CN115757748B - Method and device for controlling conversation with robot, computer equipment and storage medium - Google Patents
Method and device for controlling conversation with robot, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115757748B CN115757748B CN202211668382.6A CN202211668382A CN115757748B CN 115757748 B CN115757748 B CN 115757748B CN 202211668382 A CN202211668382 A CN 202211668382A CN 115757748 B CN115757748 B CN 115757748B
- Authority
- CN
- China
- Prior art keywords
- dialogue
- user
- robot
- round
- response
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000004044 response Effects 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 18
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 241001465754 Metazoa Species 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 241000282326 Felis catus Species 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Toys (AREA)
- Manipulator (AREA)
Abstract
The invention relates to a method, a device, a computer device and a storage medium for controlling conversation with a robot, wherein the method comprises the following steps: acquiring information input by a user and transmitting the information input by the user to a robot; selecting one or more robots to answer according to the dialogue control logic, and transmitting information input by a user to a dialogue model corresponding to the robots; and obtaining a result returned by the dialogue model and feeding back the result to the user. According to the invention, one or more robots are selected to answer according to the dialogue control logic, the information input by the user is transmitted to the dialogue model, and then the result returned by the dialogue model is fed back to the user, so that the continuity between each round of dialogue is enhanced, the dialogue round can be accurately controlled, and the method is applied to complex scenes.
Description
Technical Field
The invention relates to the technical field of conversation with a robot, in particular to a conversation control method and device with the robot, computer equipment and a storage medium.
Background
The dialogue system is a computer system for simulating human-to-human communication, and the AI dialogue robot is designed by constructing a dialogue model so as to realize dialogue interaction between the computer and the human. Dialog systems have been widely used in various applications or smart devices to provide flexible ways of communication between people and machines. The existing dialogue system basically only comprises an AI robot, one-to-one interaction is carried out between a user and the robot, most of dialogue is initiated by the user, after the dialogue system receives information input of the user, the input is analyzed through a natural language processing model, then a reply is obtained through a searching or generating mode, and finally the reply is returned to the user. As the application of the dialogue system continues to be deep, the application scene becomes complex, and the conventional one-to-one interaction mode of the single AI robot cannot meet the specific application requirement.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method and a device for controlling conversation with a robot, computer equipment and a storage medium.
In order to solve the technical problems, the invention adopts the following technical scheme:
in a first aspect, the present embodiment provides a method for controlling a session with a robot, including the following steps:
acquiring information input by a user and transmitting the information input by the user to a robot;
selecting one or more robots to answer according to the dialogue control logic, and transmitting information input by a user to a dialogue model corresponding to the robots;
And obtaining a result returned by the dialogue model and feeding back the result to the user.
The further technical scheme is as follows: before the step of acquiring the information input by the user and transmitting the information input by the user to the robot, the method further comprises the steps of: and starting a dialogue service, acquiring user login information, establishing dialogue connection, and distributing a unique session ID for the user.
The further technical scheme is as follows: the step of starting the dialogue service, obtaining the login information of the user, establishing dialogue connection and distributing unique dialogue ID for the user comprises the following steps: the AI robot is added and a dialogue model is accessed.
The further technical scheme is as follows: the robot has unique attributes including nickname, age, gender, character animation pictures, or hobbies.
In a second aspect, the present embodiment provides a conversation control apparatus with a robot, including: the device comprises an acquisition and transmission unit, a selected transmission unit and an acquisition and feedback unit;
the acquisition and transmission unit is used for acquiring information input by a user and transmitting the information input by the user to the robot;
The selected transmitting unit is used for selecting one or more robots to answer according to the dialogue control logic and transmitting information input by a user to a dialogue model corresponding to the robots;
And the acquisition feedback unit is used for acquiring a result returned by the dialogue model and feeding the result back to the user.
The further technical scheme is as follows: the apparatus further comprises: and the starting acquisition and establishment distribution unit is used for starting dialogue service, acquiring user login information, establishing dialogue connection and distributing unique session ID for the user.
The further technical scheme is as follows: the apparatus further comprises: and the adding access unit is used for adding the AI robot and accessing the dialogue model.
The further technical scheme is as follows: the robot has unique attributes including nickname, age, gender, character animation pictures, or hobbies.
In a third aspect, the present embodiment provides a computer device, where the computer device includes a memory and a processor, where the memory stores a computer program, and the processor implements the method for controlling a session with a robot as described above when executing the computer program.
In a fourth aspect, the present embodiment provides a storage medium storing a computer program comprising program instructions which, when executed by a processor, implement a method of controlling a robot dialog as described above.
Compared with the prior art, the invention has the beneficial effects that: the method and the device select one or more robots to answer according to the dialogue control logic, transfer information input by a user to the dialogue model, and feed back results returned by the dialogue model to the user, so that continuity between each round of dialogue is enhanced, the dialogue rounds can be accurately controlled, and the method and the device are applied to complex scenes.
The invention is further described below with reference to the drawings and specific embodiments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for controlling a conversation with a robot according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of a robot conversation control apparatus provided by an embodiment of the present invention;
fig. 3 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to the embodiment shown in fig. 1, the invention discloses a method for controlling a conversation with a robot, which comprises the following steps:
s1, acquiring information input by a user, and sending the information input by the user to a robot;
Specifically, the information input by the user includes text, voice, picture, video, and other different data formats.
In one embodiment, before step S1, the method further includes: and starting a dialogue service, acquiring user login information, establishing dialogue connection, and distributing a unique session ID for the user.
Specifically, the user login information includes an account number and a password, and the account number and the password need to be bound with user identity card information and a mobile phone number. And after the account number and the password pass verification, establishing dialogue connection.
Specifically, the dialogue service is started, after the user logs in the dialogue system, the dialogue system establishes connection with the AI robot at the server, each user is allocated with a global unique dialogue ID, the unique dialogue ID is bound with the URL of the dialogue chat request, the URL is stored in the dialogue record of the user, and if the user accidentally exits the dialogue system, the user can enter the dialogue flow through the URL in the dialogue record, and the last dialogue is continued.
In one embodiment, the unique session ID is unique and is generated by the dialog system after the user logs in, including the user name, login date, random code, and the like. Specifically, the random code is 4 characters or 6 characters, and has timeliness, typically 60 seconds.
Specifically, the dialog system contains at least two AI robots (but not limited to two) and one user. Each AI robot is accessed into different dialogue models to play different roles respectively, and can communicate with users in many-to-one mode.
In an embodiment, before the step of starting the session service, obtaining the login information of the user, establishing the session connection, and assigning a unique session ID to the user, the method further includes: the AI robot is added and a dialogue model is accessed.
Specifically, the websocket is an existing technology widely applied to network communication through a websocket access dialogue model. The dialogue model is a data model trained by using a deep learning method and has dialogue capability, for example, a sentence is input into the dialogue model, the dialogue model gives a reply, and the dialogue model can be regarded as a person only receiving and outputting text.
Specifically, the system administrator adds AI robots to the dialogue system, and then accesses a dialogue model for each AI robot according to the AI robots of the dialogue scene, where each AI robot has its own unique attribute, including but not limited to one or more of the following: nicknames, ages, sexes, character animation pictures, hobbies, etc. The AI robots in the dialogue system are classified into an intention recognition robot and a dialogue robot, and in this embodiment, a more specific dialogue scene is that a user uses the dialogue system to conduct dialogue classroom teaching, and a system administrator manages and creates two AI robots: the teacher robot small T and the classmate robot small C respectively correspond to different dialogue models.
In an embodiment, the system administrator may further manage the AI robots in the dialogue system according to the requirements, including adding or deleting AI robots to the dialogue system, and accessing a dialogue model for each AI robot, where the dialogue model can generate a corresponding reply according to the response content of the user.
In one embodiment, the user enters dialog content in a dialog interaction page. If the dialogue content is a text message, directly transmitting the dialogue content to a message server, and then transmitting the dialogue content to dialogue control logic for processing; if the dialogue content is voice message, converting voice into text message through voice-text conversion, then transmitting the text message to the message server, and then delivering to dialogue control logic for processing.
S2, selecting one or more robots to answer according to the dialogue control logic, and transmitting information input by a user to a dialogue model corresponding to the robots;
Specifically, the dialog control logic refers to that the dialog flow in the dialog system is controlled based on dialog turns, the dialog content of a specific application scene is decomposed into multiple rounds of dialogs, each round of dialogs is denoted as D, for the ith round of dialog D i, a Question Q i (Question), a target intention I i (Intent) and a Response R i (Response), namely D i＝{Qi,Ii,Ri }, Q is proposed by the robot, and the Response of the user is R. The response states of the user are classified into three types: correct response, incorrect response, and no response.
Correct response: extracting a target intention from the response of the user, and the additional dialog turns are correct;
Error response: the user responded, but not correctly;
no response: the user does not respond for a certain time, which is preconfigured at the start of the dialog service.
S3, obtaining a result returned by the dialogue model and feeding the result back to the user.
Specifically, after text information of a user is input into a dialogue model corresponding to the AI robot, the dialogue model searches corresponding reply content from the inside of the dialogue model according to user intention information, and then the reply content is returned to the user in a text form, and meanwhile, voice-text conversion is called to convert the text into voice and is displayed in dialogue interaction. For example: the information input by the user is a favorite question about a certain animal, and then the information is input into a corresponding dialogue model (namely an animal dialogue model) of the AI robot, and then corresponding reply content (the favorite of the animal) is searched from the inside of the animal dialogue model, and is returned to the user in the form of text.
Specifically, the dialogue interactive presentation comprises text editing and sending, voice input and playing and dialogue chat content display.
In order to facilitate an understanding of the present invention, the following specific examples are now provided:
Firstly, the classroom dialogue content is decomposed into a plurality of rounds of dialogues, when a user enters a dialogue system to interact with a robot, the response R of the user needs to be added with a dialogue round, the dialogue round is initialized to be 1, and the dialogue round is shared by the whole dialogue. For example, the user just enters the dialogue system, and the robot small T initiates a dialogue, and the dialogue round is 1.
Robot small T: "what animals you like? ".
The goal in this problem is intended to be "favorite animals".
The user: "I like cat".
And splicing the response content of the user and the dialogue turn, namely, inputting 'I like cat & & 1' into intention recognition, wherein the intention recognition extracts that animal which contains target intention 'like' in the user reply is cat, and the dialogue turn is 1, so that the user reply is judged to be correct reply, then the response content of the user is respectively transmitted to different dialogue robots, and then the dialogue turn is added with 1 to be changed into 2.
The invention also deals with some special cases:
When the response of the user is an error response, the robot can conduct repeated questioning, in order to ensure the smooth progress of the dialogue, the repeated questioning cannot be conducted all the time, a threshold value of repeated questioning is set for each round of dialogue, the threshold value is recorded as TRQ (Thresholdofrepeatedquestions), the default TRQ of the dialogue system is set as 3, and when the number of times of repeated questioning exceeds the TRQ, the robot directly enters the next round of dialogue.
When the user does not respond for a long time, which is marked as WT (WaitTime waiting time), and the user does not respond beyond the WT time, the dialogue system gives a corresponding overtime prompt. Each session also sets a maximum waiting time, noted MWT (MaximumWaitTime), for the MWT to default to 30s in the system, which can be configured before the session system service is started; when the user does not respond beyond the MWT time, the dialogue system sends a prompt message to the user, gives a corresponding overtime prompt, adds 1 to the dialogue round, and the dialogue enters the next round.
According to the invention, one or more robots are selected to answer according to the dialogue control logic, the information input by the user is transmitted to the dialogue model, and then the result returned by the dialogue model is fed back to the user, so that the continuity between each round of dialogue is enhanced, the dialogue round can be accurately controlled, the method and the device are applied to complex scenes, and the situations of unresponsiveness, response errors and the like of the user can be processed, so that the range of application scenes is enlarged.
Referring to fig. 2, the invention also discloses a device for controlling the conversation with the robot, which comprises: an acquisition transmitting unit 10, a selected transfer unit 20, and an acquisition feedback unit 30;
the acquiring and transmitting unit 10 is configured to acquire information input by a user and transmit the information input by the user to the robot;
the selected transmitting unit 20 is configured to select one or more robots to answer according to the session control logic, and transmit information input by a user to a session model corresponding to the robot;
The feedback obtaining unit 30 is configured to obtain a result returned by the dialogue model and feed back the result to the user.
In an embodiment, the device further comprises: and the starting acquisition and establishment distribution unit is used for starting dialogue service, acquiring user login information, establishing dialogue connection and distributing unique session ID for the user.
In an embodiment, the device further comprises: and the adding access unit is used for adding the AI robot and accessing the dialogue model.
In one embodiment, the robot has unique attributes including nickname, age, gender, character animation picture, or hobbies.
It should be noted that, as those skilled in the art can clearly understand, the specific implementation process of the device and the units for controlling the session with the robot may refer to the corresponding descriptions in the foregoing method embodiments, and for convenience and brevity of description, the description is omitted here.
The robot dialog control device described above may be implemented in the form of a computer program which can be run on a computer device as shown in fig. 3.
Referring to fig. 3, fig. 3 is a schematic block diagram of a computer device according to an embodiment of the present application; the computer device 500 may be a terminal or a server, where the terminal may be an electronic device with a communication function, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster formed by a plurality of servers.
With reference to FIG. 3, the computer device 500 includes a processor 502, memory, and a network interface 505, connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a method of controlling a robot dialog.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the execution of a computer program 5032 in the non-volatile storage medium 503, which computer program 5032, when executed by the processor 502, causes the processor 502 to perform a method of controlling a robot dialog.
The network interface 505 is used for network communication with other devices. It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting of the computer device 500 to which the present inventive arrangements may be implemented, and that a particular computer device 500 may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
Wherein the processor 502 is configured to execute a computer program 5032 stored in a memory to implement the steps of:
Acquiring information input by a user and transmitting the information input by the user to a robot; selecting one or more robots to answer according to the dialogue control logic, and transmitting information input by a user to a dialogue model corresponding to the robots; and obtaining a result returned by the dialogue model and feeding back the result to the user.
In an embodiment, before the step of obtaining the information input by the user and sending the information input by the user to the robot, the method further includes: and starting a dialogue service, acquiring user login information, establishing dialogue connection, and distributing a unique session ID for the user.
In an embodiment, before the step of starting the session service, obtaining the login information of the user, establishing the session connection, and assigning a unique session ID to the user, the method further includes: the AI robot is added and a dialogue model is accessed.
In one embodiment, the robot has unique attributes including nickname, age, gender, character animation picture, or hobbies.
It should be appreciated that in an embodiment of the application, the processor 502 may be a Central processing unit (Central ProcessingUnit, CPU), and the processor 502 may also be other general purpose processors, digital signal processors (DigitalSignalProcessor, DSP), application specific integrated circuits (Application SpecificIntegratedCircuit, ASIC), off-the-shelf programmable gate arrays (Field-ProgrammableGateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Those skilled in the art will appreciate that all or part of the flow in a method embodying the above described embodiments may be accomplished by computer programs instructing the relevant hardware. The computer program comprises program instructions, and the computer program can be stored in a storage medium, which is a computer readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer readable storage medium. The storage medium stores a computer program, wherein the computer program comprises program instructions which, when executed by a processor, implement the robot dialog control method described above. The storage medium stores a computer program comprising program instructions which, when executed by a processor, implement the method described above. The program instructions include the steps of:
Acquiring information input by a user and transmitting the information input by the user to a robot; selecting one or more robots to answer according to the dialogue control logic, and transmitting information input by a user to a dialogue model corresponding to the robots; and obtaining a result returned by the dialogue model and feeding back the result to the user.
In an embodiment, before the step of obtaining the information input by the user and sending the information input by the user to the robot, the method further includes: and starting a dialogue service, acquiring user login information, establishing dialogue connection, and distributing a unique session ID for the user.
In an embodiment, before the step of starting the session service, obtaining the login information of the user, establishing the session connection, and assigning a unique session ID to the user, the method further includes: the AI robot is added and a dialogue model is accessed.
In one embodiment, the robot has unique attributes including nickname, age, gender, character animation picture, or hobbies.
The storage medium may be a U-disk, a removable hard disk, a Read-only memory (ROM), a magnetic disk, or an optical disk, or other various computer-readable storage media that may store program codes.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be combined, divided and deleted according to actual needs. In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The integrated unit may be stored in a storage medium if implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a terminal, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention.
The foregoing embodiments are preferred embodiments of the present invention, and in addition, the present invention may be implemented in other ways, and any obvious substitution is within the scope of the present invention without departing from the concept of the present invention.
Claims (6)
1. The conversation control method with the robot is characterized by comprising the following steps of:
acquiring information input by a user and transmitting the information input by the user to a robot;
selecting one or more robots to answer according to the dialogue control logic, and transmitting information input by a user to a dialogue model corresponding to the robots;
Obtaining a result returned by the dialogue model and feeding back the result to the user;
Before the step of acquiring the information input by the user and transmitting the information input by the user to the robot, the method further comprises the steps of: starting dialogue service, obtaining user login information, establishing dialogue connection, and distributing unique dialogue ID for user;
The step of starting the dialogue service, obtaining the login information of the user, establishing dialogue connection and distributing unique dialogue ID for the user comprises the following steps: adding an AI robot and accessing a dialogue model;
The user inputs dialogue content in dialogue interactive page, if dialogue content is text message, then transmits dialogue content to message server, then transmits dialogue control logic to process; if the dialogue content is voice message, converting voice into text message through voice-text conversion, then transmitting the text message to a message server, and then delivering to dialogue control logic for processing;
The dialogue control logic refers to that the dialogue flow in the dialogue system is controlled based on dialogue rounds, dialogue content of a specific application scene is decomposed into multiple rounds of dialogues, each round of dialogues is marked as D, for the ith round of dialogues D i, a problem Q i, a target intention I i and a reply R i, namely D i＝{Qi,Ii,Ri, Q is proposed by a robot, and the response of a user is R;
the response states of the user are classified into three types: correct response, incorrect response, and no response;
when the response of the user is an error response, the robot carries out repeated questioning, each round of dialogue is also provided with a threshold value of repeated questioning, the threshold value is recorded as TRQ, the default TRQ of the dialogue system is set as 3, and when the number of times of repeated questioning exceeds the TRQ, the robot directly enters the next round of dialogue;
When the user does not respond for a long time, the time records the waiting time, and when the user does not respond beyond the waiting time, the dialogue system gives out a corresponding overtime prompt; each round of dialogue also sets a maximum waiting time, and the maximum waiting time in the system is set to be 30s by default; when the user does not respond after exceeding the longest waiting time, the dialogue system sends out a prompt message to the user, gives out a corresponding overtime prompt, adds 1 to the dialogue round, and the dialogue enters the next round.
2. The conversation control method with robot of claim 1 wherein the robot has unique attributes including nickname, age, gender, character animation picture, or hobbies.
3. A conversation control apparatus with a robot, comprising: the device comprises an acquisition and transmission unit, a selected transmission unit and an acquisition and feedback unit;
the acquisition and transmission unit is used for acquiring information input by a user and transmitting the information input by the user to the robot;
The selected transmitting unit is used for selecting one or more robots to answer according to the dialogue control logic and transmitting information input by a user to a dialogue model corresponding to the robots;
the feedback acquisition unit is used for acquiring a result returned by the dialogue model and feeding the result back to the user;
The apparatus further comprises: the starting acquisition and establishment allocation unit is used for starting dialogue service, acquiring user login information, establishing dialogue connection and allocating unique session ID for users;
The apparatus further comprises: the adding access unit is used for adding the AI robot and accessing the dialogue model;
The user inputs dialogue content in dialogue interactive page, if dialogue content is text message, then transmits dialogue content to message server, then transmits dialogue control logic to process; if the dialogue content is voice message, converting voice into text message through voice-text conversion, then transmitting the text message to a message server, and then delivering to dialogue control logic for processing;
The dialogue control logic refers to that the dialogue flow in the dialogue system is controlled based on dialogue rounds, dialogue content of a specific application scene is decomposed into multiple rounds of dialogues, each round of dialogues is marked as D, for the ith round of dialogues D i, a problem Q i, a target intention I i and a reply R i, namely D i＝{Qi,Ii,Ri, Q is proposed by a robot, and the response of a user is R;
the response states of the user are classified into three types: correct response, incorrect response, and no response;
when the response of the user is an error response, the robot carries out repeated questioning, each round of dialogue is also provided with a threshold value of repeated questioning, the threshold value is recorded as TRQ, the default TRQ of the dialogue system is set as 3, and when the number of times of repeated questioning exceeds the TRQ, the robot directly enters the next round of dialogue;
When the user does not respond for a long time, the time records the waiting time, and when the user does not respond beyond the waiting time, the dialogue system gives out a corresponding overtime prompt; each round of dialogue also sets a maximum waiting time, and the maximum waiting time in the system is set to be 30s by default; when the user does not respond after exceeding the longest waiting time, the dialogue system sends out a prompt message to the user, gives out a corresponding overtime prompt, adds 1 to the dialogue round, and the dialogue enters the next round.
4. A conversation control apparatus with a robot as claimed in claim 3 wherein the robot has unique attributes including nickname, age, gender, character animation picture, or hobbies.
5. A computer device, characterized in that it comprises a memory and a processor, the memory having stored thereon a computer program, the processor implementing the robot dialog control method according to any of claims 1-2 when executing the computer program.
6. A storage medium storing a computer program comprising program instructions which, when executed by a processor, implement the method of robot dialog control as claimed in any of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211668382.6A CN115757748B (en) | 2022-12-23 | 2022-12-23 | Method and device for controlling conversation with robot, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211668382.6A CN115757748B (en) | 2022-12-23 | 2022-12-23 | Method and device for controlling conversation with robot, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115757748A CN115757748A (en) | 2023-03-07 |
| CN115757748B true CN115757748B (en) | 2024-06-25 |
Family
ID=85347377
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211668382.6A Active CN115757748B (en) | 2022-12-23 | 2022-12-23 | Method and device for controlling conversation with robot, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115757748B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975622A (en) * | 2016-05-28 | 2016-09-28 | 蔡宏铭 | Multi-role intelligent chatting method and system |
| CN112559701A (en) * | 2020-11-10 | 2021-03-26 | 联想(北京)有限公司 | Man-machine interaction method, device and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017173547A (en) * | 2016-03-23 | 2017-09-28 | カシオ計算機株式会社 | Robot control device, robot, robot control method, robot control system and program |
| CN110392168B (en) * | 2018-04-16 | 2021-06-01 | 华为技术有限公司 | Call processing method, device, server, storage medium and system |
| US20220358295A1 (en) * | 2021-05-10 | 2022-11-10 | Walden University, Llc | System and method for a cognitive conversation service |
-
2022
- 2022-12-23 CN CN202211668382.6A patent/CN115757748B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105975622A (en) * | 2016-05-28 | 2016-09-28 | 蔡宏铭 | Multi-role intelligent chatting method and system |
| CN112559701A (en) * | 2020-11-10 | 2021-03-26 | 联想(北京)有限公司 | Man-machine interaction method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115757748A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11128680B2 (en) | AI mediated conference monitoring and document generation | |
| US8374859B2 (en) | Automatic answering device, automatic answering system, conversation scenario editing device, conversation server, and automatic answering method | |
| CA2697858C (en) | Virtual pet chatting system, method and virtual pet questioning and answering server | |
| US20180365026A1 (en) | Systems, devices, and methods for providing improved virtual assistants using state-based artificial intelligence | |
| US20140122619A1 (en) | Chatbot system and method with interactive chat log | |
| US10218770B2 (en) | Method and system for sharing speech recognition program profiles for an application | |
| CN116595148B (en) | Method and system for realizing dialogue flow by using large language model | |
| CN110910694A (en) | Intelligent customer service training system | |
| CN113938697B (en) | Virtual speaking method and device in live broadcasting room and computer equipment | |
| EP2869546B1 (en) | Method and system for providing access to auxiliary information | |
| CN113850898A (en) | Scene rendering method and device, storage medium and electronic equipment | |
| JP7338839B1 (en) | Server Intermediation System, Intermediation Server, Trained Model Assist System, and Assist Server | |
| US20100324908A1 (en) | Learning Playbot | |
| CN115757748B (en) | Method and device for controlling conversation with robot, computer equipment and storage medium | |
| CN110442698B (en) | Dialog content generation method and system | |
| CN117033599A (en) | Digital content generation method and related equipment | |
| WO2017165253A1 (en) | Modular communications | |
| KR20210098623A (en) | Method and system for mimicking tone and style of real person | |
| US20220253717A1 (en) | System and method for bringing inanimate characters to life | |
| CN117319340A (en) | Voice message playing method, device, terminal and storage medium | |
| CN110111793A (en) | Processing method, device, storage medium and the electronic device of audio-frequency information | |
| CN113382311A (en) | Online teaching interaction method and device, storage medium and terminal | |
| CN111556096A (en) | Information pushing method, device, medium and electronic equipment | |
| EP4395242A1 (en) | Artificial intelligence social facilitator engine | |
| CN114244791B (en) | Data processing method, device and readable 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 | ||
| GR01 | Patent grant |