context information. Then, in step 524, a response is transmitted to the user through the PA application 500. The response includes, for example, an action object requested by the corresponding user and a content object identifier such as a URL corresponding to the interpreted second user input.

Thereafter, in step 526, the PA application 500 is an example identified by the endpoint URL obtained through the response, for example, a music play library or music play application on a user device that can access the third-party task server 504. Run Then, in step 528a for further action, the PA application 500 transmits an action request including the user ID and the object ID to the third-party task server 504. Then, in step 528b, the third-party task server 504 provides a streaming service to the user as an example of a corresponding service corresponding to the object identifier through the PA application 500.

5B is a diagram illustrating an example of a screen of a user device on which a service proxy operation of the cooperative PA system according to the second embodiment of the present invention is displayed.

5B, reference numeral 501 is a start screen of the PA application 500. That is, the PA application 500 displays "what can I help you with?" As an example of a query sentence for requesting user input.

As an example of the response of the query, 'what is lonely?' Corresponds to step 506 of FIG. 5A, that is, the first user input. Here, a case of inputting the response of the query as a sentence is illustrated as an example. The response may be input to the user device in the form of speaking as mentioned above.

Next, the description ("Lonely is a music ~ You can play or download the song.") Provided in response to the response of the query in FIG. 5B is obtained as a result of context inference in step 508 of FIG. 5A, step 510. Corresponds to the middle answer.

Reference numeral 515 corresponds to the final response in step 516 of FIG. 5A. Here, as an example of the query response, while providing a sound source service such as a sound source title and a play time, an example of actions allowed to the user is provided with play and download.

In this case, suppose that the user selects 'play' as an example of a specific action through the second user input in step 520 of FIG. 5A. Then, the PA server 500 displays 'Could you play the song?' As a sentence in response to the selection of the action on the user device as a sentence. The response corresponds to step 524 of FIG. 5A. In addition, the PA application 500 provides the corresponding music with a message in the form of a sentence ("OK I will play the song 'lonely'") that provides music play to the user, for example, step 526 of FIG. 5A. Corresponds to

6A is an example of a signal flow diagram of a cooperative PA system according to a third embodiment of the present invention. In the cooperative PA system according to the third embodiment of the present invention, a third party task server that provides a task corresponding to a user's request and an object supporting it, registers a proxy service for registering personal profiles required to provide the object. to provide. That is, while the PA server retrieves the result according to the user input, the user permission is obtained to share user profile information (eg, location, phone number, etc.), and the user profile information is transmitted to the corresponding third-party task server. By delivering, it processes the action requested by the user.

 Referring to FIG. 6A, in operation 606, the user drives the PA application 600 on the user device to transmit the user input to the PA server 602. Here, the user input is transmitted in the form of words or text in the form of natural language. Then, in step 608, the PA server 602 checks whether the query requested by the corresponding user input requests the agent of the third-party task server.

As a result of the check, if it corresponds to a query that requires the agent of the third-party task server, context inference on the user input is performed using the pattern descriptors for the query stored through the procedure described in FIG. 4A. Specifically, when the PA server 602 matches one of the previously stored natural language input patterns with a user input, a task corresponding to the web service query mapped to the one input pattern and the input pattern is generated. Identifies the domain of the supported third-party task server. Then, in step 610, the PA server 602, for example, transmits an interim response in the form of a message indicating that the user is searching for the identified domain through the PA application 600.

Thereafter, in step 612, the PA server 602 configures query commands and parameters for requesting the user identifier as an example of personal information for the user as a query request, and the third party task server matching the query ( 604). The parameters are constructed from the user input along with the personal context, conversation context and inferred context. In this case, the query request includes a user identifier as an example of the personal information of the user in order to identify a user allowed by the third party provider and an action to which the user subscribes. The third party task server 604 receiving the query request transmits a query response corresponding to the query request to the PA server 602 in step 614. Specifically, the third party task server 604 includes an action descriptor including personal profile information required by the query request.

The action descriptor is shown in Table 8 below.

In step 616, the PA server 602 transmits data corresponding to the results of the query to the PA application 600 as a final response along with the user's allow request. Then, in step 618, the PA application 600 displays the content objects included in the final response to the user through the screen of the user device.

6B is a diagram illustrating an example of a screen of a user device on which a request for sharing user profile information of a user is displayed according to a third embodiment of the present invention.

Referring to FIG. 6B, as an example, an intermediate response is displayed, that is, "Let me check the Korean BBQ restaurant which is cozy you're your location". The intermediate response corresponds to step 610 of FIG. 6A.

In addition, the PA server 602 displays a final response including user-selectable actions, such as restaurant information, for example, name, street, and phone number, searched for with the intermediate response through a user device. The final response of the above type corresponds to step 618 of FIG. 6A. In addition, as an example, suppose that the user selects 'reserved' when the selectable actions include a call and a reservation.

 At this time, the PA server 602 transmits a request for the use of the personal information of the user together with a call and a reservation for the user's selectable actions.

If, in step 620, the user through the PA application 600, it is assumed that the user has passed the 'allow' for the request to the PA server 602 as a second user input. Then, the PA server 602 transmits a response to the reception of the second user input through the PA application 600. Then, in step 624, the PA server 602 requests the action including the action requested by the user and personal profile information such as phone number or location information as an example required for the third party task server 604. To pass. As mentioned above, since the user has selected 'reservation' as the action, the requested personal profile information may include a user phone number or location information. Then, in steps 626a and b, the third-party task server 604 transmits a user response corresponding to the action to the PA application 600 through the PA server 602.

7 is an example of a signal flow diagram of a preprocessing procedure for user identification between a PA server and a third party task server according to an embodiment of the present invention. Here, a pre-processing procedure for associating user information managed by each of the PA server and the third-party task server should be accompanied in order for the PA server to recognize the user's permission for the task and content object requested by the user. A typical third-party task server manages the identifiers of users who subscribe to it. In the second to third embodiments of the present invention, the pre-processing operation is required.

The pre-processing operation is performed while any user subscribes to any third party task server. For example, if a third-party task server shows a list of PA servers to the user during the subscription procedure, the user selects one PA server from the list. At this time, the third-party task server requests the user to identify the PA server. Through this, during the sign-up process, the third-party server can acquire the identifier of the PA server to which the user is associated.

Referring to FIG. 7, in step 706, the user performs a subscription procedure to the third-party task server 704 through the PA application 700 running on the user device. Here, the case where the third party task server 704 is one has been described as an example, but a pre-processing procedure for user identification must be accompanied for each of the third party task servers that provide a service that the PA server 702 intends to act on. something to do.

When the sign-up process is completed, in step 708, the third-party task server 704 delivers the user information of the users who subscribe to the third-party task to the PA server 702. For example, the user information managed by the third-party task server 704 is shown in Table 9 below.

Meanwhile, the PA server 702 and the user information it manages may be represented as <Table 10> below.

The cooperative PA system as described above acts as a service operation of a third-party task server that provides tasks and objects corresponding to user input, so that the user directly accesses the third-party task server to obtain the tasks and objects. It has the effect of reducing unnecessary procedures and resolving existing problems compared to operation.

On the other hand, in the detailed description of the present invention, although specific embodiments have been described, various modifications are possible without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined not only by the scope of the claims to be described later, but also by the scope and equivalents of the claims.

Claims (8)

In the server acting as a service provider of third party providers,
Transceiver; And
It includes a processor connected to the transceiver,
The processor,
Receiving an input from a first device,
Determine whether the input corresponds to a task executable by each of a plurality of second devices,
If the input corresponds to a task executable by each of the plurality of second devices, identify at least one pattern descriptor corresponding to the input among the plurality of pattern descriptors, wherein the plurality of pattern descriptors include service queries and Contains natural language input patterns matching the service queries.
Identify at least one second device corresponding to the identified at least one pattern descriptor among the plurality of second devices,
Sending a query request to the identified at least one second device,
In response to the query request, a server that receives a response from the identified at least one second device that includes information about one or more actions of the at least one second device associated with the task. According to claim 1,
The processor,
A server that transmits to the first device an intermediate response indicating that the task is being identified in response to the input. According to claim 1,
The response is:
A server further comprising information on items supporting the task and additional actions related to the task. According to claim 3,
The processor,
If the user's personal information for the additional action is required, transmit a request to accept the use of the user's personal information to the first device,
A server that transmits the user's personal information to the identified at least one second device when receiving acceptance of the use of the personal information from the first device. In the method of using the server to provide services of third party providers,
Receiving an input from a first device,
Determining whether the input corresponds to a task executable by each of the plurality of second devices;
Identifying at least one pattern descriptor corresponding to the input among the plurality of pattern descriptors when the input corresponds to a task executable by each of the plurality of second devices, and wherein the plurality of pattern descriptors are service queries And natural language input patterns matching the service queries.
Identifying at least one second device corresponding to the identified at least one pattern descriptor among the plurality of second devices;
Transmitting a query request to the identified at least one second device;
And in response to the query request, receiving a response from the identified at least one second device that includes information about one or more actions of the at least one second device associated with the task. The method of claim 5,
And in response to the input, sending an intermediate response indicating that the task is being identified to the first device. The method of claim 5,
The response is:
The method further includes information on items supporting the task and additional actions related to the task. The method of claim 7,
If the user's personal information for the additional action is required, transmitting a request for acceptance of the use of the user's personal information to the first device,
And receiving an acceptance for use of the personal information from the first device, transmitting the personal information of the user to the identified at least one second device.

Images