CN109688049B - Information processing method and electronic device - Google Patents
Information processing method and electronic device Download PDFInfo
- Publication number
- CN109688049B CN109688049B CN201811586327.6A CN201811586327A CN109688049B CN 109688049 B CN109688049 B CN 109688049B CN 201811586327 A CN201811586327 A CN 201811586327A CN 109688049 B CN109688049 B CN 109688049B
- Authority
- CN
- China
- Prior art keywords
- communication
- information
- determining
- historical
- target
- 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
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/02—Details
- H04L12/16—Arrangements for providing special services to substations
- H04L12/18—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast
- H04L12/1813—Arrangements for providing special services to substations for broadcast or conference, e.g. multicast for computer conferences, e.g. chat rooms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
- H04L51/046—Interoperability with other network applications or services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention provides an information processing method, which is applied to a communication group comprising more than two communication objects, wherein the communication objects are set as information sent to the group by any one of the communication objects, at least one other communication object in the communication group is visible, first information sent by a first communication object in the communication objects is automatically generated by a machine and is automatically sent to the group, the method comprises the steps of obtaining at least part of historical communication information of at least one communication object in the communication group, determining a target communication object and communication response information according to the historical communication information, sending the communication response information to the group by the first communication object in a reminding mode, and the reminding object of the communication response information is the target communication object. The present disclosure also provides an electronic device.
Description
Technical Field
The present disclosure relates to an information processing method and an electronic device.
Background
With the progress of internet technology, people's lives are more and more intelligent. For example, the user can chat with the intelligent robot through the instant messaging software, and the like.
However, in the prior art, there are still some imperfect situations for the user to chat with the intelligent robot through the instant messaging software. For example, the intelligent robot can only generate response information according to pre-designed lines, so that the response information is not targeted and can not participate in the group chat.
Disclosure of Invention
One aspect of the present disclosure provides an information processing method, applied to a communication group including more than two communication objects, where the communication objects are set to be information sent by any one of the communication objects to the group, and are visible to at least one other communication object in the communication group, and a first information sent by a first communication object in the communication objects is autonomously generated by a machine and is automatically sent to the group.
Optionally, the determining of the target communication object and the communication response information according to the historical communication information includes determining a topic area of the historical communication information according to the historical communication information, determining a communication object corresponding to the historical communication information belonging to a preset topic area as the target communication object, and determining the communication response information according to the historical communication information.
Optionally, the method further includes determining accuracy of the communication response information, where the first communication object sends the communication response information to a group in a reminding manner, where a reminding object corresponding to the reminding manner is the target communication object, and when the accuracy of the communication response information is greater than a first threshold, the first communication object sends the communication response information to the group in a reminding manner, and a reminding object corresponding to the reminding manner is the target communication object.
Optionally, the determining of the target communication object and the communication response information according to the historical communication information includes determining whether there is communication information that has not been replied within a preset time according to the historical communication information, determining a communication object corresponding to the communication information that has not been replied to as the target communication object in the case that there is communication information that has not been replied to within the preset time, and determining the communication response information based on the communication information that has not been replied to.
Optionally, the determining a target communication object and communication response information according to the historical communication information includes determining a requirement of at least one communication object according to the historical communication information, sending an acquisition request when the requirement meets a preset condition, where the acquisition request is used to acquire service information adapted to the requirement, obtain the service information, and determining communication response information based on the service information.
Optionally, determining the target communication object and the communication response information according to the historical communication information includes determining the truth of the communication information corresponding to the specific sensitive information when the historical communication information includes the specific sensitive information, and determining the target communication object and the communication response information when the truth is less than or equal to a second threshold, where the communication response information is used to prompt the truth of the dialog of the communication object.
Optionally, the determining the target communication object and the communication response information according to the historical communication information includes determining utterance sequences of a plurality of communication objects according to the historical communication information, the utterance sequences representing utterance sequences of the plurality of communication objects in the group, predicting a communication object to be uttered next based on the utterance sequences, and determining the target communication object and the communication response information according to the historical communication information when the communication object to be uttered next is a device.
Optionally, the method further includes training a language model of at least one communication object based on the historical communication information, and the determining communication response information according to the historical communication information when the communication object of the next utterance is a machine includes determining communication response information according to the historical communication information and the language model of the communication object when the communication object of the next utterance selects a machine agent to respond.
Another aspect of the present disclosure provides an electronic device, including a processor and a memory, where the instructions include computer-readable instructions stored thereon, and when executed by the processor, the instructions cause the processor to perform obtaining at least part of historical communication information of at least one communication object in the communication group, determining a target communication object and communication response information according to the historical communication information, where the first communication object sends the communication response information to the group in a reminding manner, and a reminding object of the communication response information is the target communication object.
Optionally, the processor determining a target communication object and communication response information according to the historical communication information includes determining a topic area of the historical communication information according to the historical communication information, determining a communication object corresponding to the historical communication information belonging to a preset topic area as the target communication object, and determining communication response information according to the historical communication information.
Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions for implementing the method as described above when executed.
Another aspect of the disclosure provides a computer program comprising computer executable instructions for implementing the method as described above when executed.
Drawings
For a more complete understanding of the present disclosure and the advantages thereof, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, in which:
fig. 1 schematically shows an application scenario of an information processing method according to an embodiment of the present disclosure;
FIG. 2 schematically shows a flow chart of an information processing method according to an embodiment of the present disclosure;
fig. 3 schematically shows a flow chart of determining a target communication object and communication reply information according to the historical communication information according to an embodiment of the present disclosure;
fig. 4 schematically shows a flow chart of determining a target communication object and communication reply information according to the historical communication information according to another embodiment of the present disclosure;
fig. 5 schematically shows a flowchart for determining a target communication object and communication reply information according to the historical communication information according to another embodiment of the present disclosure;
fig. 6A schematically shows a flowchart for determining a target communication object and communication reply information according to the historical communication information according to another embodiment of the present disclosure;
FIG. 6B schematically illustrates a diagram where historical communications contain certain sensitive information, in accordance with an embodiment of the disclosure;
fig. 7 schematically shows a flowchart for determining a target communication object and communication reply information according to the historical communication information according to another embodiment of the present disclosure;
FIG. 8 schematically shows a flow chart of an information processing method according to an embodiment of the present disclosure;
FIG. 9 schematically shows a block diagram of an information handling system according to an embodiment of the present disclosure;
FIG. 10 schematically shows a block diagram of an information processing system according to another embodiment of the present disclosure and
FIG. 11 schematically shows a block diagram of a computer system according to an embodiment of the disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
Some block diagrams and/or flow diagrams are shown in the figures. It will be understood that some blocks of the block diagrams and/or flowchart illustrations, or combinations thereof, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the instructions, which execute via the processor, create means for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks. The techniques of this disclosure may be implemented in hardware and/or software (including firmware, microcode, etc.). In addition, the techniques of this disclosure may take the form of a computer program product on a computer-readable storage medium having instructions stored thereon for use by or in connection with an instruction execution system.
The embodiment of the disclosure provides an information processing method, which is applied to a communication group comprising more than two communication objects, wherein the communication objects are set as information sent to the group by any one of the communication objects, at least one other communication object in the communication group is visible, first information sent by a first communication object in the communication objects is autonomously generated by a machine and is automatically sent to the group, the method comprises the steps of obtaining at least part of historical communication information of at least one communication object in the communication group, determining a target communication object and communication response information according to the historical communication information, sending the communication response information to the group by the first communication object in a reminding mode, and using a reminding object corresponding to the communication response information as the target communication object.
Fig. 1 schematically shows an application scenario of an information processing method according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a scenario in which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.
As shown in fig. 1, the application scenario includes a terminal device 100, and chat information of a group "happy group" is displayed on the terminal device 100. The members of the "happy group" include at least member P, Q, M, N and robot 110.
As shown in fig. 1, members P, Q, M, N each have spoken in the group. The robot 110 can also speak in the group.
According to an embodiment of the present disclosure, the robot 110 is able to autonomously generate and send a communication message in a group so that the communication message can be seen by the remaining members of the group. As shown in fig. 1, the robot 110 autonomously generates a communication message "today's air temperature-10 ° to 0 ° @ P" based on the history chat information, and transmits the communication message to the group so as to remind the member P, so that the member P can see the communication message.
The terminal device 100 may be, for example, various electronic devices having a display screen, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
Fig. 2 schematically shows a flow chart of an information processing method according to an embodiment of the present disclosure.
As shown in fig. 2, the method includes operations S210 to S230.
In operation S210, at least part of historical communication information of at least one of the communication objects in the communication group is acquired.
In operation S220, a target communication object and communication response information are determined according to the historical communication information.
In operation S230, the first communication object sends the communication response information to a group in a reminding manner, where a reminding object corresponding to the reminding manner is the target communication object.
The information processing method is applied to communication groups with the number larger than two communication objects, the communication objects are set as information sent to the groups by any one of the communication objects, the information is visible for at least one of the rest communication objects in the communication groups, and first information sent by a first communication object in the communication objects is autonomously generated by a machine and is automatically sent to the groups.
According to the embodiment of the disclosure, the method sends the first information generated by the machine to the group as the communication response information, so that other communication objects can see the communication response information sent by the intelligent robot, the intelligent robot participates in the chat of a plurality of communication objects, and the communication response information has pertinence, but not blindly responds to all the communication information in the group, so that the chat robot is more intelligent.
For example, in the scenario shown in fig. 1, the communication group may be a "happy group," in which the communication objects include at least the member P, Q, M, N and the robot 110, wherein the first communication object may be the robot 110, for example, and the robot 110 autonomously generates the first information and automatically transmits it to the group.
According to the embodiment of the present disclosure, in operation S210, at least part of the historical communication information of at least one communication object in the communication group may be acquired according to a predetermined rule, for example. For example, the historical communication information that newly appears in the communication group is obtained every preset time period, or a preset number of newly appearing historical communication information are obtained each time. For example, taking the preset number of 4 as an example, in the scenario shown in fig. 1, the historical communication information in the get "happy group" includes the content sent by the member P, Q, M, N.
According to an embodiment of the present disclosure, the target communication object may be, for example, a communication object that transmits historical communication information satisfying a condition to be answered by the robot in operation S220. For example, in the scenario shown in fig. 1, the target communication object is determined to be the member P from the historical communication information.
According to the embodiment of the present disclosure, in operation S230, for example, in the scenario shown in fig. 1, the robot 110 transmits a communication response message "today' S air temperature-10 ° -0 ° @ P" to the group in a manner of reminding the member P.
Fig. 3 schematically shows a flowchart for determining a target communication object and communication response information according to the historical communication information according to the embodiment of the present disclosure.
As shown in fig. 3, the method includes operations S310 to S330.
In operation S310, according to the historical communication information, a topic area corresponding to the historical communication information is determined.
In operation S320, a communication object corresponding to the historical communication information belonging to the preset topic area is determined as a target communication object.
In operation S330, communication response information is determined according to the historical communication information.
According to the embodiment of the disclosure, the robot in the method can respond to the historical communication information belonging to the preset topic field instead of responding to each piece of communication information, so that the probability of asking questions is reduced.
According to an embodiment of the present disclosure, in operation S310, the topic area may be, for example, home appliance maintenance, health maintenance, soccer, or the like. For example, the topic area corresponding to the historical communication information may be determined according to words appearing in the historical communication information. Alternatively, a machine learning model is established based on the correspondence between a large amount of communication information and the topic areas, so that the historical communication information is used as the input of the machine learning model, and the topic areas corresponding to the historical communication information are output by the machine learning model.
According to the embodiment of the present disclosure, in operation S320, for example, in the scenario shown in fig. 1, the preset topic area includes weather, and the communication object P corresponding to the historical communication information "cold outside" is determined as the target communication object.
According to the embodiment of the present disclosure, in operation S330, the communication response information may be determined to be "today' S air temperature-10 ° -0 ° @ P", for example, according to the historical communication information "cold outside".
Fig. 4 schematically shows a flowchart of determining a target communication object and communication response information according to the historical communication information according to another embodiment of the present disclosure.
As shown in fig. 4, the method includes operations S410 to S430.
In operation S410, it is determined whether there is communication information that has not been replied within a preset time, based on the historical communication information.
In operation S420, in the case where there is communication information that is not replied within a preset time, a communication object corresponding to the communication information that is not replied is determined as a target communication object.
In operation S430, communication reply information is determined based on the unanswered communication information.
The method enables the robot to autonomously generate response information under the condition that the group is cold or people in the group ask questions without being concerned by people, so that the atmosphere of the communication group is activated.
According to the embodiment of the present disclosure, in operation S410, the communication not replied to may be, for example, a communication overwhelmed by other communication, such as the communication sent by the member P shown in fig. 1, or may be a communication sent by a member, and no new communication has appeared.
According to an embodiment of the present disclosure, in operation S420, for example, in the scenario illustrated in fig. 1, the target communication object is determined to be a member P.
According to an embodiment of the present disclosure, the communication reply information is adapted with the communication information that is not replied in operation S430. For example, in the scenario shown in fig. 1, it is determined that the communication response information is today's outdoor temperature.
Fig. 5 schematically shows a flowchart for determining a target communication object and communication response information according to the historical communication information according to another embodiment of the present disclosure.
As shown in fig. 5, the method includes operations S510 to S540.
In operation S510, a requirement of at least one communication object is determined according to the historical communication information.
In operation S520, when the requirement meets a preset condition, an obtaining request is sent, where the obtaining request is used to obtain service information adapted to the requirement.
In operation S530, the service information is obtained.
In operation S540, communication response information is determined based on the service information.
The method can provide targeted service information for the communication object, and enriches the functions of the robot.
According to an embodiment of the present disclosure, in operation S510, a requirement of a communication object may be determined, for example, according to communication information transmitted by the communication object. For example, the requirement for determining the communication partner may be dinner recommendation according to the communication information "do not know what to eat at night".
According to an embodiment of the present disclosure, in operation S520, for example, an acquisition request may be transmitted to a server capable of providing a corresponding service. According to the embodiment of the disclosure, the requirement meeting the preset condition includes that the requirement is a requirement of a preset field, or the probability that the robot determines that the requirement is accurate is high. For example, the robot may establish a communication connection with servers that provide service information of preset fields, so that the robot can send an acquisition request to the servers when the demand is in the preset fields. For example, it is determined that the demand of the communication object is a recommended dinner, and in the case where the robot can communicate with a server that provides dinner information, an acquisition request is sent to the server.
According to an embodiment of the present disclosure, in operation S530, for example, service information transmitted by a server providing a service may be received. For example, dinner information provided by some dining applications is received.
According to an embodiment of the present disclosure, in operation S540, for example, dinner of different cuisine may be recommended to the user according to the dinner information.
Fig. 6A schematically shows a flowchart of determining a target communication object and communication reply information according to the historical communication information according to another embodiment of the present disclosure.
As shown in fig. 6A, the method includes operations S610 to S620.
In operation S610, in a case that the historical communication information includes specific sensitive information, a degree of truth of communication information corresponding to the specific sensitive information is determined.
In operation S620, in a case that the degree of truth is less than or equal to a second threshold, a target communication object and communication response information are determined, where the communication response information is used to prompt the communication object for the degree of truth of the dialog. The second threshold may be, for example, 0.8, or 0.9, etc. According to an embodiment of the present disclosure, the second threshold may be set, for example, according to experience of a person skilled in the art.
The method can identify the false information and prompt the communication object, prevent the communication object from being deceived by the false information, and ensure the property, the personal safety and the like of the communication object.
According to an embodiment of the present disclosure, in operation S610, the specific sensitive information may be, for example, a sensitive vocabulary pre-stored in a local or server, and may include, for example, a bank, a password, a medicine, a health product, and the like. Alternatively, whether particular sensitive information is included in the historical communication information may be determined through a method of machine learning.
Fig. 6B schematically illustrates a diagram that historical communications contain certain sensitive information, according to an embodiment of the disclosure.
As shown in fig. 6B, member P sends information 610 about a certain health product. The robot 110 can recognize that the information 610 contains certain sensitive information.
In one embodiment, where the historical communications include particular sensitive information, the content on the network regarding that information is automatically looked up. The authenticity of the communication is determined to be very low, for example in the case where the search finds that the information has already been reported on the network.
According to the embodiment of the present disclosure, in operation S620, for example, in the case that the degree of truth is less than or equal to the second threshold, it may be determined that the target communication object is all members in the group, and a message prompting that the communication information is false information is sent to the group. As shown in fig. 6B, the robot sends a message 620 to the group to alert the communicating party.
According to the embodiment of the present disclosure, the information processing method may further include determining accuracy of the communication response information, and when the accuracy of the communication response information is greater than a first threshold, the first communication object sends the communication response information to a group in a reminding manner, where a reminding object corresponding to the reminding manner is the target communication object. The method can ensure the credibility of the communication response information generated by the machine, thereby improving the user experience. According to an embodiment of the present disclosure, the first threshold may be, for example, 85%, 90%, etc. According to an embodiment of the present disclosure, the first threshold may be set, for example, according to experience of a person skilled in the art. For example, when "what is a treatment of the subjective condition" is discussed in the communication group, the robot can obtain accurate information from the cloud, and then send a communication response message to the group. For another example, when "the direction of development of the future artificial intelligence" is discussed in the communication group, the robot cannot obtain highly accurate information, and no communication response information is generated.
Fig. 7 schematically shows a flowchart for determining a target communication object and communication response information according to the historical communication information according to another embodiment of the present disclosure.
As shown in fig. 7, the method includes operations S710 to S730.
In operation S710, a speaking sequence of a plurality of communication objects is determined according to the historical communication information, and the speaking sequence represents a speaking sequence of the plurality of communication objects in the group.
In operation S720, a communication target of a next utterance is predicted based on the utterance sequence.
In operation S730, in the case where the communication target of the next utterance is a device, a target communication target and communication response information are determined according to the historical communication information.
The method enables the robot to send the communication response information at a proper time, avoids the condition that the communication response information sent by the robot is improper, and further disturbs the communication experience between communication objects.
According to an embodiment of the present disclosure, in operation S710, for example, in the scenario shown in fig. 1, the obtained utterance sequence R is obtained according to the obtained historical communication informationseq＝{P，Q，M，N}。
According to the embodiment of the present disclosure, in operation S720, for example, machine learning may be performed using the utterance sequence of the historical communication information, a prediction model is obtained, and an object of a next utterance is predicted according to the prediction model.
According to an embodiment of the present disclosure, in operation S730, the communication object of the next utterance is a machine, and the communication object of the next utterance is a real user, and the real user has selected to be answered by a machine agent. For example, a real user has opened a managed mode in the communication group. According to an embodiment of the present disclosure, the communication object of the next utterance includes that the machine participates in the chat of the group as an independent role, and the communication object of the next utterance is a role corresponding to the robot. According to an embodiment of the present disclosure, determining the communication response information according to the historical communication information includes determining a language expression of the communication response information according to the historical communication information such that the language expression of the communication response information is adapted to the historical communication information.
According to an embodiment of the present disclosure, the method further includes training a language model of at least one communication object based on the historical communication information, and determining the communication response content according to the historical communication information and the language model of the communication object when the communication object speaking next selects to be responded by the machine agent. The method ensures that the communication response information responded by the machine agent conforms to the language characteristics of the communication object, and improves the user experience.
Fig. 8 schematically shows a flow chart of an information processing method according to an embodiment of the present disclosure.
As shown in fig. 8, the method includes operations S810 to S850.
According to an embodiment of the present disclosure, in operation S810, input data is obtained. The input data may be, for example, historical communication information in the group. For example, the scenario illustrated in FIG. 8, where the historical communication sent by member R1 is "hello! ", the historical communication sent by member R2 is" weather good today ", etc.
According to an embodiment of the present disclosure, after obtaining the input data, the obtained historical communication information, for example, may be formatted, i.e., the historical communication information is arranged according to a certain format. For example, after formatting the historical communication information, obtaining the speaking sequence R of each member in the groupseqR1, R2, … …, Rn, and the speaker utterance information Si corresponding to each member Ri.
According to an embodiment of the present disclosure, in operation S820, the character language module of each speaking member learns the content information spoken by the member, thereby learning the language expression and habit of the member.
According to an embodiment of the present disclosure, in operation S830, according to the speaking sequence RseqR1, R2, … …, Rn, and predict who the next speaker is, and to which speaker's speech content should be responded.
According to an embodiment of the present disclosure, in operation S840, according to the prediction result in operation 830, a corresponding character language module is selected, and it is determined whether to speak. For example, if the predicted next speaker is Ri and Ri chooses to be responded by the machine agent, then the corresponding character language module of Ri is selected. According to an embodiment of the present disclosure, if the predicted speaker is a machine, a targeted response is generated for which speaker's speech content response is predicted. If the predicted next speaker is not a machine, no responsive content is generated.
According to an embodiment of the present disclosure, in operation S850, in the case where the predicted speaker is a machine, the dialog generation module generates a response sentence according to the historical communication information.
According to an embodiment of the present disclosure, after the answer sentence is generated, answer information is output in operation S860.
FIG. 9 schematically shows a block diagram of an information handling system 900 according to an embodiment of the disclosure.
As shown in fig. 9, the information processing system 900 includes an acquisition module 910, a determination module 920, and a transmission module 930.
The obtaining module 910, for example, performs the operation S210 described above with reference to fig. 2, and obtains at least part of the historical communication information of at least one of the communication objects in the communication group.
The determining module 920, for example, performs the operation S220 described above with reference to fig. 2, and determines the target communication object and the communication response information according to the historical communication information.
The sending module 930, for example, executes the operation S230 described above with reference to fig. 2, where the first communication object sends the communication response information to the group in a reminding manner, and a reminding object corresponding to the reminding manner is the target communication object.
According to an embodiment of the present disclosure, the determining module 920 may include a determine topic sub-module, a determine object sub-module, and a determine answer sub-module.
And the topic determining submodule is used for determining the topic field corresponding to the historical communication information according to the historical communication information.
And the object determining submodule is used for determining a communication object corresponding to the historical communication information belonging to the preset topic field as a target communication object.
And the determination response submodule is used for determining communication response information according to the historical communication information.
According to an embodiment of the present disclosure, the determining module 920 may include a first determining sub-module, a second determining sub-module, and a third determining sub-module.
The first determining submodule is used for determining whether the communication information which is not replied within the preset time exists according to the historical communication information.
The second determining submodule is used for determining a communication object corresponding to the communication information which is not replied as a target communication object under the condition that the communication information which is not replied within the preset time exists.
And the third determination submodule is used for determining communication response information based on the communication information which is not replied.
According to an embodiment of the present disclosure, the determining module 920 may include a determining requirement sub-module, a sending sub-module, an obtaining sub-module, and a fourth determining sub-module.
And the requirement determining submodule is used for determining the requirement of at least one communication object according to the historical communication information.
The sending submodule is used for sending an obtaining request under the condition that the requirement meets a preset condition, wherein the obtaining request is used for obtaining the service information adaptive to the requirement.
The obtaining submodule is used for obtaining the service information.
And the fourth determining submodule is used for determining communication response information based on the service information.
According to an embodiment of the present disclosure, the determining module 920 may include a determine liveness submodule and a fifth determining submodule.
And the truth determining submodule is used for determining the truth of the communication information corresponding to the specific sensitive information under the condition that the historical communication information comprises the specific sensitive information.
And the fifth determining submodule is used for determining a target communication object and communication response information under the condition that the truth is less than or equal to a second threshold, wherein the communication response information is used for prompting the truth of the conversation sentence of the communication object.
Fig. 10 schematically shows a block diagram of an information processing system 1000 according to another embodiment of the present disclosure.
As shown in fig. 10, the information processing system 1000 further includes a judging module 1010 on the basis of the foregoing embodiments.
The judging module 1010 is configured to judge an accuracy of the communication response message. The sending module 930 is configured to, when the accuracy of the communication response information is greater than a first threshold, send the communication response information to a group by the first communication object in a reminding manner, where a reminding object corresponding to the reminding manner is the target communication object.
According to an embodiment of the present disclosure, the determining module 920 may include a determining sequence sub-module, a prediction sub-module, and a sixth determining sub-module.
And the determining sequence submodule is used for determining speaking sequences of a plurality of communication objects according to the historical communication information, and the speaking sequences represent speaking sequences of the plurality of communication objects in the group.
And the prediction sub-module is used for predicting a communication object of the next speech based on the speech sequence.
And a sixth determining submodule configured to determine a target communication destination and communication response information based on the historical communication information, when the communication destination of the next utterance is the device.
According to the embodiment of the present disclosure, the electronic device further includes a training module on the basis of the foregoing embodiment. The training module is used for training a language model of at least one communication object based on the historical communication information. The sixth determining submodule includes a determining subunit configured to determine, when the communication target of the next utterance selects a machine agent to respond to, communication response information according to the historical communication information and a language model of the communication target.
Any number of modules, sub-modules, units, sub-units, or at least part of the functionality of any number thereof according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging a circuit, or in any one of or a suitable combination of software, hardware, and firmware implementations. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the disclosure may be at least partially implemented as a computer program module, which when executed may perform the corresponding functions.
For example, any of the obtaining module 910, the determining module 920, the sending module 930, and the determining module 1010 may be combined into one module to be implemented, or any one of the modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the obtaining module 910, the determining module 920, the sending module 930, and the determining module 1010 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware, and firmware, or any suitable combination of any of them. Alternatively, at least one of the obtaining module 910, the determining module 920, the sending module 930, and the determining block 1010 may be at least partially implemented as a computer program module, which when executed, may perform a corresponding function.
FIG. 11 schematically illustrates a block diagram of a computer system suitable for implementing the above-described method according to an embodiment of the present disclosure. The computer system illustrated in FIG. 11 is only one example and should not impose any limitations on the scope of use or functionality of embodiments of the disclosure.
As shown in fig. 11, computer system 1100 includes a processor 1110 and a computer-readable storage medium 1120. The computer system 1100 may perform a method according to an embodiment of the disclosure.
In particular, processor 1110 may include, for example, a general purpose microprocessor, an instruction set processor and/or related chip set and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), and/or the like. The processor 1110 may also include onboard memory for caching purposes. Processor 1110 may be a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.
Computer-readable storage medium 1120, for example, may be a non-volatile computer-readable storage medium, specific examples including, but not limited to: magnetic storage devices, such as magnetic tape or Hard Disk Drives (HDDs); optical storage devices, such as compact disks (CD-ROMs); a memory, such as a Random Access Memory (RAM) or a flash memory; and so on.
The computer-readable storage medium 1120 may include a computer program 1121, and the computer program 1121 may include code/computer-executable instructions that, when executed by the processor 1110, cause the processor 1110 to perform a method according to an embodiment of the present disclosure, or any variation thereof.
The computer programs 1121 can be configured to have, for example, computer program code including computer program modules. For example, in an example embodiment, code in computer program 1121 may include one or more program modules, including, for example, 1121A, 1121B, … …. It should be noted that the division and number of modules are not fixed, and those skilled in the art may use suitable program modules or program module combinations according to actual situations, so that the processor 1110 may execute the method according to the embodiment of the present disclosure or any variation thereof when the program modules are executed by the processor 1110.
According to an embodiment of the present invention, at least one of the obtaining module 910, the determining module 920, the sending module 930, and the determining block 1010 may be implemented as a computer program module described with reference to fig. 11, which, when executed by the processor 1110, may implement the corresponding operations described above.
The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer 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.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
While the disclosure has been shown and described with reference to certain exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the disclosure as defined by the appended claims and their equivalents. Accordingly, the scope of the present disclosure should not be limited to the above-described embodiments, but should be defined not only by the appended claims, but also by equivalents thereof.
Claims (9)
1. An information processing method applied to a communication group comprising more than two communication objects, wherein the communication objects are set as information sent by any one communication object to the group, the information is visible to at least one other communication object in the communication group, first information sent by a first communication object in the communication objects is autonomously generated by a machine and is automatically sent to the group, and the method comprises the following steps:
acquiring at least part of historical communication information of at least one communication object in the communication group;
determining a target communication object and communication response information according to the historical communication information; and
the first communication object sends the communication response information to a group in a reminding mode, wherein the reminding object of the communication response information is the target communication object,
wherein the determining a target communication object and communication response information according to the historical communication information comprises:
determining speaking sequences of a plurality of communication objects according to the historical communication information;
predicting a communication target of a next utterance based on the utterance sequence; and
and when the communication target of the next utterance is a device, determining a target communication target and communication response information according to the historical communication information.
2. The method of claim 1, wherein said determining a target communication object and communication reply information from said historical communication information comprises:
determining the topic field of the historical communication information according to the historical communication information;
determining a communication object corresponding to historical communication information belonging to a preset topic field as a target communication object; and
and determining communication response information according to the historical communication information.
3. The method of claim 1, further comprising: determining an accuracy of the communication reply information,
the first communication object sends the communication response information to a group in a reminding mode, and a reminding object corresponding to the communication response information is the target communication object, and the reminding object comprises:
and under the condition that the accuracy of the communication response information is greater than a first threshold value, the first communication object sends the communication response information to a group in a reminding mode, and a reminding object of the communication response information is the target communication object.
4. The method of claim 1, wherein said determining a target communication object and communication reply information from said historical communication information comprises:
determining whether communication information which is not replied within preset time exists or not according to the historical communication information;
under the condition that communication information which is not replied within preset time exists, determining a communication object corresponding to the communication information which is not replied as a target communication object; and
determining a communication reply message based on the unanswered communication message.
5. The method of claim 1, wherein said determining a target communication object and communication reply information from said historical communication information comprises:
determining the requirement of at least one communication object according to the historical communication information;
sending an acquisition request under the condition that the requirement meets a preset condition, wherein the acquisition request is used for acquiring service information adaptive to the requirement;
obtaining the service information; and
and determining communication response information based on the service information.
6. The method of claim 1, wherein said determining a target communication object and communication reply information from said historical communication information comprises:
determining the truth degree of the communication information corresponding to the specific sensitive information under the condition that the historical communication information comprises the specific sensitive information;
and under the condition that the truth is less than or equal to a second threshold value, determining a target communication object and communication response information, wherein the communication response information is used for prompting the truth of the communication information of the communication object.
7. The method of claim 1, further comprising:
training a language model of at least one communication partner based on the historical communication information,
wherein, when the communication destination of the next utterance is a device, the communicating response information according to the history communication information includes:
and when the communication object of the next utterance selects to be responded by the machine agent, determining communication response information according to the historical communication information and the language model of the communication object.
8. An information processing apparatus including a communication group of more than two communication objects, the communication objects being set as information in which any one of the communication objects transmits to the group, being visible to at least one other of the communication objects in the communication group, first information transmitted by a first communication object of the communication objects being autonomously generated by a machine and automatically transmitted into the group, the information processing apparatus comprising:
a processor; and
a memory having computer-readable instructions stored thereon that, when executed by the processor, cause the processor to perform:
acquiring at least part of historical communication information of at least one communication object in the communication group;
determining a target communication object and communication response information according to the historical communication information; and
the first communication object sends the communication response information to a group in a reminding mode, a reminding object corresponding to the communication response information is the target communication object,
wherein the determining a target communication object and communication response information according to the historical communication information comprises:
determining speaking sequences of a plurality of communication objects according to the historical communication information;
predicting a communication target of a next utterance based on the utterance sequence; and
and when the communication target of the next utterance is a device, determining a target communication target and communication response information according to the historical communication information.
9. The information processing apparatus according to claim 8, wherein the processor determining a target communication object and communication response information from the history communication information includes:
determining the topic field of the historical communication information according to the historical communication information;
determining a communication object corresponding to historical communication information belonging to a preset topic field as a target communication object; and
and determining communication response information according to the historical communication information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811586327.6A CN109688049B (en) | 2018-12-24 | 2018-12-24 | Information processing method and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811586327.6A CN109688049B (en) | 2018-12-24 | 2018-12-24 | Information processing method and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109688049A CN109688049A (en) | 2019-04-26 |
| CN109688049B true CN109688049B (en) | 2020-10-27 |
Family
ID=66189118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811586327.6A Active CN109688049B (en) | 2018-12-24 | 2018-12-24 | Information processing method and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109688049B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116319630A (en) * | 2023-03-07 | 2023-06-23 | 北京奇艺世纪科技有限公司 | Message reply method and device, electronic equipment and readable storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678269A (en) * | 2012-08-30 | 2014-03-26 | 国际商业机器公司 | Information processing method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170255974A1 (en) * | 2016-03-02 | 2017-09-07 | Paypal, Inc. | Context aware transaction management system |
| US10417021B2 (en) * | 2016-03-04 | 2019-09-17 | Ricoh Company, Ltd. | Interactive command assistant for an interactive whiteboard appliance |
| CN106357414B (en) * | 2016-08-23 | 2019-05-17 | 北京创智信科科技股份有限公司 | Information interacting method and system for base station electric generation management |
| WO2018112896A1 (en) * | 2016-12-23 | 2018-06-28 | 深圳前海达闼云端智能科技有限公司 | Chat interaction method and apparatus, and electronic device thereof |
| CN108040003B (en) * | 2017-12-21 | 2019-12-17 | 维沃移动通信有限公司 | Reminding method and device |
-
2018
- 2018-12-24 CN CN201811586327.6A patent/CN109688049B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678269A (en) * | 2012-08-30 | 2014-03-26 | 国际商业机器公司 | Information processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109688049A (en) | 2019-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10404629B2 (en) | Automatic reply method, device, apparatus, and storage medium | |
| US10079013B2 (en) | Sharing intents to provide virtual assistance in a multi-person dialog | |
| US10096316B2 (en) | Sharing intents to provide virtual assistance in a multi-person dialog | |
| US9679300B2 (en) | Systems and methods for virtual agent recommendation for multiple persons | |
| US9710459B2 (en) | Communication monitoring based on sentiment | |
| US9866511B2 (en) | Ensuring that a composed message is being sent to the appropriate recipient | |
| US10733572B2 (en) | Data protection using alerts to delay transmission | |
| US10984200B2 (en) | Contextual fit determination for proposed messages | |
| US11153109B2 (en) | Intelligent teleconference operations in an internet of things (IoT) computing environment | |
| US20120089683A1 (en) | Automated assistance for customer care chats | |
| KR102169397B1 (en) | Method and server for providing semi-automatic communication using chatbot and consultant | |
| US9369425B2 (en) | Email and instant messaging agent for dialog system | |
| EP2798610A1 (en) | Sharing user information with proximate devices | |
| WO2021068764A1 (en) | Information processing method and device | |
| US20180046707A1 (en) | Providing searching strategy in connection with answering question in message | |
| US11122024B2 (en) | Chat session dynamic security | |
| CN104394169A (en) | Method and server for anonymously sending private messages by both parties | |
| CN109688049B (en) | Information processing method and electronic device | |
| WO2017160357A1 (en) | Question and answer interface based on contextual information | |
| US20180349754A1 (en) | Communication reply bot | |
| US20180063282A1 (en) | Generating automatic responses to requests for information | |
| CN115906808A (en) | Method, device, medium and computing device for confirming speech response degree | |
| CN114157763A (en) | Information processing method and device in interactive process, terminal and storage medium | |
| US11170178B2 (en) | Determining the user's current preferred manner in communicating with user | |
| US9325658B2 (en) | Providing contextual relevance of an unposted message to an activity stream after a period of time elapses |
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 |