CN111614845A - Human-computer dialogue human-set matching method and device, computer equipment and storage medium - Google Patents
Human-computer dialogue human-set matching method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111614845A CN111614845A CN202010315517.5A CN202010315517A CN111614845A CN 111614845 A CN111614845 A CN 111614845A CN 202010315517 A CN202010315517 A CN 202010315517A CN 111614845 A CN111614845 A CN 111614845A
- Authority
- CN
- China
- Prior art keywords
- information
- target user
- robot
- user
- 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.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Manipulator (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application relates to a man-machine interaction man-set matching method, a man-machine interaction man-set matching device, a computer device and a storage medium, wherein the man-machine interaction man-set matching method comprises the steps of acquiring combination information of telephone scene information to be interacted and feature information of a target user, matching target robot set information corresponding to the combination information in a preset robot database comprising corresponding relations between the combination information of various telephone scene information and the feature information of the user and different robot set information, and then interacting with the target user according to the target robot set information. According to the method, different robot devices are used for communicating with corresponding users, and the appropriate robot devices can be matched for human-computer interaction, so that the human-computer interaction flexibility is improved.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a human-computer interaction matching method and apparatus, a computer device, and a storage medium.
Background
With the development of artificial intelligence technology, intelligent robots have been applied to various fields, for example, various types of services such as automatic customer service, intelligent marketing, content navigation, intelligent voice control, entertainment chat, and the like are provided in various fields such as telecom operators, financial services, e-government affairs, e-commerce, various intelligent terminals, and personal internet information services.
When a telephone robot communicates with a person in an existing telephone scene, the setting of the person of the telephone robot is not changed, and is always fixed according to the difference of the gender, age and scene of the user, for example, the sound of a mature female is taken as the sound of the telephone robot all the time, and the user requirements cannot be well met.
Therefore, in the conventional telephone scene, there is a problem that the setting of the character of the telephone robot is not flexible enough.
Disclosure of Invention
In view of the above, it is desirable to provide a human-machine interaction human setting matching method, apparatus, computer device, and storage medium capable of improving flexibility of human setting of a telephone robot.
In a first aspect, the present application provides a method for matching a person in a human-computer conversation, including:
acquiring the combined information of the telephone scene information to be conversed and the characteristic information of the target user;
matching target robot setting information corresponding to the combined information in a preset robot database; the robot database comprises the corresponding relation between the combination information of various telephone scene information and the characteristic information of the user and different robot setting information;
and carrying out dialogue with a target user according to the target robot setting information.
In one embodiment, if the target user is an old user; acquiring the combined information of the telephone scene information to be conversed and the characteristic information of the target user, wherein the combined information comprises the following steps:
searching the characteristic information of the target user in a user information storage database according to the communication number of the target user; and determining the telephone scene information according to whether the conversation request and/or the voice information of the target user is actively sent to the target user.
In one embodiment, if the target user is a new user; acquiring the combined information of the telephone scene information to be conversed and the characteristic information of the target user, wherein the combined information comprises the following steps:
collecting and confirming the age and the gender of a target user by a voiceprint recognition technology, wherein the age and the gender of the target user are used for representing the characteristic information of the target user; and determining the telephone scene information according to whether the conversation request and/or the voice information of the target user is actively sent to the target user.
In one embodiment, the target person setting information includes speaking attitude, tone, speed and volume of the telephone robot;
then, the above-mentioned dialogue with the target user according to the target robot setting information includes:
determining real-time characteristic information of a target user according to the voice information of the target user; the real-time characteristic information represents the emotion of a target user in the current conversation telephone scene;
switching attitudes, tone, speed and volume in the target robot setting information in real time according to the real-time characteristic information of the target user;
and carrying out conversation with the target user according to the switched robot setting information.
In one embodiment, after the session with the target user is ended, the method further includes:
acquiring dialog information of a target user and feedback opinions of the target user;
and updating the characteristic information of the target user in the robot database according to the dialog information of the target user and the feedback opinions of the target user.
In one embodiment, the building process of the robot database includes:
acquiring sample combinations of various telephone scene information and user characteristic information and sample setting information of a telephone robot corresponding to each sample combination;
and learning the corresponding relation between the sample combination of each piece of telephone scene information and user characteristic information and the sample human setting information of the telephone robot through a deep learning algorithm to obtain a robot database.
In one embodiment, the telephone scene information includes a notification type return visit scene and a customer service scene for processing a problem; the robot setting information corresponding to the notification type revisit scene comprises a steady character and a neutral attitude; the robot setting information corresponding to the customer service scene for processing the problems comprises friendly attitude and lively character.
In a second aspect, the present application provides a matching device for human equipment in human-computer conversation, the device comprising:
the information acquisition module is used for acquiring the combined information of the telephone scene information to be conversed and the characteristic information of the target user;
the robot matching module is used for matching target robot setting information corresponding to the combined information in a preset robot database; the robot database comprises the corresponding relation between the combination information of various telephone scene information and the characteristic information of the user and different robot setting information;
and the man-machine conversation module is used for carrying out conversation with a target user according to the target robot setting information.
In a third aspect, the present application provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of the method according to any one of the embodiments of the first aspect when executing the computer program.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of any of the embodiments of the first aspect described above.
The application provides a man-machine interaction man-set matching method, a man-machine interaction device, a computer device and a storage medium, through acquiring combination information of telephone scene information to be interacted and feature information of a target user, matching target robot set information corresponding to the combination information in a preset robot database comprising corresponding relations between the combination information of various telephone scene information and the feature information of the user and different robot set information, and then interacting with the target user according to the target robot set information. In the method, the robot database is constructed in advance according to the corresponding relation between the combination information of different telephone scene information and user characteristic information and different robot setting information, which is equivalent to the communication between different man-machine conversation scenes and different user characteristics and corresponding users by using different robot settings to match appropriate robot settings for man-machine interaction, so that the man-machine interaction flexibility is improved, and further, the service satisfaction and the service resolution can be improved.
Drawings
FIG. 1 is a diagram of an application environment of a matching method for human-machine interaction according to an embodiment;
FIG. 1a is a diagram illustrating an internal structure of a phone robot according to an exemplary embodiment;
FIG. 2 is a flowchart illustrating a method for matching a profile in a human-machine conversation according to an embodiment;
FIG. 3 is a flowchart illustrating a method for matching a profile in a human-computer conversation according to another embodiment;
FIG. 4 is a flowchart illustrating a method for matching a profile in a human-computer conversation according to another embodiment;
FIG. 5 is a flowchart illustrating a method for matching a profile in a human-computer conversation according to another embodiment;
FIG. 6 is a diagram illustrating a human-machine interaction matching method, according to an embodiment;
FIG. 7 is a block diagram of an apparatus for matching a profile in a human-machine dialog according to an embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, the present application provides an application environment of a human-computer interaction method, where a telephone robot 01 may perform voice interaction with a user, and the interaction scenario includes, but is not limited to, service scenarios such as online question answering, consultation, and instruction execution. The telephone robot 01 includes, but is not limited to, a calling robot, a chat robot, an intelligent customer service, an intelligent assistant, and other robots of various service types. The internal structure of the telephone robot can be seen in fig. 1a, and the telephone robot comprises a processor, a memory, a network interface and a database which are connected through a system bus. Wherein the processor is configured to provide computational and control capabilities. The memory comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database is used for storing data of a human-computer conversation human-set matching method. The network interface is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of matching a person in a human-computer conversation. It is to be understood that the internal structure of the telephone robot shown in fig. 1a is only an example and is not intended to be limiting.
The embodiment of the application provides a person setting matching method and device in man-machine conversation, computer equipment and a storage medium, so that the person setting of a telephone robot in a telephone scene is more flexible. The following describes in detail the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems by embodiments and with reference to the drawings. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. In the method for matching human equipment in a human-computer conversation provided by the present application, the main implementation bodies in fig. 2 to 6 are telephone robots. The executing main bodies in fig. 2 to fig. 6 may also be a human device matching device, and the device may be implemented as part or all of a telephone robot by software, hardware, or a combination of software and hardware.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments.
In an embodiment, fig. 2 provides a method for matching a personal setting in a man-machine conversation, where the embodiment relates to a specific process that a telephone robot matches corresponding personal setting information according to combined information of a current telephone scene and feature information of a target user during the man-machine conversation, and performs a conversation with the target user based on the matched personal setting information, as shown in fig. 2, the method includes:
s101, acquiring the combined information of the telephone scene information to be conversed and the feature information of the target user.
The phone scene information to be conversed is determined according to the specific conversation content when the current phone robot makes a call with the target user, for example, the phone scene information is a notification type return visit scene, or a customer service scene for receiving an incoming call of the target user and handling a problem, and the phone scene information is not limited in this embodiment. The characteristic information of the target user refers to information that may represent a personal characteristic of the user, including but not limited to the age, sex, character, habit, etc. of the user, which is not limited herein.
The combination information of the phone scene information and the feature information of the target user may be only the phone scene information to be currently conversed, or only the feature information of the target user, or a mixture of the two. When the telephone robot acquires the combination information of the telephone scene information to be conversed and the feature information of the target user, the contents in the information can be acquired according to the actual situation. For example, a telephone scene is determined according to the intention of calling a target user or the speaking content of the target user after the call is received; and determining the characteristic information of the target user according to the tone, the speech speed, the tone and the like of the speaking of the target user.
It can be understood that there is no sequential limitation when the telephone robot acquires the combined information, that is, after the telephone scene information and the target user feature information are respectively acquired according to the information in the current man-machine conversation scene, all the acquired information is determined as the combined information.
S102, matching target robot set information corresponding to the combined information in a preset robot database; the robot database includes the corresponding relation between the combination information of various telephone scene information and the characteristic information of the user and different robot setting information.
After the combined information of the telephone scene information and the characteristic information of the target user is obtained, the telephone robot matches the target robot setting information corresponding to the combined information in a preset robot database according to the combined information.
The target robot setting information refers to target person setting information matched from a preset robot database, the person setting information refers to set sex, character, speech speed, emotion and other information of the robot, and the person setting information can be constructed into robots with various personality. For example, the age groups in the robot setting information include young males, old females, young females, and the like; the character includes lively, enthusiasm, friendly, steady, neutral, etc.; the speech rate includes fast, slow, medium, etc.
The robot database is pre-constructed, and the robot database includes a large amount of combination information of the telephone scene information and the user characteristic information and corresponding relations between different robot setting information, for example, if the acquired combination information is a notification return visit, and the target user is a young male, and the character is more stable, then the matched robot setting information is a young female, the character is slightly lively, and the sound is clear. Therefore, the telephone robot can match corresponding robot setting information from the robot database according to the acquired combination information, and finally match target robot setting information which is most suitable for the combination information.
And S103, carrying out conversation with the target user according to the target robot setting information.
After the target robot setting information is matched in the above step S102, the telephone robot performs a dialogue with the target user using the target robot setting information.
For example, if the target robot sets the information as female youth, neutral attitude, medium speech rate, and sweet tone, the telephone robot uses the voice of the female sweet tone to keep the neutral attitude, and talk with the target user at the medium speech rate.
In the man-machine interaction man-set matching method provided by the embodiment, the combined information of the phone scene information to be interacted and the feature information of the target user is obtained, the target robot set information corresponding to the combined information is matched in the preset robot database comprising the corresponding relations between the combined information comprising various phone scene information and the feature information of the user and different robot set information, and then conversation is carried out with the target user according to the target robot set information. In the method, the robot database is constructed in advance according to the corresponding relation between the combination information of different telephone scene information and user characteristic information and different robot setting information, so that different robot settings are used for communicating with corresponding users to match with the appropriate robot settings for human-computer interaction, the human-computer interaction flexibility is improved, and further, the service satisfaction and the service resolution can be improved.
In the above embodiment, when the telephone robot acquires the combination information of the telephone scene information to be spoken and the feature information of the target user, it may acquire the combination information in different manners according to different situations, and the target user includes an old user and a new user as an example. In one embodiment, the target user is an old user, and the step S101 includes: searching the characteristic information of the target user in a user information storage database according to the communication number of the target user; and determining the telephone scene information according to whether the conversation request and/or the voice information of the target user is actively sent to the target user.
In the case that the target user is an old user, the feature information of the target user is stored in the user information storage database in advance, and of course, if only a part of the target user is known in the historical interaction, the stored user feature information may only include the part of the target user. In some scenarios, the user information storage database storing the user feature information stores a large amount of user feature information indexed by the user identifier, such as the communication number of the user, or other information, and when the application is performed, the telephone robot searches the user information storage database for the feature information of the target user according to the communication number of the target user.
When the phone scene information is determined, the phone robot can judge whether the man-machine conversation is actively initiated to the target user or not, if the man-machine conversation is actively initiated to the target user, namely the call-out scene is the call-out scene, the phone scene information can be determined according to the purpose of initiating the man-machine conversation, for example, the purpose of initiating the man-machine conversation to the target user is to return visit, and the phone scene information can be determined to be a return visit survey scene. If the call is a call incoming scene, the telephone robot can determine the call scene according to the voice information of the target user, namely according to the speaking content of the target user, for example, after the target user calls the call, the intention of inquiring some services can be actively explained, and then the telephone robot can be determined as a customer service scene for processing the problem.
In another embodiment, the target user is a new user; the step S101 includes: collecting and confirming the age and the gender of a target user by a voiceprint recognition technology, wherein the age and the gender of the target user are used for representing the characteristic information of the target user; and determining the telephone scene information according to whether the conversation request and/or the voice information of the target user is actively sent to the target user.
In the case that the target user is a new user, the telephone robot may collect the voice of the target user at the beginning of the conversation with the target user, and then identify the basic information of the user through the voice, for example, identify the information such as age and sex of the voice through the voiceprint identification technology.
In this embodiment, the telephone robot determines that the telephone scene information is the same as that of the target user who is an old user, and reference may be made to the description of the target user who is an old user, which is not described herein again.
In the embodiment, when the combined information of the telephone scene information to be conversed and the feature information of the target user is acquired, the target user is divided into two situations of an old user and a new user, so that the combined information is acquired in different modes according to different situations, the acquired combined information is closer to the actual situation of the target user, and the accuracy of the combined information is ensured.
Different phone scene information may correspond to different robot setting information, and the following description is provided by an embodiment. In one embodiment, the telephone scene information comprises a notification type return visit scene and a customer service scene for processing problems; the robot setting information corresponding to the notification type revisit scene comprises a steady character and a neutral attitude; the robot setting information corresponding to the customer service scene for processing the problems comprises friendly attitude and lively character.
The call scene information is a notification return visit, and neutral attitude and stable character can be adopted in the notification return visit. Specifically, the notification type return visit may be an outbound scene, and then before the outbound call, the list of users to be dialed is cleaned, screened, and classified. The calling-out can be carried out by using the telephone robot arranged by the same person for the users of the same type, such as young males, old females, young females and the like. And different types of clients are interacted by using the telephone robots respectively corresponding to the users, for example, the female young uses the robot with the normal speech rate of the female young for interaction, and the female old client uses the robot with the slower speech rate of the female old for communication interaction. Therefore, appropriate robot setting information is adopted to communicate with the user according to the specific type pertinence of the user, and a better human-computer interaction effect can be achieved.
And the method can select the lively character and friendly attitude for the customer service scene of the problem of processing the received telephone. Specifically, the customer service scenario of the call answering problem is an incoming call scenario, and for the incoming call scenario, when an incoming call of a user is received, feature information stored by the user, such as the age, the region, the character, the gender, the source channel of the user, and the like of the user, can be determined in advance according to the communication number of the user, so that the user is classified and is subjected to a conversation with a corresponding robot device. For example, if the target user is a young male client visiting through a microblog, a robot of a young female who likes to use a network hotword may be used to perform a conversation with the target user, so that a human-computer interaction effect is improved, and the satisfaction degree of the service is improved.
In the man-machine conversation scene, the emotion fluctuation of the user can be caused by the conversation content, and in order to enable the users under different emotions to obtain better service, the man-machine information of the telephone robot can be switched according to the actual emotion of the user in the man-machine conversation process. As shown in fig. 3, in an embodiment, the step S103 includes:
s201, determining real-time characteristic information of a target user according to voice information of the target user; the real-time characteristic information represents the emotion of the target user in the telephone scene of the current conversation.
The method comprises the steps that a telephone robot monitors voice information of a target user in real time in a conversation process with the user, for example, information which can reflect emotion of a speaker, such as semantics, attitude, speech speed and tone of the voice information is monitored, and real-time characteristic information of the target user is determined according to the information, namely emotion of the target user in a current conversation telephone scene is determined, for example, the attitude is medium, the speech speed and the tone are moderate, and the emotion of the target user is normal.
S202, switching attitudes, tone, speed and volume in the target robot setting information in real time according to the real-time characteristic information of the target user.
And S203, carrying out conversation with the target user according to the switched robot setting information.
Based on the determined real-time characteristic information of the target user, the telephone robot switches the current robot setting information, and takes the target person setting information including the speaking attitude, tone, speed and volume of the telephone robot as an example, the telephone robot switches the current robot attitude, tone, speed and volume and carries out conversation with the target user by the switched human setting information.
For example, the real-time characteristic information of the target user indicates that the current emotion of the target user is not good, the posture of people switched by the telephone robot needs to be enthusiasm, the voice is gentle, the voice speed is kept medium, and the volume is also switched to be gentle, so that when the conversation is carried out with the target user, the emotion of the target user can be pacified, the service quality is improved, and the service problem solving rate can be improved to a certain extent.
In order to improve the accuracy of the characteristic information of the user stored in the robot database, the attribute characteristic information of the user can be updated according to the result and the satisfaction degree of each man-machine interaction session. Then, as shown in fig. 4, in one embodiment, the method further comprises:
s301, obtaining the dialog information of the target user and the feedback opinions of the target user.
After each man-machine conversation, the telephone robot may analyze information of the current conversation with the target user, for example, analyze the service consulted by the current target user, analyze new personal information (for example, age, sex, character) provided by the current target user, and so on, so as to obtain new feature information of the target user from the conversation information of the target user.
And after each time of the man-machine conversation, receiving feedback opinions of the target user, such as suggestions provided by the target user for the man-machine conversation, satisfaction degree and the like.
And S302, updating the characteristic information of the target user in the robot database according to the dialog information of the target user and the feedback opinions of the target user.
According to the acquired dialog information of the target user and the feedback opinions of the target user, the feature information of the target user in the robot database is updated, so that after the feature information of the target user is updated, on one hand, the accuracy of the feature information of the target user can be guaranteed, on the other hand, the matched robot setting information is the most suitable for the target user when the next man-machine dialog is carried out, and therefore the man-machine interaction quality is improved.
In addition, the present application further provides an embodiment of a process for constructing a robot database, as shown in fig. 5, the process for constructing a robot database includes:
s401, obtaining sample combinations of various telephone scene information and user characteristic information and sample human setting information of the telephone robot corresponding to each sample combination.
In the step, a large number of diversified samples need to be obtained initially in order to ensure that data in a robot database is accurate and rich, so that sample combinations of various telephone scene information and user characteristic information and sample human setting information of the telephone robot corresponding to each sample combination need to be obtained first in the step.
S402, learning the corresponding relation between the sample combination of the telephone scene information and the user characteristic information and the sample human setting information of the telephone robot through a deep learning algorithm to obtain a robot database.
After a large amount of sample information is obtained, the corresponding relation between the sample combination of each piece of telephone scene information and user characteristic information in the sample and the sample human setting information of the telephone robot can be learned through a deep learning algorithm, and a robot database is established based on the learning result, so that the obtained robot database comprises the corresponding relation between a large amount of combination information of the telephone scene information and the user characteristic information and the robot setting information. Therefore, the robot device of the more appropriate user can be matched from the robot database for man-machine conversation subsequently, the flexibility of the man-machine conversation is improved, and the service quality is also ensured.
In addition, the present application also provides a method for matching a person in a human-computer conversation, as shown in fig. 6, the embodiment includes:
s1, constructing a robot database;
s2, acquiring the combined information of the telephone scene information to be conversed and the characteristic information of the target user;
s3, matching target robot setting information corresponding to the combined information in a robot database;
s4, carrying out dialogue with the target user according to the target robot setting information;
s5, determining real-time characteristic information of the target user according to the voice information of the target user;
s6, switching attitudes, tone, speech speed and volume in the target robot setting information in real time according to the real-time characteristic information of the target user;
s7, carrying out dialogue with the target user according to the switched robot setting information;
s8, acquiring dialog information of the target user and feedback opinions of the target user;
and S9, updating the characteristic information of the target user in the robot database according to the dialog information of the target user and the feedback opinions of the target user.
The implementation principle and technical effect of the steps in the human-computer matching method in all human-computer conversations provided in the above embodiment are similar to those in the previous embodiments of the human-computer matching method in all human-computer conversations, and are not described herein again.
It should be understood that although the various steps in the flow charts of fig. 2-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-6 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 7, there is provided a human-machine interaction human-device matching device, comprising: information acquisition module 10, people set matching module 11 and man-machine dialogue module 12, wherein:
the information acquisition module 10 is used for acquiring the combined information of the telephone scene information to be conversed and the feature information of the target user;
the human setting matching module 11 is used for matching target robot setting information corresponding to the combined information in a preset robot database; the robot database comprises the corresponding relation between the combination information of various telephone scene information and the characteristic information of the user and different robot setting information;
and the man-machine conversation module 12 is used for carrying out conversation with a target user according to the target robot setting information.
In one embodiment, if the target user is an old user; the information obtaining module 10 is specifically configured to search the feature information of the target user in the user information storage database according to the communication number of the target user; and determining the telephone scene information according to whether the conversation request and/or the voice information of the target user is actively sent to the target user.
In one embodiment, if the target user is a new user; the information obtaining module 10 is specifically configured to collect and confirm the age and gender of the target user through a voiceprint recognition technology, where the age and gender of the target user are used to represent feature information of the target user; and determining the telephone scene information according to whether the conversation request and/or the voice information of the target user is actively sent to the target user.
In one embodiment, the human-machine dialog module 12 comprises:
the characteristic information determining unit is used for determining the real-time characteristic information of the target user according to the voice information of the target user; the real-time characteristic information represents the emotion of a target user in the current conversation telephone scene;
the switching personnel setting unit is used for switching attitudes, tone, speed and volume in the target robot setting information in real time according to the real-time characteristic information of the target user;
and the man-machine conversation unit is used for carrying out conversation with the target user according to the switched robot setting information.
In one embodiment, the apparatus further comprises:
the data acquisition module is used for acquiring the dialogue information of the target user and the feedback opinions of the target user;
and the updating module is used for updating the characteristic information of the target user in the robot database according to the dialogue information of the target user and the feedback opinions of the target user.
In one embodiment, the apparatus further comprises:
the system comprises a sample acquisition module, a data processing module and a data processing module, wherein the sample acquisition module is used for acquiring sample combinations of various telephone scene information and user characteristic information and sample setting information of a telephone robot corresponding to each sample combination;
and the database construction module is used for learning the corresponding relation between the sample combination of the telephone scene information and the user characteristic information and the sample human setting information of the telephone robot through a deep learning algorithm to obtain the robot database.
In one embodiment, the telephone scene information comprises a notification type return visit scene and a customer service scene for processing problems; the robot setting information corresponding to the notification type revisit scene comprises a steady character and a neutral attitude; the robot setting information corresponding to the customer service scene for processing the problems comprises friendly attitude and lively character.
The implementation principle and technical effect of the human-machine matching device in all human-machine conversations provided by the above embodiment are similar to those of the human-machine matching method in the above human-machine conversation, and are not described herein again.
For the specific definition of the human-computer interaction matching device, reference may be made to the above definition of the human-computer interaction matching method, which is not described herein again. All or part of each module in the human-computer interaction human-set matching device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of matching a person in a human-computer conversation. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring the combined information of the telephone scene information to be conversed and the characteristic information of the target user;
matching target robot setting information corresponding to the combined information in a preset robot database; the robot database comprises the corresponding relation between the combination information of various telephone scene information and the characteristic information of the user and different robot setting information;
and carrying out dialogue with a target user according to the target robot setting information.
The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring the combined information of the telephone scene information to be conversed and the characteristic information of the target user;
matching target robot setting information corresponding to the combined information in a preset robot database; the robot database comprises the corresponding relation between the combination information of various telephone scene information and the characteristic information of the user and different robot setting information;
and carrying out dialogue with a target user according to the target robot setting information.
The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for matching human equipment in man-machine conversation, which is characterized by comprising the following steps:
acquiring the combined information of the telephone scene information to be conversed and the characteristic information of the target user;
matching target robot setting information corresponding to the combined information in a preset robot database; the robot database comprises the corresponding relation between the combination information of various telephone scene information and the characteristic information of the user and different robot setting information;
and carrying out conversation with the target user according to the target robot setting information.
2. The method of claim 1, wherein if the target user is an old user; the acquiring of the combined information of the phone scene information to be conversed and the feature information of the target user comprises the following steps:
searching the characteristic information of the target user in a user information storage database according to the communication number of the target user; and determining the telephone scene information according to whether a conversation request and/or the voice information of the target user is actively sent to the target user.
3. The method of claim 1, wherein if the target user is a new user; the acquiring of the combined information of the phone scene information to be conversed and the feature information of the target user comprises the following steps:
collecting and confirming the age and the gender of the target user through a voiceprint recognition technology, wherein the age and the gender of the target user are used for representing the characteristic information of the target user; and determining the telephone scene information according to whether a conversation request and/or the voice information of the target user is actively sent to the target user.
4. The method according to any one of claims 1-3, wherein the target human-set information includes attitude, tone, speed, volume of speech of the telepresence robot;
the setting information according to the target robot, and the dialogue with the target user, including:
determining real-time characteristic information of the target user according to the voice information of the target user; the real-time characteristic information represents the emotion of the target user in the current conversation telephone scene;
switching attitudes, tone, speed and volume in the target robot setting information in real time according to the real-time characteristic information of the target user;
and carrying out conversation with the target user according to the switched robot setting information.
5. The method of claim 4, wherein after the end of the session with the target user, the method further comprises:
acquiring dialog information of the target user and a feedback opinion of the target user;
and updating the characteristic information of the target user in the robot database according to the dialog information of the target user and the feedback opinions of the target user.
6. A method according to any of claims 1-3, characterized in that the building process of the robot database comprises:
acquiring sample combinations of various telephone scene information and user characteristic information and sample setting information of a telephone robot corresponding to each sample combination;
and learning the corresponding relation between each sample combination of the telephone scene information and the user characteristic information and the sample human setting information of the telephone robot through a deep learning algorithm to obtain the robot database.
7. The method of any of claims 1-3, wherein the phone scenario information includes notification-like revisit scenarios and customer service scenarios to handle questions;
the robot setting information corresponding to the notification type revisit scene comprises a steady character and a neutral attitude; the robot setting information corresponding to the customer service scene for processing the problems comprises friendly attitude and lively character.
8. A device for matching a person in a man-machine conversation, said device comprising:
the information acquisition module is used for acquiring the combined information of the telephone scene information to be conversed and the characteristic information of the target user;
the human setting matching module is used for matching target robot setting information corresponding to the combined information in a preset robot database; the robot database comprises the corresponding relation between the combination information of various telephone scene information and the characteristic information of the user and different robot setting information;
and the man-machine conversation module is used for carrying out conversation with the target user according to the target robot setting information.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010315517.5A CN111614845A (en) | 2020-04-21 | 2020-04-21 | Human-computer dialogue human-set matching method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010315517.5A CN111614845A (en) | 2020-04-21 | 2020-04-21 | Human-computer dialogue human-set matching method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111614845A true CN111614845A (en) | 2020-09-01 |
Family
ID=72200101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010315517.5A Pending CN111614845A (en) | 2020-04-21 | 2020-04-21 | Human-computer dialogue human-set matching method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111614845A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112201222A (en) * | 2020-12-03 | 2021-01-08 | 深圳追一科技有限公司 | Voice interaction method, device, equipment and storage medium based on voice call |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102238262A (en) * | 2010-04-20 | 2011-11-09 | 上海博路信息技术有限公司 | Individual auto-answer audio system of mobile phone |
| CN107580153A (en) * | 2017-09-20 | 2018-01-12 | 携程旅游网络技术（上海）有限公司 | Trunk convergence method, system, equipment and the storage medium of call center |
| CN109274843A (en) * | 2018-09-19 | 2019-01-25 | 平安科技（深圳）有限公司 | Key prediction technique, device and computer readable storage medium |
| CN109451188A (en) * | 2018-11-29 | 2019-03-08 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of the self-service response of otherness |
| CN110232573A (en) * | 2018-03-06 | 2019-09-13 | 广州供电局有限公司 | Based on interactive intelligent response system |
-
2020
- 2020-04-21 CN CN202010315517.5A patent/CN111614845A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102238262A (en) * | 2010-04-20 | 2011-11-09 | 上海博路信息技术有限公司 | Individual auto-answer audio system of mobile phone |
| CN107580153A (en) * | 2017-09-20 | 2018-01-12 | 携程旅游网络技术（上海）有限公司 | Trunk convergence method, system, equipment and the storage medium of call center |
| CN110232573A (en) * | 2018-03-06 | 2019-09-13 | 广州供电局有限公司 | Based on interactive intelligent response system |
| CN109274843A (en) * | 2018-09-19 | 2019-01-25 | 平安科技（深圳）有限公司 | Key prediction technique, device and computer readable storage medium |
| CN109451188A (en) * | 2018-11-29 | 2019-03-08 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of the self-service response of otherness |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112201222A (en) * | 2020-12-03 | 2021-01-08 | 深圳追一科技有限公司 | Voice interaction method, device, equipment and storage medium based on voice call |
| CN112201222B (en) * | 2020-12-03 | 2021-04-06 | 深圳追一科技有限公司 | Voice interaction method, device, equipment and storage medium based on voice call |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101932876B1 (en) | Intelligent automated agent for a contact center | |
| CN111105782B (en) | Session interaction processing method and device, computer equipment and storage medium | |
| US10171659B2 (en) | Customer portal of an intelligent automated agent for a contact center | |
| CN105592237B (en) | A kind of method, apparatus and intelligent customer service robot of session switching | |
| CN110347863B (en) | Speaking recommendation method and device and storage medium | |
| US20190065498A1 (en) | System and method for rich conversation in artificial intelligence | |
| CN113868404A (en) | Multi-robot conversation management method, device, equipment and medium | |
| CN112383667A (en) | Call data processing method, device, equipment and storage medium | |
| CN111614845A (en) | Human-computer dialogue human-set matching method and device, computer equipment and storage medium | |
| CN114203173A (en) | Method and device for robot to reserve client, computer equipment and storage medium | |
| CN113539261A (en) | Man-machine voice interaction method and device, computer equipment and storage medium | |
| CN113724036A (en) | Method and electronic equipment for providing question consultation service | |
| CN115083412B (en) | Voice interaction method and related device, electronic equipment and storage medium | |
| CN108182942B (en) | Method and device for supporting interaction of different virtual roles | |
| EP4093005A1 (en) | System method and apparatus for combining words and behaviors | |
| CN114969299A (en) | Conversation management method and device, computer equipment and storage medium | |
| CN114222029A (en) | Intelligent customer service call method and device, computer equipment and storage medium | |
| KR20060117860A (en) | Method and system of providing conversational agent service using images | |
| CN111639167A (en) | Task conversation method and device | |
| CN111125321A (en) | Question answering method, device, terminal equipment and storage medium | |
| KR20070018388A (en) | Method and system of providing conversational agent service using images | |
| CN113282708B (en) | Method and device for replying to robot dialog, computer equipment and storage medium | |
| JP2018190070A (en) | Interaction support method, device and program | |
| CN112839137A (en) | Call processing method, device, equipment and storage medium based on background environment | |
| CN117834783A (en) | Telephone outbound method, device, 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200901 |