CN111191019A - Information processing method, electronic equipment and information processing system - Google Patents
Information processing method, electronic equipment and information processing system Download PDFInfo
- Publication number
- CN111191019A CN111191019A CN201911424359.0A CN201911424359A CN111191019A CN 111191019 A CN111191019 A CN 111191019A CN 201911424359 A CN201911424359 A CN 201911424359A CN 111191019 A CN111191019 A CN 111191019A
- Authority
- CN
- China
- Prior art keywords
- information
- input information
- robot
- user
- robots
- 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.)
- Pending
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 30
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 230000003993 interaction Effects 0.000 claims abstract description 97
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000012216 screening Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 4
- 238000000586 desensitisation Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Abstract
The application provides an information processing method, an electronic device and an information processing system, wherein the method comprises the following steps: receiving first input information of a user in an intelligent dialogue system; determining a target robot based on the first input information; establishing an interaction between the user and the target robot in the intelligent dialog system; the intelligent dialogue system can generate response information based on input information to achieve multi-round interaction with the user, and accuracy of the intelligent dialogue system for solving problems for the user is improved.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to an information processing method, an electronic device, and an information processing system.
Background
At present, the task type chat robot can be applied to an intelligent dialogue system to answer questions posed by users. Specifically, the user may perform multiple rounds of interaction with the randomly assigned robot, thereby solving the user's problem.
But the intelligent dialogue system has low accuracy in solving problems due to the limited ability of the robot to solve the problems.
Disclosure of Invention
In view of the above, the present invention provides an information processing method, an electronic device and an information processing system to solve the above technical problems.
In order to achieve the purpose, the invention provides the following technical scheme:
an information processing method comprising:
receiving first input information of a user in an intelligent dialogue system;
determining a target robot based on the first input information;
establishing an interaction between the user and the target robot in the intelligent dialog system; the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user.
Preferably, the determining the target robot based on the first input information includes:
sending the first input information to a plurality of robots;
receiving a plurality of pieces of first response information fed back by the plurality of robots, wherein the first response information carries a matching degree parameter for responding to the first input information;
and determining that the robot which sends the matching degree parameter carried in the first response information meets a first preset condition is a target robot.
Preferably, the determining the target robot based on the first input information includes:
sending the first input information to a plurality of robots;
receiving a plurality of first response messages fed back by the plurality of robots;
matching the plurality of first response information with preset dimensional characteristics respectively to determine matching degree parameters;
and screening the robot which sends the first response information and meets the first preset condition as the target robot.
Preferably, the sending the first input information to a plurality of robots includes:
determining a robot type based on the first input information;
and sending the first input information to a plurality of robots with the robot types.
Preferably, the target robot comprises at least two target robots, the method further comprising:
outputting first response information of the at least two target robots, wherein the first response information is information responding to the first input information;
acquiring second input information of the user;
determining a first target robot among the at least two target robots based on the second input information;
maintaining the user's interaction with the first target robot, canceling the user's interaction with other target robots than the first target robot.
An electronic device, comprising:
a first interface for receiving first input information of a user in an intelligent dialog system;
a processor for determining a target robot based on the first input information, establishing an interaction between the user and the target robot in the intelligent dialog system; the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user.
Preferably, the method further comprises the following steps:
a second interface;
the processor determines a target robot based on the first input information, comprising:
sending the first input information to a plurality of robots through the second interface;
receiving a plurality of pieces of first response information fed back by the plurality of robots through the second interface, wherein the first response information carries a matching degree parameter for responding the input information;
and determining that the robot which sends the matching degree parameter carried in the first response information meets a first preset condition is a target robot.
Preferably, the method further comprises the following steps:
a second interface;
the processor determines a target robot based on the first input information, comprising:
sending the first input information to a plurality of robots through the second interface;
receiving a plurality of first response messages fed back by the plurality of robots through the second interface;
matching the plurality of first response information with preset dimensional characteristics respectively to determine matching degree parameters;
and screening the robot which sends the first response information and meets the first preset condition as the target robot.
Preferably, the processor sends the first input information to a plurality of robots through the second interface, and the method includes:
determining a robot type based on the first input information;
and sending the first input information to a plurality of robots with the robot types through the second interface.
An information processing system comprising:
a plurality of robots;
an electronic device in communication with the plurality of robots, the electronic device comprising:
a first interface for receiving first input information of a user in an intelligent dialog system;
a processor for determining a target robot based on the first input information, establishing an interaction between the user and the target robot in the intelligent dialog system; the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user.
According to the technical scheme, the information processing method comprises the steps of receiving first input information of a user in an intelligent dialogue system, determining a target robot based on the first input information, and establishing interaction between the user and the target robot in the intelligent dialogue system, wherein the intelligent dialogue system can generate response information based on the input information to realize multi-round interaction with the user; therefore, the target robot interacting with the user can be matched based on the first input information of the user, namely the target robot is allocated to the user in a targeted mode, and therefore the accuracy of the intelligent dialogue system for solving the problem for the user is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of an information processing method according to a first method embodiment of the present application;
fig. 2 is a schematic flowchart of an information processing method according to a second embodiment of the present disclosure;
fig. 3 is a schematic flowchart of an information processing method according to a third method embodiment of the present application;
fig. 4 is a schematic flowchart of an information processing method according to a fourth method embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to a first apparatus embodiment of the present application;
fig. 6 is a schematic structural diagram of an information processing system according to a sixth apparatus embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A first method embodiment of the present application provides an information processing method, as shown in fig. 1, the method may include the following steps:
step 101: receiving first input information of a user in an intelligent dialogue system;
the information processing method can be executed by electronic equipment, the electronic equipment can be specifically a server, the electronic equipment can be applied to an intelligent dialogue system, the intelligent dialogue system can generate response information based on input information to realize multi-round interaction with the user, and the target robot determined subsequently can complete the multi-round interaction with the user.
Step 102: determining a target robot based on the first input information;
the electronic device may communicate with the plurality of robots to determine a target robot from the plurality of robots based on the first input information. In particular, the electronic device may provide an open interface to multiple robots to communicate with the multiple robots.
It should be noted that the robot in the present application may be a task-based chat robot.
Step 103: establishing an interaction between the user and the target robot in the intelligent dialog system.
In particular, a direct interaction of the user with the target robot may be established, i.e. the interaction of the user with the target robot may not be performed by the electronic device. Alternatively, an indirect interaction of the user with the target robot can also be established, i.e. the interaction of the user with the target robot is still performed by the electronic device.
Under the condition that the user establishes interaction with the target robot, the user can perform multi-round interaction with the target robot in the intelligent dialogue system, namely, the target robot can generate response information based on the input information of the user so as to realize multi-round interaction with the user. This multi-round interaction can refer to inputting information once for the user, and information is fed back once for the target robot, and information is input once again for the user, and information is fed back once again for the target robot. For example, the input information of the user is: how do I's cell phone often turn off? The target robot generates response information based on the input information: asking for your mobile phone model number is? The user inputs again based on the response information of the target robot: the model of the mobile phone is xxxx. The target robot continues to generate response information based on the input information: asking for how much the current electricity quantity of the mobile phone is. The user inputs the information … again, and the target robot generates the response information … again, so that the problem that the mobile phone of the user is frequently turned off is solved through multiple rounds of interaction.
It should be noted that the above-mentioned multiple rounds of interaction may be performed in a conversation window, and specifically may be communicated in a text or voice manner.
In summary, in the embodiment, the interaction between the user and the target robot is established in the intelligent dialogue system by receiving the first input information of the user in the intelligent dialogue system, determining the target robot based on the first input information, wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user; therefore, the target robot interacting with the user can be matched based on the first input information of the user, namely the target robot is allocated to the user in a targeted mode, and therefore the accuracy of the intelligent dialogue system for solving the problem for the user is improved.
A second method embodiment of the present application provides an information processing method, which mainly describes an implementation manner of determining a target robot based on first input information, as shown in fig. 2, the method includes the following steps:
step 201: receiving first input information of a user in an intelligent dialogue system;
step 202: sending the first input information to a plurality of robots;
the electronic device may communicate with the plurality of robots to send the first input information to the plurality of robots. Specifically, the electronic device may provide an open interface through which the robot may register on the electronic device, thereby enabling the electronic device to communicate with the registered plurality of robots.
In this embodiment, optionally, in order to prevent the privacy information of the user from being leaked, before the first input information is sent to the multiple robots, whether the first input information includes sensitive information may be detected, and if it is determined that the first input information includes the sensitive information, desensitization processing is performed on the first input information, that is, the sensitive information in the first input information is replaced with general information corresponding to the sensitive information, so that the desensitized first input information is sent to the multiple robots.
The sensitive information may include various private information such as user personal information, device information used, etc. If the first input information contains Zhang III, the Zhang III can be replaced by general information 'some' because Zhang III is the personal information of the user.
In this embodiment, optionally, in order to ensure that the plurality of robots can improve the recognition rate of the first input information after receiving the desensitization-processed first input information, the electronic device may further label the sensitive information type of the general information in the desensitization-processed first input information, and then send the general information to the plurality of robots.
For example, after "zhang san" is replaced with "something", a replacement name may be marked after something, and the concrete expression may be "something (for replacing a name)". Of course, this is merely a simple example, and the present application does not limit the specific labeling.
Step 203: receiving a plurality of first response messages fed back by the plurality of robots.
Specifically, after receiving the first input information, the robot generates first response information matched with the first input information, and determines a matching degree parameter of the first response information corresponding to the first input information, where the matching degree parameter may be specifically characterized as a matching degree, a matching grade, a matching score, or the like.
Wherein, the matching degree can be characterized by high, medium and low, and the higher the degree is, the higher the matching degree is. The matching grade can be characterized by first grade, second grade, third grade and the like, and the higher grade represents the higher matching degree. The matching score can be characterized numerically, e.g., 90 points, 80 points, etc., with higher scores representing higher degrees of matching.
In order to facilitate information identification, optionally, in this embodiment, the first input information sent to the multiple robots may carry information such as a session time and a session turn, and the multiple first response information fed back by the multiple robots may also carry information such as a response time and a session turn.
Step 204: determining that the robot which sends the matching degree parameter carried in the first response information meets a first preset condition is a target robot;
the first preset condition is used for screening out first response information with high matching degree from the plurality of first response information, so that the robot sending the screened first response information is determined as a target robot. Specifically, in one mode, the robot that can determine that the matching degree parameter carried in the sent first response information satisfies the preset matching degree parameter is the target robot.
Taking the matching parameter as the matching degree as an example, the first response information with high matching degree can be determined, so that the robot sending the information is determined as the target robot. Taking the matching degree parameter as the matching score as an example, the first response information carrying the matching score larger than the preset score can be determined, so that the robot sending the information is determined as the target robot. Taking the matching parameter as the matching level as an example, the first response information carrying the matching level greater than the preset level can be determined, so that the robot transmitting the determined first response information is determined as the target robot.
In another mode, matching degree parameters such as matching degree, matching score or matching grade and the like can be sorted from high to low, so that one or the first N pieces of first response information with the matching degree, matching score or matching grade at the head is screened out, and the robot sending the screened first response information is determined to be the target robot.
It follows that the target robots identified in the present application can be one or more.
Wherein step 202-204 is a step of determining the specific implementation of the target robot based on the first input information.
Step 205: establishing an interaction between the user and the target robot in the intelligent dialog system.
In particular, a direct interaction of the user with the target robot may be established, i.e. the interaction of the user with the target robot may not be performed by the electronic device. Alternatively, an indirect interaction of the user with the target robot can also be established, i.e. the interaction of the user with the target robot is still performed by the electronic device.
Under the condition that the user establishes interaction with the target robot, the user can perform multi-round interaction with the target robot in the intelligent dialogue system, namely, the target robot can generate response information based on the input information of the user so as to realize multi-round interaction with the user.
A third method embodiment of the present application provides an information processing method, which mainly describes an implementation manner of determining a target robot based on first input information, as shown in fig. 3, the method includes the following steps:
step 301: receiving first input information of a user in an intelligent dialogue system;
step 302: sending the first input information to a plurality of robots;
the electronic device may communicate with the plurality of robots to send the first input information to the plurality of robots. Specifically, the electronic device may provide an open interface, and the robot may register on the electronic device, thereby enabling the electronic device to communicate with the registered plurality of robots.
In this embodiment, optionally, in order to prevent the privacy information of the user from being leaked, before the first input information is sent to the multiple robots, whether the first input information includes sensitive information may be detected, and if it is determined that the first input information includes the sensitive information, desensitization processing is performed on the first input information, that is, the sensitive information in the first input information is replaced with general information corresponding to the sensitive information, so that the desensitized first input information is sent to the multiple robots.
The sensitive information may include various private information such as user personal information, device information used, etc. If the first input information contains Zhang III, the Zhang III can be replaced by general information 'some' because Zhang III is the personal information of the user.
In this embodiment, optionally, in order to ensure that the plurality of robots can improve the recognition rate of the first input information after receiving the desensitization-processed first input information, the electronic device may further label the sensitive information type of the general information in the desensitization-processed first input information, and then send the general information to the plurality of robots.
For example, after "zhang san" is replaced with "something", a replacement name may be marked after something, and the concrete expression may be "something (for replacing a name)". Of course, this is merely a simple example, and the present application does not limit the specific labeling.
Step 303: receiving a plurality of first response messages fed back by the plurality of robots;
specifically, after receiving the first input information, the robot generates first response information matched with the first input information, so that the first response information is sent to the electronic device.
Step 304: matching the plurality of first response information with preset dimensional characteristics respectively to determine matching degree parameters;
after receiving the first response information fed back by the robots, the electronic device may match the first response information with preset dimensional characteristics, and determine a matching degree parameter of each first response information.
In this embodiment, the preset dimensional characteristics may include: one or more of historical chat frequency, robot score, content richness, historical user satisfaction, and the like.
Wherein, the historical chat frequency can be characterized as the chat times of the robot with the user in the historical record. The robot score may be characterized as a score for the robot by the historical user. The historical user satisfaction may be characterized as the satisfaction of the historical user with the robot.
The electronic device can perform matching weighting on each piece of first response information and at least one dimension characteristic, so as to determine a matching degree parameter. The matching degree parameter may be specifically characterized as a matching degree or a matching grade or a matching score, etc.
Wherein, the matching degree can be characterized by high, medium and low, and the higher the degree is, the higher the matching degree is. The matching grade can be characterized by first grade, second grade, third grade and the like, and the higher grade represents the higher matching degree. The matching score can be characterized numerically, e.g., 90 points, 80 points, etc., with higher scores representing higher degrees of matching.
In order to facilitate information identification of the electronic device, optionally, in this embodiment, the first input information sent to the multiple robots may carry information such as session time and session turn, and the multiple first response information fed back by the multiple robots may also carry information such as response time and session turn.
Step 305: screening the robot which sends the first response information and has the matching degree parameter meeting a first preset condition as a target robot;
the first preset condition is used for screening out first response information with high matching degree from the plurality of first response information, so that the robot sending the screened first response information is determined as a target robot. Specifically, in one mode, the robot that can determine that the matching degree parameter carried in the sent first response information satisfies the preset matching degree parameter is the target robot.
Taking the matching parameter as the matching degree as an example, the first response information with high matching degree can be determined, so that the robot sending the information is determined as the target robot. Taking the matching degree parameter as the matching score as an example, the first response information carrying the matching score larger than the preset score can be determined, so that the robot sending the information is determined as the target robot. Taking the matching parameter as the matching level as an example, the first response information carrying the matching level greater than the preset level can be determined, so that the robot transmitting the determined first response information is determined as the target robot.
In another mode, matching degree parameters such as matching degree, matching score or matching grade and the like can be sorted from high to low, one or the first N pieces of first response information with the matching degree, matching score or matching grade at the head is screened out, and therefore the robot sending the screened first response information is determined to be the target robot.
That is, the target robot determined in the present application may be one or more.
Wherein steps 302-305 are steps of determining a specific implementation of the target robot based on the first input information.
Step 306: establishing an interaction between the user and the target robot in the intelligent dialog system.
In particular, a direct interaction of the user with the target robot may be established, i.e. the interaction of the user with the target robot may not be performed by the electronic device. Alternatively, an indirect interaction of the user with the target robot can also be established, i.e. the interaction of the user with the target robot is still performed by the electronic device.
Under the condition that the user establishes interaction with the target robot, the user can perform multi-round interaction with the target robot, namely, the target robot can generate response information based on input information of the user so as to realize multi-round interaction with the user.
Optionally, in the second method embodiment and the third method embodiment, sending the first input information to the plurality of robots may include:
(1) determining a robot type based on the first input information;
in the present application, robot types of a plurality of robots communicating with an electronic device are various. Among other things, the robot type may be characterized as one or more of an avatar characteristic of the robot, a speaking style of the robot, a field of expertise of the robot, a language in which the robot is used, and the like. The first input information can determine which type of robot the user of the first input information is suitable for, and specifically, the type of robot can be determined by the expression form of the first input information, the content of the first input information, and the language of the first input information.
The image characteristics of the robot are used for representing the image of the robot and can comprise various image characteristics such as cartoons, girls, boys and the like. The adept field of the robot refers to the field of electronic equipment, the living field and the like, which is suitable for answering the questions of which field. The speech style of the robot is an expression form of response information generated for the robot. The robot uses a language that is a language for input information that the robot can understand or for response information that is generated.
For example, if the first input information is information on a problem of a mobile phone, it is possible to determine a robot which is good in the field of electronic devices.
(2) And sending the first input information to a plurality of robots with the robot types.
When the robot type is determined, the targeted transmission can be carried out, namely, the first input information is transmitted to a plurality of robots with the robot type, so that the first response information fed back by the robots of the type is received, the target robot is further determined, the user friendliness can be improved, and the communication efficiency is improved.
In the present application, the target robot may include one or more. When the target robot is one, an interaction between the user and one of the target robots may be established, and if the interaction is a direct interaction of the user and the target robot, the target robot may directly output the first response information in the intelligent dialogue system, and if the interaction is an indirect interaction of the user and the target robot, the electronic device may output the first response information in the intelligent dialogue system.
When the target robot includes at least two, the fourth embodiment of the present invention further provides an information processing method, as shown in fig. 4, including the steps of:
step 401: receiving first input information of a user in an intelligent dialogue system;
step 402: determining a target robot based on the first input information;
in this embodiment, the number of target robots is 2 or more.
Step 403: establishing an interaction between the user and the target robot in the intelligent dialog system;
wherein an indirect interaction of the user with the at least two target robots can be established via the electronic device.
Step 404: outputting first response information of the at least two target robots;
the first response information is information for responding the first input information; the electronic device outputs the determined first response information fed back by all the target robots.
Step 405: acquiring second input information of the user;
step 406: determining a first target robot among the at least two target robots based on the second input information;
after seeing the first response information, the user generally inputs second input information in the intelligent dialogue system, so that the first target robot with the maximum relevance with the second input information can be determined.
It should be noted that, since the first response information of the plurality of target robots is different, it is possible to determine that the target robot transmitting the corresponding first response information is determined to be the first target robot by determining which first response information the second input information of the user is feedback information about or with which first response information is most related.
Step 407: maintaining the user's interaction with the first target robot, canceling the user's interaction with other target robots than the first target robot.
Specifically, the electronic device may continue to maintain the user's interaction with the first target robot at the distance, or the electronic device may switch the interaction of the user with the first target robot at the distance to the direct interaction of the user with the first target robot.
In this embodiment, when the number of the determined target robots is plural, the final first target robot can be determined based on the second input information of the user, so that the interaction between the user and the first target robot is maintained, and the interaction between the user and the other target robots except the first target robot is cancelled.
In an information processing method provided by the present application, after establishing the interaction between the user and a target robot or between the user and a first target robot, optionally, the method may further include: and adjusting the target robot based on the input information of the user to obtain the target robot which is more in line with the current requirements of the user. In particular, the adjustment may be similar to the way described above for the target robot. It should be noted that the electronic device may mask the perception of the user of the adjustment of the target robot, or may notify the user that the adjustment of the target robot is performed.
Corresponding to the information processing method, the embodiment of the apparatus of the present application further provides an electronic device, which is described below with several embodiments of the apparatus.
An embodiment of a first apparatus of the present application provides an electronic device, as shown in fig. 5, an electronic device 100 may include: a first interface 110, a processor 120. Wherein:
a first interface 110 for receiving first input information of a user in the intelligent dialog system;
the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user, and particularly, the multiple rounds of interaction with the user can be completed by the target robot determined subsequently.
A processor 120 for determining a target robot based on the first input information, establishing an interaction between the user and the target robot in the intelligent dialog system; the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user.
In particular, the processor 120 may establish direct interaction of the user with the target robot, i.e. the interaction of the user with the target robot may not be performed by the electronic device. Alternatively, the processor 120 may also establish an indirect interaction of the user with the target robot, i.e. the interaction of the user with the target robot is still performed by the electronic device.
Under the condition that the user establishes interaction with the target robot, the user can perform multi-round interaction with the target robot, namely, the target robot can generate response information based on input information of the user so as to realize multi-round interaction with the user. It should be noted that the multiple rounds of interaction may be performed in a conversation window, and specifically, may be communicated in a text or voice manner.
In summary, in the embodiment, the interaction between the user and the target robot is established in the intelligent dialogue system by receiving the first input information of the user in the intelligent dialogue system, determining the target robot based on the first input information, wherein the intelligent dialogue system can generate response information based on the input information to realize multiple rounds of interaction with the user; it can be seen from this that, in the present application, the target robot interacting with the user can be matched based on the first input information of the user, that is, the target robot is assigned to the user specifically, thereby improving the accuracy of solving the problem for the user.
In the second apparatus embodiment of the present application, the electronic device may further include a second interface, and the processor determines the target robot based on the first input information, including:
(1) sending the first input information to a plurality of robots through a second interface;
specifically, the second interface may be an open interface, and the robot may register on the electronic device through the second interface, so that the processor can communicate with the registered plurality of robots.
In this embodiment, optionally, in order to prevent the privacy information of the user from being leaked, before the first input information is sent to the multiple robots, the processor may detect whether the first input information includes sensitive information, and if it is determined that the first input information includes the sensitive information, perform desensitization processing on the first input information, that is, replace the sensitive information in the first input information with general information corresponding to the sensitive information, so as to send the desensitized first input information to the multiple robots.
The sensitive information may include various private information such as user personal information, device information used, etc. If the first input information contains Zhang III, the Zhang III can be replaced by general information 'some' because Zhang III is the personal information of the user.
In this embodiment, optionally, in order to ensure that the plurality of robots can improve the recognition rate of the first input information after receiving the desensitization-processed first input information, the processor may further label the sensitive information type of the general information in the desensitization-processed first input information, and then send the general information to the plurality of robots.
(2) Receiving a plurality of pieces of first response information fed back by the plurality of robots through a second interface, wherein the first response information carries a matching degree parameter for responding to the input information;
specifically, after receiving the first input information, the robot generates first response information matched with the first input information, and determines a matching degree parameter of the first response information corresponding to the first input information, where the matching degree parameter may be specifically characterized as a matching degree, a matching grade, a matching score, or the like.
Wherein, the matching degree can be characterized by high, medium and low, and the higher the degree is, the higher the matching degree is. The matching grade can be characterized by first grade, second grade, third grade and the like, and the higher grade represents the higher matching degree. The matching score can be characterized numerically, e.g., 90 points, 80 points, etc., with higher scores representing higher degrees of matching.
In order to facilitate information identification, optionally, in this embodiment, the first input information sent by the processor to the multiple robots may carry information such as session time and session turn, and the multiple first response information fed back by the multiple robots may also carry information such as response time and session turn.
(2) And determining that the robot which sends the matching degree parameter carried in the first response information meets a first preset condition is a target robot.
The first preset condition is used for screening out first response information with high matching degree from the plurality of first response information, so that the robot sending the screened first response information is determined as a target robot. Specifically, in one mode, the processor may determine that the matching degree parameter carried in the sent first response information satisfies the preset matching degree parameter, and the robot is the target robot.
Taking the matching parameter as the matching degree as an example, the first response information with high matching degree can be determined, so that the robot sending the information is determined as the target robot. Taking the matching degree parameter as the matching score as an example, the first response information carrying the matching score larger than the preset score can be determined, so that the robot sending the information is determined as the target robot. Taking the matching parameter as the matching level as an example, the first response information carrying the matching level greater than the preset level can be determined, so that the robot transmitting the determined first response information is determined as the target robot.
In another mode, the processor may sort the matching degree parameters such as the matching degree, the matching score, or the matching grade from high to low, screen out one or the first N pieces of first response information with the matching degree, the matching score, or the matching grade at the head, and determine the robot sending the screened first response information as the target robot.
It can be seen that the target robots determined by the processor can be one or more.
In the third apparatus embodiment of the present application, the electronic device may further include a second interface, and the processor may determine the target robot based on the first input information, and may include:
(1) sending the first input information to a plurality of robots through a second interface;
specifically, the second interface may be an open interface, and the robot may register on the electronic device through the second interface, so that the processor can communicate with the registered plurality of robots.
In this embodiment, optionally, in order to prevent the privacy information of the user from being leaked, before the first input information is sent to the multiple robots, the processor may detect whether the first input information includes sensitive information, and if it is determined that the first input information includes the sensitive information, perform desensitization processing on the first input information, that is, replace the sensitive information in the first input information with general information corresponding to the sensitive information, so as to send the desensitized first input information to the multiple robots.
The sensitive information may include various private information such as user personal information, device information used, etc. If the first input information contains Zhang III, the Zhang III can be replaced by general information 'some' because Zhang III is the personal information of the user.
In this embodiment, optionally, in order to ensure that the plurality of robots can improve the recognition rate of the first input information after receiving the desensitization-processed first input information, the processor may further label the sensitive information type of the general information in the desensitization-processed first input information, and then send the general information to the plurality of robots.
(2) Receiving a plurality of first response messages fed back by the plurality of robots through a second interface;
specifically, after receiving the first input information, the robot generates first response information matched with the first input information, so that the first response information is sent to the electronic device.
(3) Matching the plurality of first response information with preset dimensional characteristics respectively to determine matching degree parameters;
after receiving the first response information fed back by the robots, the electronic device may match the first response information with preset dimensional characteristics, and determine a matching degree parameter of each first response information.
In this embodiment, the preset dimensional characteristics may include: one or more of historical chat frequency, robot score, content richness, historical user satisfaction, and the like.
Wherein, the historical chat frequency can be characterized as the chat times of the robot with the user in the historical record. The robot score may be characterized as a score for the robot by the historical user. The historical user satisfaction may be characterized as the satisfaction of the historical user with the robot.
The electronic device can perform matching weighting on each piece of first response information and at least one dimension characteristic, so as to determine a matching degree parameter. The matching degree parameter may be specifically characterized as a matching degree or a matching grade or a matching score, etc.
Wherein, the matching degree can be characterized by high, medium and low, and the higher the degree is, the higher the matching degree is. The matching grade can be characterized by first grade, second grade, third grade and the like, and the higher grade represents the higher matching degree. The matching score can be characterized numerically, e.g., 90 points, 80 points, etc., with higher scores representing higher degrees of matching.
In order to facilitate information identification of the electronic device, optionally, in this embodiment, the first input information sent by the processor to the multiple robots through the second interface may carry information such as session time and session turn, and the multiple first response information fed back by the multiple robots may also carry information such as response time and session turn.
(4) And screening the robot which sends the first response information and meets the first preset condition as the target robot.
The first preset condition is used for screening out first response information with high matching degree from the plurality of first response information, so that the robot sending the screened first response information is determined as a target robot. Specifically, in one mode, the processor may determine that the matching degree parameter carried in the sent first response information satisfies the preset matching degree parameter, and the robot is the target robot.
Taking the matching parameter as the matching degree as an example, the first response information with high matching degree can be determined, so that the robot sending the information is determined as the target robot. Taking the matching degree parameter as the matching score as an example, the first response information carrying the matching score larger than the preset score can be determined, so that the robot sending the information is determined as the target robot. Taking the matching parameter as the matching level as an example, the first response information carrying the matching level greater than the preset level can be determined, so that the robot transmitting the determined first response information is determined as the target robot.
In another mode, the processor may sort the matching degree parameters such as the matching degree, the matching score, or the matching grade from high to low, and screen out one or the first N pieces of first response information with the matching degree, the matching score, or the matching grade at the head, so as to determine the robot sending the screened first response information as the target robot.
That is, the target robot determined in the present application may be one or more.
In an embodiment of the fourth apparatus of the present application, the sending, by the processor, the first input information to a plurality of robots through a second interface includes:
(1) determining a robot type based on the first input information;
in the present application, robot types of a plurality of robots communicating with an electronic device are various. Among other things, the robot type may be characterized as one or more of an avatar characteristic of the robot, a speaking style of the robot, a field of expertise of the robot, a language in which the robot is used, and the like. The processor can determine which type of robot the user of the first input information is suitable for through the first input information, and specifically, the type of robot can be determined through the expression form of the first input information, the content of the first input information and the language of the first input information.
The image characteristics of the robot are used for representing the image of the robot and can comprise various image characteristics such as cartoons, girls, boys and the like. The adept field of the robot refers to the field of electronic equipment, the living field and the like, which is suitable for answering the questions of which field. The speech style of the robot is an expression form of response information generated for the robot. The robot uses a language that is a language for input information that the robot can understand or for response information that is generated.
(2) And sending the first input information to a plurality of robots with the robot types through a second interface.
When the robot type is determined, the targeted transmission can be carried out, namely, the first input information is transmitted to a plurality of robots with the robot type, so that the first response information fed back by the robots of the type is received, the target robot is further determined, the user friendliness can be improved, and the communication efficiency is improved.
In the present application, the target robot may include one or more. When the target robot is one, the processor may establish an interaction between the user and the one target robot, and if the interaction is a direct interaction of the user and the target robot, the target robot may directly output the first response information in the intelligent dialogue system, and if the interaction is an indirect interaction of the user and the target robot, the processor may output the first response information in the intelligent dialogue system.
In a fifth apparatus embodiment of the present application, when the target robots include at least two, the processor is further configured to output first response information of the at least two target robots, obtain second input information of the user, determine a first target robot among the at least two target robots based on the second input information, maintain the interaction of the user with the first target robot, and cancel the interaction of the user with other target robots than the first target robot.
The first response information is information responding to the first input information, and the processor can output the determined first response information fed back by all target robots.
After seeing the first response information, the user generally inputs second input information in the intelligent dialogue system, so that the first target robot with the maximum relevance of the second input information can be determined.
It should be noted that, since the first response information of the plurality of target robots is different, it is possible to determine that the target robot transmitting the corresponding first response information is determined to be the first target robot by determining which first response information the second input information of the user is feedback information about or with which first response information is most related.
Specifically, the processor may continue to maintain the spaced interaction of the user with the first target robot, or the processor may switch the spaced interaction of the user with the first target robot to a direct interaction of the user with the first target robot.
In this embodiment, when the number of the determined target robots is plural, the final first target robot can be determined based on the second input information of the user, so that the interaction between the user and the first target robot is maintained, and the interaction between the user and the other target robots except the first target robot is cancelled.
In this application, the treater is after establishing the interaction of user and a target robot, perhaps establishes the interaction of user and a first target robot, and is optional, and the treater can also adjust the target robot based on user's input information to the adjustment is the target robot that accords with user's current demand more. In particular, the adjustment may be similar to the way described above for the target robot. It should be noted that the processor may mask the perception of the user of the adjustment of the target robot, or may inform the user that the adjustment of the target robot was made.
An embodiment of the sixth apparatus of the present application further provides an information processing system, as shown in fig. 6, the information processing system may include: the electronic device 100 and the robot 200 specifically include: robot 2001, robot 2002 …, and robot 200 n. n is 2 or more.
The electronic apparatus 100 includes: a first interface 110, a processor 120; wherein:
a first interface 110 for receiving first input information of a user in the intelligent dialog system;
a processor 120 for determining a target robot among a plurality of robots based on the first input information, an interaction between the user and the target robot being established in the intelligent dialogue system; the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user.
It is understood that the specific implementation form of the electronic device can participate in the foregoing embodiments related to the electronic device, and will not be described in detail herein.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An information processing method comprising:
receiving first input information of a user in an intelligent dialogue system;
determining a target robot based on the first input information;
establishing an interaction between the user and the target robot in the intelligent dialog system; the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user.
2. The method of claim 1, the determining a target robot based on the first input information, comprising:
sending the first input information to a plurality of robots;
receiving a plurality of pieces of first response information fed back by the plurality of robots, wherein the first response information carries a matching degree parameter for responding to the first input information;
and determining that the robot which sends the matching degree parameter carried in the first response information meets a first preset condition is a target robot.
3. The method of claim 1, the determining a target robot based on the first input information, comprising:
sending the first input information to a plurality of robots;
receiving a plurality of first response messages fed back by the plurality of robots;
matching the plurality of first response information with preset dimensional characteristics respectively to determine matching degree parameters;
and screening the robot which sends the first response information and meets the first preset condition as the target robot.
4. The method of claim 2 or 3, the sending the first input information into a plurality of robots, comprising:
determining a robot type based on the first input information;
and sending the first input information to a plurality of robots with the robot types.
5. The method of claim 1, the target robot comprising at least two target robots, the method further comprising:
outputting first response information of the at least two target robots, wherein the first response information is information responding to the first input information;
acquiring second input information of the user;
determining a first target robot among the at least two target robots based on the second input information;
maintaining the user's interaction with the first target robot, canceling the user's interaction with other target robots than the first target robot.
6. An electronic device, comprising:
a first interface for receiving first input information of a user in an intelligent dialog system;
a processor for determining a target robot based on the first input information, establishing an interaction between the user and the target robot in the intelligent dialog system; the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user.
7. The electronic device of claim 6, further comprising:
a second interface;
the processor determines a target robot based on the first input information, comprising:
sending the first input information to a plurality of robots through the second interface;
receiving a plurality of pieces of first response information fed back by the plurality of robots through the second interface, wherein the first response information carries a matching degree parameter for responding the input information;
and determining that the robot which sends the matching degree parameter carried in the first response information meets a first preset condition is a target robot.
8. The electronic device of claim 6, further comprising:
a second interface;
the processor determines a target robot based on the first input information, comprising:
sending the first input information to a plurality of robots through the second interface;
receiving a plurality of first response messages fed back by the plurality of robots through the second interface;
matching the plurality of first response information with preset dimensional characteristics respectively to determine matching degree parameters;
and screening the robot which sends the first response information and meets the first preset condition as the target robot.
9. The electronic device of claim 7 or 8, the processor sending the first input information into a plurality of robots through the second interface, comprising:
determining a robot type based on the first input information;
and sending the first input information to a plurality of robots with the robot types through the second interface.
10. An information processing system comprising:
a plurality of robots;
an electronic device in communication with the plurality of robots, the electronic device comprising:
a first interface for receiving first input information of a user in an intelligent dialog system;
a processor for determining a target robot among the plurality of robots based on the first input information, establishing an interaction between the user and the target robot in the intelligent dialog system; the intelligent dialogue system can generate response information based on input information to realize multiple rounds of interaction with the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424359.0A CN111191019A (en) | 2019-12-31 | 2019-12-31 | Information processing method, electronic equipment and information processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424359.0A CN111191019A (en) | 2019-12-31 | 2019-12-31 | Information processing method, electronic equipment and information processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111191019A true CN111191019A (en) | 2020-05-22 |
Family
ID=70708095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911424359.0A Pending CN111191019A (en) | 2019-12-31 | 2019-12-31 | Information processing method, electronic equipment and information processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111191019A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966795A (en) * | 2020-06-29 | 2020-11-20 | 出门问问信息科技有限公司 | Intelligent control method, central control equipment and storage medium |
| CN113894783A (en) * | 2021-10-12 | 2022-01-07 | 北京声智科技有限公司 | Interaction method, device and equipment of robot and computer readable storage medium |
| CN111966795B (en) * | 2020-06-29 | 2024-05-17 | 出门问问信息科技有限公司 | Intelligent control method, central control equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160358240A1 (en) * | 2015-06-08 | 2016-12-08 | IntelliResponse Systems, Inc. | Method and apparatus for facilitating comprehension of user queries during interactions |
| CN106233378A (en) * | 2014-05-13 | 2016-12-14 | 夏普株式会社 | Control device and message output control system |
| CN106528692A (en) * | 2016-10-31 | 2017-03-22 | 北京百度网讯科技有限公司 | Dialogue control method and device based on artificial intelligence |
| CN107135143A (en) * | 2017-03-27 | 2017-09-05 | 厦门快商通科技股份有限公司 | Many chat robots switching systems and its dialogue method |
| CN108000526A (en) * | 2017-11-21 | 2018-05-08 | 北京光年无限科技有限公司 | Dialogue exchange method and system for intelligent robot |
| CN108319599A (en) * | 2017-01-17 | 2018-07-24 | 华为技术有限公司 | A kind of interactive method and apparatus |
-
2019
- 2019-12-31 CN CN201911424359.0A patent/CN111191019A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106233378A (en) * | 2014-05-13 | 2016-12-14 | 夏普株式会社 | Control device and message output control system |
| US20160358240A1 (en) * | 2015-06-08 | 2016-12-08 | IntelliResponse Systems, Inc. | Method and apparatus for facilitating comprehension of user queries during interactions |
| CN106528692A (en) * | 2016-10-31 | 2017-03-22 | 北京百度网讯科技有限公司 | Dialogue control method and device based on artificial intelligence |
| CN108319599A (en) * | 2017-01-17 | 2018-07-24 | 华为技术有限公司 | A kind of interactive method and apparatus |
| CN107135143A (en) * | 2017-03-27 | 2017-09-05 | 厦门快商通科技股份有限公司 | Many chat robots switching systems and its dialogue method |
| CN108000526A (en) * | 2017-11-21 | 2018-05-08 | 北京光年无限科技有限公司 | Dialogue exchange method and system for intelligent robot |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966795A (en) * | 2020-06-29 | 2020-11-20 | 出门问问信息科技有限公司 | Intelligent control method, central control equipment and storage medium |
| CN111966795B (en) * | 2020-06-29 | 2024-05-17 | 出门问问信息科技有限公司 | Intelligent control method, central control equipment and storage medium |
| CN113894783A (en) * | 2021-10-12 | 2022-01-07 | 北京声智科技有限公司 | Interaction method, device and equipment of robot and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102138156B (en) | Persisting a group in an instant messaging application | |
| CN107040450B (en) | Automatic reply method and device | |
| CN112838978B (en) | System and method for real-time short message robot supporting man-machine cooperation | |
| CN109245990B (en) | Message display method, device, terminal and storage medium | |
| CN109547332B (en) | Communication session interaction method and device, and computer equipment | |
| CN104065564B (en) | A kind of method and device for question and answer | |
| CN110347863B (en) | Speaking recommendation method and device and storage medium | |
| CN107995370B (en) | Call control method, device, storage medium and mobile terminal | |
| CN106202308A (en) | A kind of method of Information Sharing and electronic equipment | |
| CN105827501A (en) | Message reminding method and electronic equipment | |
| US20130124631A1 (en) | Apparatus, system, and method for digital communications driven by behavior profiles of participants | |
| CN108173835B (en) | Verification method, device, server and terminal | |
| CN113810265A (en) | System and method for indicating and measuring responses in a multi-channel contact center | |
| CN112383667A (en) | Call data processing method, device, equipment and storage medium | |
| CN111611365A (en) | Flow control method, device, equipment and storage medium of dialog system | |
| CN111191019A (en) | Information processing method, electronic equipment and information processing system | |
| CN111554280A (en) | Real-time interpretation service system for mixing interpretation contents using artificial intelligence and interpretation contents of interpretation experts | |
| US20150304381A1 (en) | Apparatus, system, and method for digital communications driven by behavior profiles of participants | |
| CN105100435A (en) | Application method and device of mobile communication | |
| CN116431316B (en) | Task processing method, system, platform and automatic question-answering method | |
| CN105827517B (en) | A kind of method and device that social activity group is added | |
| CN110336740B (en) | Equipment management method, server and system | |
| CN111883098B (en) | Speech processing method and device, computer readable storage medium and electronic device | |
| CN111400475A (en) | Information processing method and device and electronic equipment | |
| CN112969000A (en) | Control method and device of network conference, electronic equipment and storage medium |
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 |