CN106888161B - Social method executed in social agent terminal, terminal and medium - Google Patents

Social method executed in social agent terminal, terminal and medium Download PDF

Info

Publication number
CN106888161B
CN106888161B CN201710250499.5A CN201710250499A CN106888161B CN 106888161 B CN106888161 B CN 106888161B CN 201710250499 A CN201710250499 A CN 201710250499A CN 106888161 B CN106888161 B CN 106888161B
Authority
CN
China
Prior art keywords
user
terminal
message
voice
social
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710250499.5A
Other languages
Chinese (zh)
Other versions
CN106888161A (en
Inventor
刘锐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Netease Hangzhou Network Co Ltd
Original Assignee
Netease Hangzhou Network Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Netease Hangzhou Network Co Ltd filed Critical Netease Hangzhou Network Co Ltd
Priority to CN201710250499.5A priority Critical patent/CN106888161B/en
Publication of CN106888161A publication Critical patent/CN106888161A/en
Application granted granted Critical
Publication of CN106888161B publication Critical patent/CN106888161B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/52User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services

Abstract

In an embodiment of the present invention, a social method executed in a social agent terminal is provided: receiving an interactive request sent by a first user through a first terminal; determining whether the first user is allowed to interact with a second user by adopting a preset rule; wherein the first user is associated with the first terminal and the second user is associated with the social proxy terminal; in the scheme, after the interaction request is received, the social agent terminal can judge whether the first user and the second user are allowed to interact, so that the social function of the user is realized through the social agent function of the social agent terminal, and the social efficiency and the social experience are improved.

Description

Social method executed in social agent terminal, terminal and medium
Technical Field
The embodiment of the invention relates to the field of intelligent terminals, in particular to a social method, a terminal and a medium executed in a social agent terminal.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
With the continuous progress of the intelligent terminal technology and the continuous pursuit of the quality of life, the intelligent terminal serving as one of the applications of the Internet of things has a wide market application prospect.
Singing and listening to songs are common entertainment modes in daily life, so that the intelligent sound box can be used for carrying. The intelligent sound box is mainly connected to an external network through a wireless router, so that playing is more free, and the specific principle is as follows: firstly, the link of the multimedia resource is transmitted to the intelligent sound box through an intelligent transmission protocol, the intelligent sound box downloads the multimedia resource, and the downloaded multimedia resource is directly decoded and played on the intelligent sound box.
With the continuous increase of the demand, in many cases, a user needs to perform social interaction with other users, and chinese patent CN104065718A discloses a method and a system for realizing social sharing of an intelligent sound box, where the method includes: the intelligent sound box receives a social operation instruction of a user, identifies social operation and sends corresponding social parameters to the social network server; and interacting with the social network server through the social account password, and carrying out sharing operation according to the social sharing mode of the social operation. Patent CN104065718A mainly solves the sharing operation problem, relies on social network services, and does not solve the social problem itself.
The invention mainly solves the problem of how to realize social agent and social interaction among users by means of intelligent equipment.
Disclosure of Invention
In the prior art, content can be shared through a smart speaker, but social interaction cannot be performed through a smart device (e.g., smart speaker), which is a very annoying process.
For this reason, there is a high necessity for an improved social method performed in a social proxy terminal by which social interaction between users is achieved.
In this context, embodiments of the present invention are intended to provide a new social approach.
In a first aspect of embodiments of the present invention, there is provided a social method performed in a social proxy terminal, including:
receiving an interactive request sent by a first user through a first terminal;
determining whether the first user is allowed to interact with a second user by adopting a preset rule;
wherein the first user is associated with the first terminal and the second user is associated with the social proxy terminal.
In one embodiment, the method according to the above embodiment of the present invention further comprises:
when the first user is allowed to interact with the second user, receiving part or all of interactive contents sent by the first terminal; and/or the presence of a gas in the gas,
when determining that the first user is not allowed to interact with the second user, refusing to receive the interactive content sent by the first terminal, or ignoring the interactive content sent by the first terminal; and/or the presence of a gas in the gas,
and when the first user is determined to be allowed to interact with the second user, sending a first type voice message to the second user.
In some embodiments, the method according to any of the above embodiments of the invention, further comprising:
and receiving a second type voice message of the second user, and forwarding the second type voice message to the first user.
In some embodiments, the method according to any of the above embodiments of the invention, further comprising:
receiving a second type of voice message of the second user;
obtaining a third type message according to the second type voice message;
and replying a third type message to the first user.
In some embodiments, the method according to any one of the above embodiments of the present invention, obtaining a third type of message from the second type of voice message, includes:
obtaining a third type message according to the corresponding relation between the preset third type message and the recognition result of the second type voice message; alternatively, the first and second electrodes may be,
and obtaining the third type message according to the second type voice message and a first preset machine learning model.
In some embodiments, the method according to any of the above embodiments of the present invention, wherein the third type of message is a third type of voice message, and the third type of voice message shares voice parameters associated with the social proxy terminal or the second user with the first type of voice message.
In some embodiments, the method according to any of the above embodiments of the present invention, determining whether to allow the first user to interact with the second user using a preset rule includes:
sending a voice inquiry message to the second user, wherein the voice inquiry message is used for inquiring whether the second user allows interaction with the first terminal;
and receiving a voice response message corresponding to the voice inquiry message, and determining whether to allow the interaction with the second user according to the voice response message.
In some embodiments, the method according to any of the above embodiments of the present invention, determining whether to allow the first user to interact with the second user using a preset rule, includes:
judging whether the first user is matched with the second user or not by adopting a preset rule according to the request type and/or the related parameters of the first user carried in the interactive request;
and determining whether the first user is allowed to interact with the second user according to the judgment result.
In some embodiments, according to the method of any one of the above embodiments of the present invention, the preset rule is a rule satisfying a conditional expression and/or a logical tree expression.
In some embodiments, the method according to any of the above embodiments of the present invention, wherein issuing a first type of voice message to the second user comprises:
obtaining the first type voice message by using a preset configuration relation or a second preset machine learning model according to the interactive request or the interactive content sent by the first terminal;
and sending the first type voice message to the second user;
and the second preset machine learning model is generated according to the interactive corpus materials of the second user and the social agent terminal or other users.
In some embodiments, according to the method of any one of the above embodiments of the present invention, the social agent terminal is a smart speaker.
In some embodiments, the method according to any of the above embodiments of the present invention, receiving an interaction request sent by a first user through a first terminal, includes:
and receiving an interaction request forwarded by a first social platform server where the social agent terminal is located, wherein the interaction request forwarded by the first social platform server is sent to the first social platform server by a second social platform server where the first terminal is located.
In some embodiments, according to the method of any one of the foregoing embodiments of the present invention, the interaction request is directly sent by the first terminal when the first terminal determines that the preset object meets a certain condition, or the interaction request is sent by sending an inquiry message to the first user when the first terminal determines that the preset object meets a certain condition, and sending the inquiry message according to the inquiry message.
In some embodiments, according to the method of any one of the above embodiments of the present invention, the preset object is a preset object other than the first user and the second user.
In a second aspect of the embodiments of the present invention, there is provided a social proxy terminal, including:
the receiving unit is used for receiving an interactive request sent by a first user through a first terminal;
the judging unit is used for determining whether the first user and the second user are allowed to interact or not by adopting a preset rule;
wherein the first user is associated with the first terminal and the second user is associated with the social proxy terminal.
In one embodiment, according to the terminal of the above embodiment of the present invention, the apparatus further includes a rejecting unit and a sending unit, wherein:
the receiving unit is configured to receive a part of or all of the interactive content sent by the first terminal when the determining unit determines that the first user is allowed to interact with the second user; and/or the presence of a gas in the gas,
the rejecting unit is configured to reject to receive the interactive content sent by the first terminal or ignore the interactive content sent by the first terminal when the determining unit determines that the first user is not allowed to interact with the second user; and/or the presence of a gas in the gas,
the sending unit is configured to send a first type voice message to the second user when the determining unit determines that the first user is allowed to interact with the second user.
In some embodiments, according to the terminal of any previous embodiment of the present invention, the receiving unit is further configured to receive a second type voice message of the second user;
the sending unit is further configured to forward the second type of voice message to the first user.
In some embodiments, according to the terminal of any previous embodiment of the present invention, the receiving unit is further configured to receive a second type voice message of the second user;
the device also comprises a determining unit used for obtaining a third type message according to the second type voice message;
the sending unit is further configured to reply the third type message to the first user.
In some embodiments, according to the terminal of any one of the foregoing embodiments of the present invention, when the determining unit obtains the third type message according to the second type voice message, specifically:
obtaining a third type message according to the corresponding relation between the preset third type message and the recognition result of the second type voice message; alternatively, the first and second electrodes may be,
and obtaining the third type message according to the second type voice message and a first preset machine learning model.
In some embodiments, the terminal according to any of the above embodiments of the present invention, wherein the third type of message is a third type of voice message, and the third type of voice message shares a voice parameter associated with the social proxy terminal or the second user with the first type of voice message.
In some embodiments, the terminal according to any of the above embodiments of the present invention further includes a sending unit, configured to send a voice query message to the second user, where the voice query message is used to query whether the second user allows interaction with the first terminal;
the receiving unit is further configured to receive a voice response message corresponding to the voice query message;
and the judging unit is used for determining whether to allow the interaction with the second user according to the voice response message.
In some embodiments, according to the terminal of any one of the above embodiments of the present invention, when the determining unit determines whether to allow the first user to interact with the second user by using a preset rule, specifically:
and judging whether the first user is matched with the second user or not by adopting a preset rule according to the request type and/or the related parameters of the first user carried in the interaction request, and determining whether the interaction between the first user and the second user is allowed or not according to a judgment result.
In some embodiments, according to the terminal of any one of the above embodiments of the present invention, the preset rule is a rule that satisfies a conditional expression and/or a logical tree expression.
In some embodiments, according to the terminal of any one of the above embodiments of the present invention, when the sending unit sends the first type voice message to the second user, specifically:
obtaining the first type voice message by using a preset configuration relation or a second preset machine learning model according to the interactive request or the interactive content sent by the first terminal;
and sending the first type voice message to the second user;
and the second preset machine learning model is generated according to the interactive corpus materials of the second user and the social agent terminal or other users.
In some embodiments, according to the terminal of any one of the above embodiments of the present invention, the social agent terminal is a smart speaker.
In some embodiments, according to the terminal of any one of the above embodiments of the present invention, when the receiving unit receives the interaction request sent by the first user through the first terminal, specifically:
and receiving an interaction request forwarded by a first social platform server where the social agent terminal is located, wherein the interaction request forwarded by the first social platform server is sent to the first social platform server by a second social platform server where the first terminal is located.
In some embodiments, according to the terminal of any one of the above embodiments of the present invention, the interaction request is directly sent by the first terminal when the first terminal determines that the preset object meets a certain condition, or the interaction request is sent by the first terminal when the first terminal determines that the preset object meets a certain condition, and sending an inquiry message to the first user according to the inquiry message.
In some embodiments, according to the terminal of any one of the above embodiments of the present invention, the preset object is a preset object other than the first user and the second user.
In a third aspect of embodiments of the present invention, there is provided a social proxy terminal, including:
one or more processors;
a memory;
a program stored in the memory, which, when executed by the one or more processors, causes the terminal to perform the method of the first aspect or any one of the embodiments of the first aspect.
In a fourth aspect of embodiments of the present invention, there is provided a computer-readable storage medium storing a program which, when executed by a processor, causes the processor to perform the method according to the first aspect or any one of the embodiments of the first aspect.
In a fifth aspect of embodiments of the present invention, there is provided a social method comprising:
determining whether a preset object meets a certain condition;
and directly sending an interaction request when the preset object is determined to meet a certain condition, or sending an inquiry message to the first user when the preset object is determined to meet the certain condition, and sending the interaction request according to the inquiry message.
In one embodiment, according to the method of the above embodiment of the present invention, the preset object is a preset object other than the first user and the second user.
In some embodiments, the method according to any of the above embodiments of the present invention, wherein the query message is used to query the first user whether to send an interaction request; the sending of the interactive request according to the inquiry message includes: receiving a response message of the inquiry message, and sending an interaction request according to the response message;
or, the query message is used for querying a target object sent by the interactive request; the sending of the interactive request according to the inquiry message includes: and receiving a response message of the inquiry message, and sending the interaction request to the target object according to the response message.
In a sixth aspect of embodiments of the present invention, there is provided an intelligent terminal, including:
the judging unit is used for determining whether the preset object meets a certain condition or not;
and the sending unit is used for directly sending an interaction request when the judging unit determines that the preset object meets a certain condition, or sending an inquiry message to the first user when the judging unit determines that the preset object meets a certain condition, and sending the interaction request according to the inquiry message.
In an embodiment, according to the terminal of the foregoing embodiment of the present invention, the preset object is a preset object other than the first user and the second user.
In some embodiments, the terminal according to any of the above embodiments of the present invention, wherein the query message is used to query whether the first user sends an interaction request; the terminal also comprises a receiving unit used for receiving a response message of the inquiry message; when the sending unit sends the interactive request according to the inquiry message, the sending unit specifically comprises: sending an interaction request according to the response message;
or, the query message is used for querying a target object sent by the interactive request; the terminal also comprises a receiving unit used for receiving a response message of the inquiry message; sending an interactive request according to the inquiry message, comprising: and sending the interaction request to the target object according to the response message.
In a seventh aspect of the embodiments of the present invention, there is provided an intelligent terminal, including:
one or more processors;
a memory;
a program stored in the memory, which, when executed by the one or more processors, causes the terminal to perform the method of any one of the embodiments of the fifth aspect or the fifth aspect.
In an eighth aspect of embodiments of the present invention, there is provided a computer-readable storage medium storing a program which, when executed by a processor, causes the processor to perform the method according to any one of the fifth aspect or the fifth aspect.
In an embodiment of the present invention, a social method executed in a social agent terminal is provided: receiving an interactive request sent by a first user through a first terminal; determining whether the first user is allowed to interact with a second user by adopting a preset rule; wherein the first user is associated with the first terminal and the second user is associated with the social proxy terminal; in the scheme, after the interaction request is received, the social agent terminal can judge whether the first user and the second user are allowed to interact, so that the social function of the user is realized through the social agent function of the social agent terminal, and the social efficiency and the social experience are improved.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
FIG. 1 is a schematic diagram illustrating a scenario of a social method performed in a social agent terminal according to an embodiment of the present invention;
FIG. 2 schematically illustrates a flow diagram of a social method for execution in a social proxy terminal, according to an embodiment of the present invention;
FIG. 3 schematically illustrates another flow diagram for a social method according to an embodiment of the present invention;
FIG. 4 schematically shows a diagram of a social proxy terminal according to an embodiment of the present invention;
FIG. 5 schematically illustrates a schematic diagram of a smart terminal according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a social device for execution in a social proxy terminal according to an embodiment of the present invention;
FIG. 7 schematically illustrates another schematic diagram of a social device for execution in a social proxy terminal, according to an embodiment of the present invention;
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Detailed Description
The principles and spirit of the present invention will be described with reference to a number of exemplary embodiments. It is understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the invention, and are not intended to limit the scope of the invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As will be appreciated by one skilled in the art, embodiments of the present invention may be embodied as a system, apparatus, device, method, or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
According to the embodiment of the invention, a social method, a terminal and a medium executed in a social agent terminal are provided.
In this document, any number of elements in the drawings is by way of example and not by way of limitation, and any nomenclature is used solely for differentiation and not by way of limitation.
The principles and spirit of the present invention are explained in detail below with reference to several representative embodiments of the invention.
Summary of The Invention
The inventor finds that social interaction can be achieved by adding a social proxy function to the smart speaker, for example, a first user interacts with a smart speaker 2 associated with a second user through an associated smart terminal 1 in advance, the smart terminal 1 sends an interaction request to the smart speaker 2, and after receiving the interaction request, the smart speaker 2 with the social proxy function determines whether to allow the first user to interact with the second user according to a preset rule, so that the first user and the second user can perform social interaction through the smart speaker, and therefore the smart speaker achieves the social function, and social efficiency and social experience are improved.
Having described the general principles of the invention, various non-limiting embodiments of the invention are described in detail below.
Application scene overview
Referring to fig. 1, the wave pre-socializes with red, the smart terminal 1 associated with the wave sends the information about the good-quality song 1 considered by the wave to the smart speaker 2 associated with red, when the smart speaker 2 with the social agent function receives the interactive request from the smart terminal 1, if the wave and the red are determined to be allowed to interact according to the preset rule, the related information of the high-quality song 1 is received, for example, a play link for a good quality song 1 is received, and the good quality song 1 is played according to the play link, and after hearing the good quality song 1 in red, a voice can be uttered, for example, say "true good hearing", when smart speaker 2 receives "true good hearing", send this sentence of "true good hearing" to smart terminal 1, smart terminal 1 can send the message to smart speaker 2 again based on this reply, can realize the social interaction between ripples and red from this.
Examples of the inventionSexual method
In the following, in connection with the application scenario of fig. 1, a social method for execution in a social proxy terminal according to an exemplary embodiment of the present invention is described with reference to fig. 2. It should be noted that the above application scenarios are merely illustrated for the convenience of understanding the spirit and principles of the present invention, and the embodiments of the present invention are not limited in this respect. Rather, embodiments of the present invention may be applied to any scenario where applicable.
Referring to fig. 2, in an embodiment of the present invention, a social method 20 executed in a social proxy terminal is provided, including:
step 200: receiving an interactive request sent by a first user through a first terminal;
step 210: determining whether the first user is allowed to interact with a second user by adopting a preset rule;
wherein the first user is associated with the first terminal and the second user is associated with the social proxy terminal.
In the embodiment of the present invention, further, the method further includes:
receiving part or all of the interactive content sent by the first terminal when determining that the first user is allowed to interact with the second user, for example, receiving a complete song or receiving the first 10 seconds of a song when determining that the first user is allowed to interact with the second user; and/or the presence of a gas in the gas,
when determining that the first user is not allowed to interact with the second user, refusing to receive the interactive content sent by the first terminal, or ignoring the interactive content sent by the first terminal, for example, when determining that the first user is not allowed to interact with the second user, refusing to receive a song, or directly ignoring the song or directly ignoring an interaction request; and/or the presence of a gas in the gas,
and when the first user is determined to be allowed to interact with the second user, sending a first type voice message to the second user.
When sending the first type voice message to the second user, the following method may be adopted:
obtaining the first type voice message by using a preset configuration relation or a second preset machine learning model according to the interactive request or the interactive content sent by the first terminal;
and sending the first type voice message to the second user;
and the second preset machine learning model is generated according to the interactive corpus materials of the second user and the social agent terminal or other users.
For example, the intelligent terminal 1 sends a voice message of "your head portrait is really good" to the intelligent sound box 2, and when the intelligent sound box 2 receives the voice message, the first type of voice message "strangers want to create accounts with you" is obtained according to the second preset machine learning model, and "strangers want to create accounts with you" is played to the second user.
The foregoing describes determining whether to allow the first user and the second user to interact, where the first user and the second user are allowed to interact, the first user and the second user may perform social interaction, where when the first user and the second user interact, a plurality of manners, such as an explicit manner or an implicit manner, may be adopted, and therefore, in this embodiment of the present invention, the method further includes:
receiving a second type voice message of the second user, and forwarding the second type voice message to the first user, in this way, the second terminal adopts a direct forwarding function, and the received second type voice message is not changed, for example, the first user sends a voice message "your head looks true and beautiful" to the smart sound box 2 through the smart terminal 1, the second user related to the smart sound box 2 says "thank you for a great prize", the smart sound box 2 directly sends "thank you for a great prize" to the smart terminal 1, and the feedback heard by the first user is "thank you for a great prize". This direct forwarding approach is the explicit approach described above.
Alternatively, the following, implicit ones described above, may also be employed:
receiving a second type voice message of the second user, obtaining a third type message according to the second type voice message, and replying the third type message to the first user, in this way, instead of directly sending the second type voice message to the first user, a new message, such as the third type message, is generated according to the received second type voice message, and the third type message is sent to the first user, for example, the first user sends a voice message "your head is true beauty" to the smart sound box 2 through the smart terminal 1, the second user associated with the smart sound box 2 says "thank you for a prize", the smart sound box 2 obtains a new message "know you with great interest" according to "thank you for a prize", and sends "know you with great interest" to the smart terminal 1, and the feedback heard by the first user is a sentence "happy you", and the sentence "thank you for a quartic prize" is not included.
In the embodiment of the present invention, when obtaining the third type message according to the second type voice message, a plurality of manners may be adopted, and optionally, the following manner may be adopted:
and obtaining the third type message according to the corresponding relation between the preset third type message and the recognition result of the second type voice message.
For example, the first user sends a master song in a new album of singer a to the second user, the second user listens and says a sentence of ' the new song of singer a is really good at listening ', the social proxy terminal associated with the second user receives the sentence of ' the new song of singer a is really good at listening ' and then performs voice recognition, and then finds a pair of preset rules of ' the new song of singer a is really good at listening ', ' your taste is really good at right ' or a pair of preset rules of ' the singer a ' -your taste is really good at right ', takes ' your taste is really good at right ' as a third type message, and then sends ' your taste is really good at right ' to the first user in a voice form;
alternatively, the following method may be adopted:
and obtaining the third type message according to the second type voice message and a first preset machine learning model.
For example, the first user sends a main song in a new album of singer a to the second user, the second user listens and says a sentence of 'the new song of singer a is really good at the right, after receiving the sentence of' the new song of singer a is really good at the right 'voice, the social proxy terminal associated with the second user performs voice recognition, and then obtains a third type message' your taste is really good at 'according to the recognition result, the new song of singer a is really good at the right' or 'the singer a' and a first preset machine learning model, and sends 'your taste is really good' to the first user in a voice form.
In this embodiment of the present invention, optionally, the third type of message is a third type of voice message, in this case, the third type of voice message may share the voice parameter associated with the social proxy terminal with the first type of voice message, that is, the social proxy terminal sends the voice message to the first user or the second user based on the same voice parameter, the voice parameter is associated with the social proxy terminal and does not change with the source of the voice or the user to be reached, but the content of the voice may be different, for example, the social proxy terminal sends "your taste is really good" to the first user and "thank you" to the second user, in this case, the two words use the same male voice, and the tone color, tone quality, etc. of the voice are the same, and will not change with the different objects of the voice message transmission.
It is described above that the voice parameters are associated with the social proxy terminal, but of course, the voice parameters may also be associated with the user, and thus, the third type voice message may share the voice parameters associated with the second user with the first type voice message. That is, the voice parameter is associated with the user corresponding to the third type of voice message, and the voice parameter is not changed as long as the user corresponding to the third type of voice message is not changed. For example, smart sound box 2 is associated with a second user, and the voice parameters based on which the third type of voice message is sent by smart sound box 2 are invariant regardless of which user wants to socially interact with the second user.
In the embodiment of the present invention, when determining whether to allow the first user and the second user to interact with each other, the opinion of the second user may be queried, and the opinion of the second user is referred to determine whether to allow the first user and the second user to interact with each other, so when determining whether to allow the first user and the second user to interact with each other by using a preset rule, optionally, the following manner may be adopted:
sending a voice inquiry message to the second user, wherein the voice inquiry message is used for inquiring whether the second user allows interaction with the first terminal;
and receiving a voice response message corresponding to the voice inquiry message, and determining whether to allow the interaction with the second user according to the voice response message.
For example, when receiving the interaction request from the smart terminal 1, the smart sound box 2 sends a voice query message "whether you agree to interact with the first user", if the second user replies "disagree", it is determined that the interaction between the first user and the second user is not allowed, and if the second user replies "very agreeable", it is determined that the interaction between the first user and the second user is allowed.
In the embodiment of the present invention, when determining whether to allow the first user to interact with the second user by using a preset rule, the following method may be adopted:
judging whether the first user is matched with the second user or not by adopting a preset rule according to the request type and/or the related parameters of the first user carried in the interactive request;
and determining whether the first user is allowed to interact with the second user according to the judgment result.
For example, if the second user sets that the user sending the interaction request is a fan of the same idol, the second user allows social interaction with the first user, and if the first user related parameter carried in the interaction request has a parameter capable of indicating that the user is the fan of the same idol, the second user allows the first user to interact with the second user.
The foregoing describes that whether the first user and the second user are matched is determined according to the request type and/or the first user related parameter, but of course, other manners may also be available, for example, a time point when the interaction request is sent, or a type of an application program corresponding to the interaction request is sent, or other manners may also be available, and various manners may be separately implemented, or any combination may also be implemented, which is not specifically limited herein.
In the embodiment of the present invention, optionally, the preset rule is a rule that satisfies a conditional expression and/or a logic tree expression.
In the embodiment of the present invention, optionally, the social agent terminal is an intelligent speaker.
In this embodiment of the present invention, optionally, receiving an interaction request sent by a first user through a first terminal includes:
and receiving an interaction request forwarded by a first social platform server where the social agent terminal is located, wherein the interaction request forwarded by the first social platform server is sent to a second social platform server by the second social platform server where the first terminal is located. According to the embodiment of the invention, the social agent terminal interacts with the second social server to form a second social system, the second social system can be opened to other social systems, for example, the second social system can be opened to a certain instant messaging system, when a first user initiates an interaction request to the social agent terminal by using an instant messaging tool, the interaction request is sent to the second social server through the instant messaging server, and then is sent to the social agent terminal by the second social server.
In the embodiment of the present invention, optionally, the interaction request is directly sent by the first terminal when the first terminal determines that the preset object meets a certain condition, or the interaction request is sent by the first terminal to the first user and sent according to an inquiry message when the first terminal determines that the preset object meets a certain condition.
The query message may be used to query the first user whether to send the interactive request, so that the first terminal may determine whether to send the interactive request according to a response message of the query message, or the query message may be a target object to which the query interactive request is to be sent, so that the first terminal may determine to whom the interactive request is to be sent according to the response message of the query message.
Of course, the above are some examples of the query message, and the query message is not limited to this in practical application, and will not be described in detail here.
In this embodiment of the present invention, optionally, the preset object is a preset object other than the first user and the second user.
For example, the preset object is a common singer idol of the first user and the second user, or a common math teacher of the same network course of the first user and the second user, and the like. The preset objects may be other entities or abstract concepts, such as new premium media content, in addition to characters.
Referring to fig. 3, the embodiment of the present invention further provides a social method 30, including:
step 300: determining whether a preset object meets a certain condition;
step 310: and directly sending an interaction request when the preset object is determined to meet a certain condition, or sending an inquiry message to the first user when the preset object is determined to meet the certain condition, and sending the interaction request according to the inquiry message.
For example, the user sends the interactive request directly when finding the premium content, or when the singer concerned issues a new album.
Optionally, the preset object is a preset object other than the first user and the second user. For example, the preset object is a common singer idol of the first user and the second user, or a common math teacher of the same network course of the first user and the second user, and the like. The preset objects may be other entities or abstract concepts, such as new premium media content, in addition to characters.
Optionally, the query message is used to query the first user whether to send an interaction request; at this time, when the interactive request is sent according to the inquiry message, the following method can be adopted: receiving a response message of the inquiry message, and sending an interaction request according to the response message;
or, optionally, the query message may also be used to query the target object sent by the interaction request; at this time, when sending the interactive request according to the query message, the following method may be adopted: and receiving a response message of the inquiry message, and sending the interaction request to the target object according to the response message.
For example, when the idol of the wave shows a new song, and after the intelligent terminal 1 obtains the information, it sends an inquiry message to the wave, saying "who you want to push the song to, your friend or nearby people, and" want to recommend to friend red ", the intelligent terminal 1 sends an interaction request to the smart sound box 2 associated with red.
It should be noted that, in the embodiment of the present invention, the first terminal may be a PC (Personal Computer), a mobile phone, a tablet Computer, a smart speaker, and the like, and the social agent terminal may also be a PC, a mobile phone, a tablet Computer, a smart speaker, and the like, which is not limited herein.
Exemplary devices
Having introduced the media of the exemplary embodiments of the present invention, next, a social proxy terminal 40 of the exemplary embodiments of the present invention will be described with reference to fig. 4, the social proxy terminal 40 including:
a receiving unit 400, configured to receive an interaction request sent by a first user through a first terminal;
a determining unit 410, configured to determine whether to allow the first user to interact with a second user according to a preset rule;
wherein the first user is associated with the first terminal and the second user is associated with the social proxy terminal.
In this embodiment of the present invention, further, the apparatus further includes a rejecting unit 420 and a sending unit 430, where:
the receiving unit 400 is configured to receive a part of or all of the interactive content sent by the first terminal when the determining unit 410 determines that the first user is allowed to interact with the second user, for example, receive a complete song or receive the first 10 seconds of a song when the determining unit determines that the first user is allowed to interact with the second user; and/or the presence of a gas in the gas,
the rejecting unit 420 is configured to reject to receive the interactive content sent by the first terminal or ignore the interactive content sent by the first terminal when the determining unit 410 determines that the first user is not allowed to interact with the second user, for example, reject to receive a song, directly ignore the song or directly ignore an interaction request when the determining unit determines that the first user is not allowed to interact with the second user; and/or the presence of a gas in the gas,
the sending unit 430 is configured to send a first type voice message to the second user when the determining unit 410 determines that the first user is allowed to interact with the second user.
When the sending unit 430 sends the first type voice message to the second user, the method specifically includes:
obtaining the first type voice message by using a preset configuration relation or a second preset machine learning model according to the interactive request or the interactive content sent by the first terminal;
and sending the first type voice message to the second user;
and the second preset machine learning model is generated according to the interactive corpus materials of the second user and the social agent terminal or other users.
For example, the intelligent terminal 1 sends a voice message of "your head portrait is really good" to the intelligent sound box 2, and when the intelligent sound box 2 receives the voice message, the first type of voice message "strangers want to create accounts with you" is obtained according to the second preset machine learning model, and "strangers want to create accounts with you" is played to the second user.
The foregoing describes that determining whether to allow the first user and the second user to interact, where the first user and the second user may perform social interaction under the condition that the first user and the second user are allowed to interact, where when the first user and the second user interact, a plurality of manners may be adopted, for example, an explicit manner or an implicit manner, and therefore in this embodiment of the present invention, the receiving unit 400 is further configured to receive the second type voice message of the second user;
the sending unit 430 is further configured to forward the second type voice message to the first user, in this way, the second terminal adopts a direct forwarding function, and the received second type voice message is not changed, for example, the first user sends a voice message "your head is true" to the smart sound box 2 through the smart terminal 1, the second user related to the smart sound box 2 says "thank you for a bonus, the smart sound box 2 directly sends" thank you for a bonus "to the smart terminal 1, and the feedback heard by the first user is" thank you for a bonus ". This direct forwarding approach is the explicit approach described above.
Or, the receiving unit 400 is further configured to receive a second type voice message of the second user;
the apparatus further comprises a determining unit 440, configured to obtain a third type message according to the second type voice message;
the sending unit 430 is further configured to reply to the third type message to the first user. This is the implicit mode described above
In this way, instead of directly sending the second type of voice message to the first user, a new message, for example, a third type of message, is generated according to the received second type of voice message, and the third type of message is sent to the first user, for example, the first user sends the voice message "your head is true beauty" to the smart sound box 2 through the smart terminal 1, the second user associated with the smart sound box 2 says "thank for the rich prize", the smart sound box 2 gets a new message "know you with great interest" according to "thank for the rich prize", and sends "know you with great interest" to the smart terminal 1, and the feedback heard by the first user is "know you with great interest" and is not "thank for the rich prize".
In this embodiment of the present invention, optionally, when the determining unit 440 obtains the third type of message according to the second type of voice message, specifically:
and obtaining the third type message according to the corresponding relation between the preset third type message and the recognition result of the second type voice message.
For example, the first user sends a master song in a new album of singer a to the second user, the second user listens and says a sentence of ' the new song of singer a is really good at listening ', the social proxy terminal associated with the second user receives the sentence of ' the new song of singer a is really good at listening ' and then performs voice recognition, and then finds a pair of preset rules of ' the new song of singer a is really good at listening ', ' your taste is really good at right ' or ' the singer a ' -your taste is really good at right ' according to the recognition result, and uses ' your taste is really good at right ' as a third type message, and then sends ' your taste is really good at right ' to the first user in a voice form.
Alternatively, the following method may be adopted:
and obtaining the third type message according to the second type voice message and a first preset machine learning model.
For example, the first user sends a main song in a new album of singer a to the second user, the second user listens and says a sentence of 'the new song of singer a is really good at the right, after receiving the sentence of' the new song of singer a is really good at the right 'voice, the social proxy terminal associated with the second user performs voice recognition, and then obtains a third type message' your taste is really good at 'according to the recognition result, the new song of singer a is really good at the right' or 'the singer a' and a first preset machine learning model, and sends 'your taste is really good' to the first user in a voice form.
In the embodiment of the present invention, optionally, the third type of message is a third type of voice message, and the third type of voice message and the first type of voice message share the voice parameter associated with the social proxy terminal, that is, the social proxy terminal sends the voice message to the first user or the second user based on the same voice parameter, and the voice parameter is associated with the social proxy terminal and does not change with the source of the voice or the user to be reached, but the content of the voice may be different, for example, the social proxy terminal sends "your taste is not wrong" to the first user and "thank you" to the second user, and at this time, the two words use the same male voice, and the tone, tone quality and the like of the voice are the same, and will not change with the different objects of the voice message transmission.
It is described above that the voice parameters are associated with the social proxy terminal, but of course, the voice parameters may also be associated with the user, and thus, the third type voice message may share the voice parameters associated with the second user with the first type voice message. That is, the voice parameter is associated with the user corresponding to the third type of voice message, and the voice parameter is not changed as long as the user corresponding to the third type of voice message is not changed. For example, smart sound box 2 is associated with a second user, and the voice parameters based on which the third type of voice message is sent by smart sound box 2 are invariant regardless of which user wants to socially interact with the second user.
In the embodiment of the present invention, when determining whether to allow the interaction between the first user and the second user, the sending unit 430 is further configured to send a voice query message to the second user, where the voice query message is used to query whether to allow the interaction between the second user and the first terminal;
the receiving unit 400 is further configured to receive a voice response message corresponding to the voice query message;
the determining unit 410 is configured to determine whether to allow interaction with the second user according to the voice response message.
For example, when receiving the interaction request from the smart terminal 1, the smart sound box 2 sends a voice query message "whether you agree to interact with the first user", if the second user replies "disagree", it is determined that the interaction between the first user and the second user is not allowed, and if the second user replies "very agreeable", it is determined that the interaction between the first user and the second user is allowed.
In this embodiment of the present invention, optionally, when the determining unit 410 determines whether to allow the first user to interact with the second user by using a preset rule, specifically:
and judging whether the first user is matched with the second user or not by adopting a preset rule according to the request type and/or the related parameters of the first user carried in the interaction request, and determining whether the interaction between the first user and the second user is allowed or not according to a judgment result.
For example, if the second user sets that the user sending the interaction request is a fan of the same idol, the second user allows social interaction with the first user, and if the first user related parameter carried in the interaction request has a parameter capable of indicating that the user is the fan of the same idol, the second user allows the first user to interact with the second user.
The foregoing describes that whether the first user and the second user are matched is determined according to the request type and/or the first user related parameter, but of course, other manners may also be available, for example, a time point when the interaction request is sent, or a type of an application program corresponding to the interaction request is sent, or other manners may also be available, and various manners may be separately implemented, or any combination may also be implemented, which is not specifically limited herein.
In the embodiment of the present invention, optionally, the preset rule is a rule that satisfies a conditional expression and/or a logic tree expression.
In the embodiment of the present invention, optionally, the social agent terminal is an intelligent speaker.
In this embodiment of the present invention, optionally, when the receiving unit 400 receives an interaction request sent by a first user through a first terminal, specifically:
and receiving an interaction request forwarded by a first social platform server where the social agent terminal is located, wherein the interaction request forwarded by the first social platform server is sent to the first social platform server by a second social platform server where the first terminal is located. According to the embodiment of the invention, the social agent terminal interacts with the second social server to form a second social system, the second social system can be opened to other social systems, for example, the second social system can be opened to a certain instant messaging system, when a first user initiates an interaction request to the social agent terminal by using an instant messaging tool, the interaction request is sent to the second social server through the instant messaging server, and then is sent to the social agent terminal by the second social server.
In the embodiment of the present invention, optionally, the interaction request is directly sent by the first terminal when the first terminal determines that the preset object meets a certain condition, or the interaction request is sent by the first terminal to the first user and sent according to an inquiry message when the first terminal determines that the preset object meets a certain condition.
The query message may be used to query the first user whether to send the interactive request, so that the first terminal may determine whether to send the interactive request according to a response message of the query message, or the query message may be a target object to which the query interactive request is to be sent, so that the first terminal may determine to whom the interactive request is to be sent according to the response message of the query message.
Of course, the above are some examples of the query message, and the query message is not limited to this in practical application, and will not be described in detail here.
In this embodiment of the present invention, optionally, the preset object is a preset object other than the first user and the second user.
For example, the preset object is a common singer idol of the first user and the second user, or a common math teacher of the same network course of the first user and the second user, and the like. The preset objects may be other entities or abstract concepts, such as new premium media content, in addition to characters.
Referring to fig. 5, a smart terminal 50 is further provided, which includes:
a judging unit 500 for determining whether a preset object meets a certain condition;
a sending unit 510, configured to directly send an interaction request when the determining unit 500 determines that the preset object meets a certain condition, or send an inquiry message to the first user when the determining unit 500 determines that the preset object meets a certain condition, and send an interaction request according to the inquiry message.
For example, the user sends the interactive request directly when finding the premium content, or when the singer concerned issues a new album.
In this embodiment of the present invention, optionally, the preset object is a preset object other than the first user and the second user. For example, the preset object is a common singer idol of the first user and the second user, or a common math teacher of the same network course of the first user and the second user, and the like. The preset objects may be other entities or abstract concepts, such as new premium media content, in addition to characters.
Optionally, the query message is used to query the first user whether to send an interaction request; at this time, the terminal further includes a receiving unit 520 for receiving a response message of the inquiry message; when the sending unit 510 sends the interactive request according to the inquiry message, specifically, the sending unit is to: sending an interaction request according to the response message;
or, optionally, the query message is used to query the target object sent by the interactive request; at this time, the terminal further includes a receiving unit 520 for receiving a response message of the inquiry message; sending an interactive request according to the inquiry message, comprising: and sending the interaction request to the target object according to the response message.
For example, when the idol of the wave shows a new song, and after the intelligent terminal 1 obtains the information, it sends an inquiry message to the wave, saying "who you want to push the song to, your friend or nearby people, and" want to recommend to friend red ", the intelligent terminal 1 sends an interaction request to the smart sound box 2 associated with red.
It should be noted that, in the embodiment of the present invention, the first terminal may be a PC, a mobile phone, a tablet computer, an intelligent speaker, and the like, and the social agent terminal may also be a PC, a mobile phone, a tablet computer, an intelligent speaker, and the like, which is not limited specifically herein.
Exemplary device
Having described the method and apparatus of the exemplary embodiments of the present invention, next, a terminal for social interaction performed in a social proxy terminal according to another exemplary embodiment of the present invention is described.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
In some possible embodiments, a terminal for performing social interaction in a social proxy terminal according to the present invention may comprise at least one processing unit, and at least one storage unit. Wherein the storage unit stores program code which, when executed by the processing unit, causes the processing unit to perform the steps in the social method for execution in a social proxy terminal according to various exemplary embodiments of the present invention described in the above section "exemplary method" of this specification. For example, the processing unit may perform step 200 as shown in fig. 2: receiving an interactive request sent by a first user through a first terminal; step 210: determining whether the first user is allowed to interact with a second user by adopting a preset rule; wherein the first user is associated with the first terminal and the second user is associated with the social proxy terminal.
For another example, the processing unit may perform step 300 as shown in fig. 3: determining whether a preset object meets a certain condition; step 310: and directly sending an interaction request when the preset object is determined to meet a certain condition, or sending an inquiry message to the first user when the preset object is determined to meet the certain condition, and sending the interaction request according to the inquiry message.
A terminal 60 for social interaction performed in the social proxy terminal according to this embodiment of the present invention is described below with reference to fig. 6. The terminal 60 for social interaction performed in the social proxy terminal shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 6, a terminal 60 for social interaction performed in a social proxy terminal is represented in the form of a general purpose computing device. The components of the terminal 60 for social interaction performed in a social proxy terminal may include, but are not limited to: the at least one processing unit 16, the at least one memory unit 28, and the bus 18 that connects the various system components (including the memory unit 28 and the processing unit 16).
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.
The storage unit 28 may include readable media in the form of volatile memory, such as Random Access Memory (RAM)31 and/or cache memory 32, and may further include Read Only Memory (ROM) 34.
Storage unit 28 may also include a program/utility 41 having a set (at least one) of program modules 42, such program modules 42 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The social terminal 60 for execution in a social proxy terminal may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, Bluetooth device, etc.), and may also communicate with one or more devices that enable a user to interact with the social terminal 60 for execution in a social proxy terminal, and/or with any device (e.g., router, modem, etc.) that enables the social terminal 60 for execution in a social proxy terminal to communicate with one or more other computing devices.
Exemplary program product
In some possible embodiments, aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a device to perform the steps in the social method for execution in a social proxy terminal according to various exemplary embodiments of the present invention described in the above section "exemplary method" of this specification, when the program product is run on the device, for example, the device may perform the steps 200 as shown in fig. 2: receiving an interactive request sent by a first user through a first terminal; step 210: determining whether the first user is allowed to interact with a second user by adopting a preset rule; wherein the first user is associated with the first terminal and the second user is associated with the social proxy terminal.
For example, the device may perform step 300 as shown in fig. 3: determining whether a preset object meets a certain condition; step 310: and directly sending an interaction request when the preset object is determined to meet a certain condition, or sending an inquiry message to the first user when the preset object is determined to meet the certain condition, and sending the interaction request according to the inquiry message.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
As shown in fig. 7, a program product 70 for social interaction performed in a social proxy terminal according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including AN object oriented programming language such as Java, C + +, or the like, as well as conventional procedural programming languages, such as the "C" language or similar programming languages.
It should be noted that although in the above detailed description several means or sub-means of the device for social interaction performed in a social proxy terminal are mentioned, this division is only not mandatory. Indeed, the features and functions of two or more of the devices described above may be embodied in one device, according to embodiments of the invention. Conversely, the features and functions of one apparatus described above may be further divided into embodiments by a plurality of apparatuses.
Moreover, while the operations of the method of the invention are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
While the spirit and principles of the invention have been described with reference to several particular embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, nor is the division of aspects, which is for convenience only as the features in such aspects may not be combined to benefit. The invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims (32)

1. A social method performed in a social proxy terminal, comprising:
receiving an interactive request sent by a first user through a first terminal;
determining whether the first user is allowed to interact with a second user by adopting a preset rule;
wherein the first user is associated with the first terminal, the second user is associated with the social proxy terminal, the social proxy terminal can instantly output voice when receiving the interaction request, and the social proxy terminal can instantly receive voice input of the second user;
the interaction request is directly sent when the first terminal determines that a preset object meets a certain condition, or the interaction request is sent to the first user by sending an inquiry message and sending the inquiry message according to a response message of the inquiry message when the first terminal determines that the preset object meets the certain condition;
the method for determining whether to allow the first user to interact with the second user by adopting a preset rule comprises one of the following two methods:
sending a voice inquiry message to the second user, wherein the voice inquiry message is used for inquiring whether the second user allows interaction with the first terminal; receiving a voice response message corresponding to the voice inquiry message, and determining whether to allow interaction with the second user according to the voice response message; or
Judging whether the first user is matched with the second user or not by adopting a preset rule according to the request type and/or the related parameters of the first user carried in the interactive request; and determining whether the first user is allowed to interact with the second user according to the judgment result.
2. The method of claim 1, further comprising:
when the first user is allowed to interact with the second user, receiving part or all of interactive contents sent by the first terminal; and/or the presence of a gas in the gas,
when determining that the first user is not allowed to interact with the second user, refusing to receive the interactive content sent by the first terminal, or ignoring the interactive content sent by the first terminal; and/or the presence of a gas in the gas,
and when the first user is determined to be allowed to interact with the second user, sending a first type voice message to the second user.
3. The method of claim 2, further comprising:
and receiving a second type voice message of the second user, and forwarding the second type voice message to the first user.
4. The method of claim 2, further comprising:
receiving a second type of voice message of the second user;
obtaining a third type message according to the second type voice message;
and replying a third type message to the first user.
5. The method of claim 4, deriving a third type of message from the second type of voice message, comprising:
obtaining a third type message according to the corresponding relation between the preset third type message and the recognition result of the second type voice message; alternatively, the first and second electrodes may be,
and obtaining the third type message according to the second type voice message and a first preset machine learning model.
6. The method of claim 4 or 5, wherein the third type of message is a third type of voice message, and the third type of voice message shares voice parameters associated with the social proxy terminal or the second user with the first type of voice message.
7. The method of claim 1, wherein the preset rule is a rule satisfying a conditional expression and/or a logical tree expression.
8. The method of claim 2, wherein issuing a first type of voice message to the second user comprises:
obtaining the first type voice message by using a preset configuration relation or a second preset machine learning model according to the interactive request or the interactive content sent by the first terminal;
and sending the first type voice message to the second user;
and the second preset machine learning model is generated according to the interactive corpus materials of the second user and the social agent terminal or other users.
9. The method of claim 1, wherein the social agent terminal is a smart speaker.
10. The method of claim 1, receiving an interactive request sent by a first user through a first terminal, comprising:
and receiving an interaction request forwarded by a first social platform server where the social agent terminal is located, wherein the interaction request forwarded by the first social platform server is sent to the first social platform server by a second social platform server where the first terminal is located.
11. The method of claim 1, wherein the preset object is a preset object other than the first user and the second user.
12. A social proxy terminal, comprising:
the receiving unit is used for receiving an interactive request sent by a first user through a first terminal;
the judging unit is used for determining whether the first user and the second user are allowed to interact or not by adopting a preset rule;
wherein the first user is associated with the first terminal, the second user is associated with the social proxy terminal, the social proxy terminal can instantly output voice when receiving the interaction request, and the social proxy terminal can instantly receive voice input of the second user;
the interaction request is directly sent when the first terminal determines that a preset object meets a certain condition, or the interaction request is sent to the first user by sending an inquiry message and sending the inquiry message according to a response message of the inquiry message when the first terminal determines that the preset object meets the certain condition;
the social agent terminal further comprises a sending unit, configured to send a voice query message to the second user, where the voice query message is used to query whether the second user allows interaction with the first terminal, the receiving unit is further used to receive a voice response message corresponding to the voice query message, and the determining unit is used to determine whether to allow interaction with the second user according to the voice response message; or
When the judging unit determines whether to allow the first user to interact with the second user by adopting a preset rule, the method specifically comprises the following steps: and judging whether the first user is matched with the second user or not by adopting a preset rule according to the request type and/or the related parameters of the first user carried in the interaction request, and determining whether the interaction between the first user and the second user is allowed or not according to a judgment result.
13. The terminal of claim 12, further comprising a rejection unit and a transmission unit, wherein:
the receiving unit is configured to receive a part of or all of the interactive content sent by the first terminal when the determining unit determines that the first user is allowed to interact with the second user; and/or the presence of a gas in the gas,
the rejecting unit is configured to reject to receive the interactive content sent by the first terminal or ignore the interactive content sent by the first terminal when the determining unit determines that the first user is not allowed to interact with the second user; and/or the presence of a gas in the gas,
the sending unit is configured to send a first type voice message to the second user when the determining unit determines that the first user is allowed to interact with the second user.
14. The terminal of claim 13, wherein the receiving unit is further configured to receive a second type voice message of the second user;
the sending unit is further configured to forward the second type of voice message to the first user.
15. The terminal of claim 13, wherein the receiving unit is further configured to receive a second type voice message of the second user;
the terminal also comprises a determining unit used for obtaining a third type message according to the second type voice message;
the sending unit is further configured to reply the third type message to the first user.
16. The terminal according to claim 15, wherein when the determining unit obtains a third type of message according to the second type of voice message, specifically:
obtaining a third type message according to the corresponding relation between the preset third type message and the recognition result of the second type voice message; alternatively, the first and second electrodes may be,
and obtaining the third type message according to the second type voice message and a first preset machine learning model.
17. The terminal of claim 15 or 16, wherein the third type of message is a third type of voice message, and the third type of voice message shares voice parameters associated with the social proxy terminal or the second user with the first type of voice message.
18. The terminal according to claim 12, wherein the preset rule is a rule satisfying a conditional expression and/or a logical tree expression.
19. The terminal according to claim 13, wherein when the sending unit sends the first type voice message to the second user, specifically:
obtaining the first type voice message by using a preset configuration relation or a second preset machine learning model according to the interactive request or the interactive content sent by the first terminal;
and sending the first type voice message to the second user;
and the second preset machine learning model is generated according to the interactive corpus materials of the second user and the social agent terminal or other users.
20. The terminal of claim 12, wherein the social agent terminal is a smart speaker.
21. The terminal of claim 12, wherein when the receiving unit receives the interaction request sent by the first user through the first terminal, specifically:
and receiving an interaction request forwarded by a first social platform server where the social agent terminal is located, wherein the interaction request forwarded by the first social platform server is sent to the first social platform server by a second social platform server where the first terminal is located.
22. The terminal according to claim 12, wherein the preset object is a preset object other than the first user and the second user.
23. A social proxy terminal, comprising:
one or more processors;
a memory;
a program stored in the memory, which when executed by the one or more processors, causes the terminal to perform the method of any one of claims 1-11.
24. A computer-readable storage medium storing a program which, when executed by a processor, causes the processor to perform the method of any one of claims 1-11.
25. A social method, comprising:
determining whether a preset object meets a certain condition;
directly sending an interaction request when the preset object is determined to meet a certain condition, or sending an inquiry message to a first user when the preset object is determined to meet the certain condition, and sending the interaction request according to a response message of the inquiry message;
the interaction request is used for enabling the social agent terminal to determine whether to allow the first user to interact with a second user by adopting a preset rule after receiving the interaction request, wherein the first user is associated with the first terminal, and the second user is associated with the social agent terminal; the social proxy terminal can instantly output voice when receiving the interaction request, and the social proxy terminal can instantly receive the voice input of the second user;
adopting a preset rule to determine whether to allow the first user to interact with the second user, wherein the method comprises one of the following two methods:
sending a voice inquiry message to the second user, wherein the voice inquiry message is used for inquiring whether the second user allows interaction with the first terminal; receiving a voice response message corresponding to the voice inquiry message, and determining whether to allow interaction with the second user according to the voice response message; or
Judging whether the first user is matched with the second user or not by adopting a preset rule according to the request type and/or the related parameters of the first user carried in the interactive request; and determining whether the first user is allowed to interact with the second user according to the judgment result.
26. The method of claim 25, wherein the preset object is a preset object other than the first user and the second user.
27. The method of claim 25 or 26, wherein the query message is used to query the first user whether to send an interaction request; the sending of the interactive request according to the inquiry message includes: receiving a response message of the inquiry message, and sending an interaction request according to the response message;
or, the query message is used for querying a target object sent by the interactive request; the sending of the interactive request according to the inquiry message includes: and receiving a response message of the inquiry message, and sending the interaction request to the target object according to the response message.
28. An intelligent terminal, comprising:
the judging unit is used for determining whether the preset object meets a certain condition or not;
a sending unit, configured to directly send an interaction request when the determining unit determines that the preset object meets a certain condition, or send an inquiry message to a first user when the determining unit determines that the preset object meets a certain condition, and send an interaction request according to a response message of the inquiry message;
the interaction request is used for enabling the social agent terminal to determine whether to allow the first user to interact with a second user by adopting a preset rule after receiving the interaction request, wherein the first user is associated with the first terminal, and the second user is associated with the social agent terminal; the social proxy terminal can instantly output voice when receiving the interaction request, and the social proxy terminal can instantly receive the voice input of the second user;
adopting a preset rule to determine whether to allow the first user to interact with the second user, wherein the method comprises one of the following two methods:
sending a voice inquiry message to the second user, wherein the voice inquiry message is used for inquiring whether the second user allows interaction with the first terminal; receiving a voice response message corresponding to the voice inquiry message, and determining whether to allow interaction with the second user according to the voice response message; or
Judging whether the first user is matched with the second user or not by adopting a preset rule according to the request type and/or the related parameters of the first user carried in the interactive request; and determining whether the first user is allowed to interact with the second user according to the judgment result.
29. The terminal of claim 28, wherein the preset object is a preset object other than the first user and the second user.
30. The terminal of claim 28 or 29, wherein the query message is for querying whether the first user sends an interaction request; the terminal also comprises a receiving unit used for receiving a response message of the inquiry message; when the sending unit sends the interactive request according to the inquiry message, the sending unit specifically comprises: sending an interaction request according to the response message;
or, the query message is used for querying a target object sent by the interactive request; the terminal also comprises a receiving unit used for receiving a response message of the inquiry message; sending an interactive request according to the inquiry message, comprising: and sending the interaction request to the target object according to the response message.
31. An intelligent terminal, comprising:
one or more processors;
a memory;
a program stored in the memory, which when executed by the one or more processors, causes the terminal to perform the method of any of claims 25-27.
32. A computer-readable storage medium storing a program which, when executed by a processor, causes the processor to perform the method of any one of claims 25-27.
CN201710250499.5A 2017-04-17 2017-04-17 Social method executed in social agent terminal, terminal and medium Active CN106888161B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710250499.5A CN106888161B (en) 2017-04-17 2017-04-17 Social method executed in social agent terminal, terminal and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710250499.5A CN106888161B (en) 2017-04-17 2017-04-17 Social method executed in social agent terminal, terminal and medium

Publications (2)

Publication Number Publication Date
CN106888161A CN106888161A (en) 2017-06-23
CN106888161B true CN106888161B (en) 2020-07-31

Family

ID=59183024

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710250499.5A Active CN106888161B (en) 2017-04-17 2017-04-17 Social method executed in social agent terminal, terminal and medium

Country Status (1)

Country Link
CN (1) CN106888161B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107749874B (en) * 2017-10-10 2024-03-15 上海嘉楠捷思信息技术有限公司 Message processing method and system
CN109039869B (en) * 2018-08-16 2020-05-05 北京达佳互联信息技术有限公司 Social communication method and device, electronic equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104065718A (en) * 2014-06-19 2014-09-24 深圳米唐科技有限公司 Method and system for achieving social sharing through intelligent loudspeaker box
CN104144108A (en) * 2013-09-30 2014-11-12 腾讯科技(深圳)有限公司 Information response method, device and system
CN104253902A (en) * 2014-07-21 2014-12-31 宋婉毓 Method for voice interaction with intelligent voice device
CN104301399A (en) * 2014-09-28 2015-01-21 深圳市星盘科技有限公司 System and method for remotely controlling loudspeaker box through voice
CN105930697A (en) * 2016-04-11 2016-09-07 厦门幻世网络科技有限公司 Method and device for opening use permission of interactive information

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104144108A (en) * 2013-09-30 2014-11-12 腾讯科技(深圳)有限公司 Information response method, device and system
CN104065718A (en) * 2014-06-19 2014-09-24 深圳米唐科技有限公司 Method and system for achieving social sharing through intelligent loudspeaker box
CN104253902A (en) * 2014-07-21 2014-12-31 宋婉毓 Method for voice interaction with intelligent voice device
CN104301399A (en) * 2014-09-28 2015-01-21 深圳市星盘科技有限公司 System and method for remotely controlling loudspeaker box through voice
CN105930697A (en) * 2016-04-11 2016-09-07 厦门幻世网络科技有限公司 Method and device for opening use permission of interactive information

Also Published As

Publication number Publication date
CN106888161A (en) 2017-06-23

Similar Documents

Publication Publication Date Title
US11240050B2 (en) Online document sharing method and apparatus, electronic device, and storage medium
US10019989B2 (en) Text transcript generation from a communication session
CN107895578B (en) Voice interaction method and device
US10637806B2 (en) User interface for a chatting application displaying a visual representation of a voice message with feature information indicating a mood
US10616154B2 (en) Method, system, storage medium for creating instant messaging discussion group
US11682393B2 (en) Method and system for context association and personalization using a wake-word in virtual personal assistants
EP2079030A1 (en) System and method for filtering user supplied video content using fingerprints
US9378474B1 (en) Architecture for shared content consumption interactions
WO2021129262A1 (en) Server-side processing method and server for actively initiating conversation, and voice interaction system capable of actively initiating conversation
EP3404875A1 (en) Electronic device providing dialog contents, server and method thereof
US10785270B2 (en) Identifying or creating social network groups of interest to attendees based on cognitive analysis of voice communications
CN108573393A (en) Comment information processing method, device, server and storage medium
CN111638928A (en) Operation guiding method, device, equipment and readable storage medium of application program
TW202022849A (en) Voice data identification method, apparatus and system
CN106888161B (en) Social method executed in social agent terminal, terminal and medium
WO2014194647A1 (en) Data exchange method, device, and system for group communication
KR20130062799A (en) Method for managing keyword information server
CN112929253A (en) Virtual image interaction method and device
CN104239371B (en) A kind of command information processing method and processing device
KR101351264B1 (en) System and method for message translation based on voice recognition
CN109325180A (en) Article abstract method for pushing, device, terminal device, server and storage medium
CN110418181B (en) Service processing method and device for smart television, smart device and storage medium
US20140362982A1 (en) Data exchange method, device, and system for group communication
CN113643706B (en) Speech recognition method, device, electronic equipment and storage medium
KR102127909B1 (en) Chatting service providing system, apparatus and method thereof

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant