CN113626568A - Man-machine conversation control method and device for robot, computer equipment and medium - Google Patents
Man-machine conversation control method and device for robot, computer equipment and medium Download PDFInfo
- Publication number
- CN113626568A CN113626568A CN202110874814.8A CN202110874814A CN113626568A CN 113626568 A CN113626568 A CN 113626568A CN 202110874814 A CN202110874814 A CN 202110874814A CN 113626568 A CN113626568 A CN 113626568A
- Authority
- CN
- China
- Prior art keywords
- robot
- data
- service
- dialogue data
- dialogue
- 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
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000003058 natural language processing Methods 0.000 claims abstract description 25
- 230000003993 interaction Effects 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 239000012141 concentrate Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Human Computer Interaction (AREA)
- Manipulator (AREA)
Abstract
The application relates to the field of artificial intelligence, and discloses a man-machine conversation control method, a man-machine conversation control device, computer equipment and a storage medium of a robot based on semantic analysis, wherein the method comprises the following steps: acquiring dialogue data collected by a front-end robot; recognizing the intention of the dialogue data according to a natural language processing algorithm, and determining the service field of the dialogue data according to the intention; matching a target service robot at the rear end according to the service field, and forwarding the dialogue data to the target service robot; acquiring answer data of the dialogue data, wherein the answer data is obtained by analyzing the semantics of the dialogue data and then matching the semantics with the target business robot; and outputting the answer data to reply to the dialogue data. According to the method and the device, the replying efficiency and accuracy of the robot dialogue data under the man-machine dialogue can be improved.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to a method and an apparatus for controlling a human-computer interaction of a robot based on semantic analysis, a computer device, and a storage medium.
Background
With the development of internet technology and the continuous development of digitalization, intelligent conversation robots are widely applied to the fields of medical question answering, online customer service sales, telephone call centers, intelligent toys for children and the like, the existing intelligent customer service robots are designed independently for specific service scenes, and if people want to know products or services of different service lines, accurate answers cannot be obtained from one customer service robot or irrelevant answers are directly fed back, so that the question answering efficiency of the robots is low, and the question answering accuracy is low.
Disclosure of Invention
The application mainly aims to provide a man-machine conversation control method, a man-machine conversation control device, computer equipment and a storage medium of a robot based on semantic analysis, and aims to solve the problems that the current robot is low in question and answer efficiency and accuracy in different business fields.
In order to achieve the above object, the present application provides a human-machine interaction control method for a robot, including:
acquiring dialogue data collected by a front-end robot;
recognizing the intention of the dialogue data according to a natural language processing algorithm, and determining the service field of the dialogue data according to the intention;
matching a target service robot at the rear end according to the service field, and forwarding the dialogue data to the target service robot;
acquiring answer data of the dialogue data, wherein the answer data is obtained by analyzing the semantics of the dialogue data and then matching the semantics with the target business robot;
and outputting the answer data to reply to the dialogue data.
Further, the forwarding the dialogue data to the target business robot includes:
judging the data type of the dialogue data;
if the data type is a text type, forwarding the original text of the dialogue data to the target business robot;
and if the data type is a non-text type, converting the dialogue data into text type dialogue data, and forwarding the text type dialogue data to the target service robot.
Further, the identifying the intention of the dialogue data according to the natural language processing algorithm, and determining the business field of the dialogue data according to the intention comprise:
identifying a plurality of intents contained in the dialogue data according to a natural language processing algorithm;
determining a plurality of fields to be selected contained in the dialogue data according to the intention;
counting the corpus quantity of each to-be-selected field; the corpus quantity is the corpus quantity contained in the intention corresponding to the field to be selected in the dialogue data;
and selecting the field to be selected, the corpus quantity of which meets the preset value, and determining the field to be the service field of the dialogue data.
Further, the determining the business domain of the dialogue data according to the intention includes:
determining a plurality of fields to be selected contained in the dialogue data according to the intention;
outputting options corresponding to the fields to be selected;
and receiving a selection instruction of any option, and determining the to-be-selected field corresponding to the selected option as the service field of the dialogue data.
Further, after outputting the answer data to reply to the dialog data, the method further includes:
counting feedback information of the user on the answer data;
counting the accuracy of each service robot according to the feedback information;
receiving update information of any service robot with accuracy rate lower than a preset value;
and sending the updating information to the corresponding service robot, and controlling the corresponding service robot to update.
Further, the matching of the target service robot at the back end according to the service field includes:
acquiring a first service robot currently connected with the front-end robot;
judging whether the first service robot is matched with the service field or not;
if so, determining that the first service robot is a target service robot;
and if not, matching the target service robot at the rear end according to the service field, and establishing connection with the target service robot.
Further, after establishing the connection with the target business robot, the method includes:
taking the first service robot as a candidate service robot, and configuring the life cycle of the candidate service robot;
and in the life cycle, if the conversation data of the service field matched with the candidate service robot is not connected, disconnecting the connection with the candidate service robot.
The present application also provides a human-computer interaction control device of a robot, including:
the data acquisition module is used for acquiring dialogue data acquired by the front-end robot;
the domain identification module is used for identifying the intention of the dialogue data according to a natural language processing algorithm and determining the service domain of the dialogue data according to the intention;
the data forwarding module is used for matching a target service robot at the rear end according to the service field and forwarding the dialogue data to the target service robot;
the answer obtaining module is used for obtaining answer data of the dialogue data, and the answer data is obtained by analyzing the semantics of the dialogue data and then matching the semantics with the target business robot;
and the answer output module is used for outputting the answer data so as to reply the dialogue data.
The application also provides computer equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the man-machine interaction control method of the robot when executing the computer program.
The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when being executed by a processor, implements the steps of the human-machine interaction control method for a robot according to any one of the above-mentioned embodiments.
The application example provides a man-machine conversation control method for a conversation robot to carry out conversation data shunting technology based on different fields, wherein a front-end robot is configured at the front end, conversation data is obtained based on the front-end robot, the conversation data is conversation data to be replied, the intention of the conversation data is identified according to a natural language processing algorithm, words, short sentences and question sentences contained in the conversation data are identified, the intention of the words, short sentences and question sentences contained in the conversation data is judged, so that the intention of the conversation data is judged, the service field of the conversation data is determined according to the intention, the front-end robot is linked with a plurality of rear-end service robots, after the service field of the conversation data is obtained, the corresponding target service robots are matched according to the service field, and the conversation data is forwarded to the target service robots, the service robot is used for identifying, analyzing and matching the dialogue data in the service field, the target service robot identifies the semantics of the dialogue data and matches the preset answers to obtain answer data matched with the dialogue data, then the target service robot forwards the answer data to the front-end robot, the front-end robot obtains the answer data of the dialogue data, the front-end robot outputs the answer data to reply the dialogue data to realize the decoupling of the front-end robot and the rear-end service robot, the service field to which the intention of the dialogue data belongs is identified by the front-end robot and is automatically accessed to different service robots at the rear end, and the service robot in the specific service field identifies and matches answers to the dialogue data in the specific service field, so that the accuracy of the dialogue data can be improved, and 1 front-end robot image is used, the back end is linked with a plurality of service robots for supporting, the service robots do not need to be frequently jumped, the phenomenon that the service robots are switched for a plurality of times in the conversation process is avoided, and therefore the efficiency of man-machine conversation reply is improved.
Drawings
FIG. 1 is a schematic flow chart illustrating an embodiment of a human-machine interaction control method of a robot according to the present application;
FIG. 2 is a schematic structural diagram of an embodiment of a human-machine interaction control device of a robot according to the present application;
FIG. 3 is a block diagram illustrating a computer device according to an embodiment of the present invention.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
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, an embodiment of the present application provides a human-computer interaction control method for a robot, including steps S10-S50, and the detailed description of each step of the human-computer interaction control method for the robot is as follows.
And S10, acquiring dialogue data collected by the front-end robot.
In this embodiment, the dialog data may be obtained and processed based on an artificial intelligence technology, and is particularly applied to a robot dialog and question-and-answer scenario, when a user sends dialog contents to a robot through voice or text, the robot needs to reply to the dialog contents, in the present invention, a man-machine dialog control method of the robot is completed by a dialog robot, the dialog robot includes a front-end robot and a rear-end business robot, specifically, a front-end robot is configured at the front end, and the front-end robot links a plurality of rear-end business robots, and replies the received dialog data with the image of the front-end robot, that is, the dialog data collected by the front-end robot is obtained based on the front-end robot, and the dialog data is dialog data to be replied, in an implementation manner, a user carries out dialogue with the robot through a dialogue box, and at the moment, dialogue data are obtained by obtaining information input by the user in the dialogue box; in another embodiment, the user has a conversation with the robot by voice, and the voice data of the user is picked up by a microphone at this time, thereby acquiring the conversation data.
And S20, recognizing the intention of the dialogue data according to a natural language processing algorithm, and determining the business field of the dialogue data according to the intention.
In this embodiment, after obtaining the dialogue data to be replied, the front-end robot identifies the intention of the dialogue data according to a natural language processing algorithm (NLP), but does not specifically identify the explicit semantics of the dialogue data, but identifies the words, phrases and question sentences contained in the dialogue data, determines the intention of the dialogue data, that is, the intention to which the words, phrases and question sentences belong, according to the words, phrases and question sentences contained in the dialogue data, and then determines the business field of the dialogue data, that is, determines which business field the dialogue data belongs to according to the intention, for example, the business fields include chatting, life insurance, car insurance, accident insurance, loan and the like. The front-end robot collects historical dialogue data in different business fields through big data, determines intentions contained in the different business fields, identifies words, short sentences and question sentences contained in the historical dialogue data, and takes the identified words, short sentences and question sentences as the words, short sentences and question sentences corresponding to the intentions, so that the business fields, the intentions and the relations among the words, the short sentences and the question sentences are established.
And S30, matching the target service robot at the rear end according to the service field, and forwarding the dialogue data to the target service robot.
In this embodiment, a front-end robot is configured at a front end, the front-end robot is linked with a plurality of back-end service robots, and each back-end service robot is configured to process session data corresponding to a service field, so that the back-end service robot is matched according to the service field, the matched service robot is determined as a target service robot, after the back-end target service robot is determined, the session data is forwarded to the target service robot, the service robot is configured to identify, analyze and match the session data in its service field with answers of the session data, and in one implementation, the original text of the session data is forwarded to the target service robot.
And S40, obtaining answer data of the dialogue data, wherein the answer data is obtained by analyzing the semantics of the dialogue data and then matching the semantics by the target service robot.
In this embodiment, after forwarding the dialogue data to the target service robot, the target service robot performs answer search and matching according to the dialogue data, specifically, the target service robot analyzes semantics of the dialogue data, performs matching according to the semantics of the dialogue data and a preset answer to obtain answer data matched with the dialogue data, and then the target service robot forwards the answer data to a front-end robot, and the front-end robot obtains the answer data of the dialogue data.
And S50, outputting the answer data to reply the dialogue data.
In this embodiment, after obtaining the answer data by the target service robot according to parsing and matching the dialogue data, the answer data is output based on the front-end robot to reply the dialogue data, the front-end robot does not need to parse the dialogue data in detail, only needs to determine the service field of the dialogue data, and matches the dialogue data by different service robots aiming at the dialogue data of different service fields, so as to achieve the decoupling of the front-end robot and the back-end service robot, and automatically accesses to the robots of different service lines at the back-end by identifying the service field to which the intention of the client belongs, so as to achieve the effect that 1 customer service robot at the front-end is visualized, the N service robots at the back-end are supported, and the phenomenon of multiple switching of the dialogue robots is avoided, therefore, the reply efficiency and accuracy of the man-machine conversation are improved.
The embodiment provides a man-machine conversation control method for a conversation robot to perform conversation data distribution technology based on different fields, the method comprises the steps of configuring a front-end robot at a front end, obtaining conversation data based on the front-end robot, identifying the intention of the conversation data according to a natural language processing algorithm, identifying words, short sentences and question sentences contained in the conversation data, judging the intentions of the words, short sentences and question sentences contained in the conversation data, determining the service field of the conversation data according to the intention, linking a plurality of rear-end service robots with the front-end robot, matching the corresponding target service robots according to the service field after the service field of the conversation data is obtained, and forwarding the conversation data to the target service robots, the service robot is used for identifying, analyzing and matching the dialogue data in the service field, the target service robot identifies the semantics of the dialogue data and matches the preset answers to obtain answer data matched with the dialogue data, then the target service robot forwards the answer data to the front-end robot, the front-end robot obtains the answer data of the dialogue data, the front-end robot outputs the answer data to reply the dialogue data to realize the decoupling of the front-end robot and the rear-end service robot, the service field to which the intention of the dialogue data belongs is identified by the front-end robot and is automatically accessed to different service robots at the rear end, and the service robot in the specific service field identifies and matches answers to the dialogue data in the specific service field, so that the accuracy of the dialogue data can be improved, and 1 front-end robot image is used, the back end is linked with a plurality of service robots for supporting, the service robots do not need to be frequently jumped, the phenomenon that the service robots are switched for a plurality of times in the conversation process is avoided, and therefore the efficiency of man-machine conversation reply is improved.
In one embodiment, said forwarding said dialogue data to said target business robot comprises:
judging the data type of the dialogue data;
if the data type is a text type, forwarding the original text of the dialogue data to the target business robot;
and if the data type is a non-text type, converting the dialogue data into text type dialogue data, and forwarding the text type dialogue data to the target service robot.
In this embodiment, in the process of forwarding the dialogue data to the target service robot, the data type of the dialogue data is determined, the front-end robot may determine the data type of the dialogue data, then obtain the data type of the dialogue data determined by the front-end robot, if the data type is a text type, forward the original text of the dialogue data to the target service robot, if the data type is a non-text type, the front-end robot converts the dialogue data into the dialogue data of the text type first, so as to obtain the dialogue data of the converted text type, and then forward the dialogue data of the text type to the target service robot, so that all the back-end service robots only need to process the dialogue data of the text type without performing type identification or type conversion on the dialogue data, the front-end robot concentrates on conversion of the dialogue data and recognition of the business field, and the back-end business robot concentrates on answer matching of the text type dialogue data, so that the efficiency and accuracy of man-machine dialogue are improved.
In one embodiment, the identifying the intent of the dialogue data according to a natural language processing algorithm, the determining the business domain of the dialogue data according to the intent, comprises:
identifying a plurality of intents contained in the dialogue data according to a natural language processing algorithm;
determining a plurality of fields to be selected contained in the dialogue data according to the intention;
counting the corpus quantity of each to-be-selected field; the corpus quantity is the corpus quantity contained in the intention corresponding to the field to be selected in the dialogue data;
and selecting the field to be selected, the corpus quantity of which meets the preset value, and determining the field to be the service field of the dialogue data.
In this embodiment, in the process of identifying the intention of the dialog data according to a natural language processing algorithm and determining the service field of the dialog data according to the intention, there is a phenomenon that the dialog data includes a plurality of service fields, when it is identified that the dialog data includes a plurality of intentions according to the natural language processing algorithm, a plurality of fields included in the dialog data are determined according to the intentions, the plurality of fields are defined as a plurality of fields to be selected, then the number of corpuses of each field to be selected is counted, the number of corpuses is the number of corpuses included in the intention corresponding to the field to be selected in the dialog data, that is, the number of corpuses related to each field to be selected appearing in the dialog data, and the corpuses include words or short sentences. For example, according to a natural language processing algorithm, it is identified that dialogue data includes corpus A, B, C, D, E, corpus A, B, C is identified to belong to intention Y1, corpus D belongs to intention Y2, corpus E belongs to intention Y3, corresponding candidate field P1 is determined according to intention Y1, corresponding candidate field P2 is determined according to intention Y2, corresponding candidate field P3 is determined according to intention Y3, then the candidate fields with corpus numbers meeting preset values are selected, and the selected candidate fields are determined as the business field of the dialogue data, so that the accuracy of business field determination is improved, and the efficiency and the accuracy of man-machine dialogue are improved.
In one embodiment, the determining the business segment of the dialogue data according to the intention includes:
determining a plurality of fields to be selected contained in the dialogue data according to the intention;
outputting options corresponding to the fields to be selected;
and receiving a selection instruction of any option, and determining the to-be-selected field corresponding to the selected option as the service field of the dialogue data.
In this embodiment, in the process of determining the service domain of the dialog data according to the intention, there is a phenomenon that the dialog data includes a plurality of service domains, in one embodiment, the intention of the obtained dialog data cannot be clearly determined, or in another embodiment, the dialog data is extracted to include a plurality of intentions, at this time, the plurality of domains included in the dialog data are determined according to the intentions, the plurality of domains are defined as a plurality of candidate domains, and then before matching the target service robot at the rear end according to the service domains, options corresponding to the respective candidate domains are output, for example, a selection box click is output, for example, "ask if you want to know the following related services: and the user can select any one of the options, namely, a selection instruction of any option is received, and the selected field corresponding to the selected option is determined as the service field of the dialogue data, so that the service field of the dialogue data can be quickly positioned in a plurality of different fields to be selected, and the interaction efficiency of man-machine dialogue is improved.
In one embodiment, after outputting the answer data to reply to the dialog data, the method further includes:
counting feedback information of the user on the answer data;
counting the accuracy of each service robot according to the feedback information;
receiving update information of any service robot with accuracy rate lower than a preset value;
and sending the updating information to the corresponding service robot, and controlling the corresponding service robot to update.
In this embodiment, after the front-end robot outputs the answer data, the user may feed back the answer data to feed back whether the answer data meets the requirement of the user, and then, according to the feedback information, count the accuracy of each service robot, because the front-end robot links a plurality of back-end service robots, the front-end robot may update the front-end robot, and meanwhile, the front-end robot serves as an entrance, any one of the back-end service robots is updated based on the front-end robot, specifically, update information for any one of the back-end service robots is received, the update information is sent to the corresponding service robot based on the front-end robot, the corresponding service robot is controlled to update, in one embodiment, update information for any one of the service robots having an accuracy lower than a preset value is received, and when the accuracy of the answer data of any one of the service robots is lower than the preset value, the service robot is updated, the update information is sent to the corresponding service robot, the corresponding service robot is controlled to update, the front-end robot and the rear-end service robot are decoupled, and different service robots at the rear end are also decoupled, so that data separation can be realized, the maintenance efficiency of the service robot is improved, and further, the update information and the updated service robot are stored in a block chain, so that the update data of each service robot can be traced.
In one embodiment, the matching a target service robot at a back end according to the service domain includes:
acquiring a first service robot currently connected with the front-end robot;
judging whether the first service robot is matched with the service field or not;
if so, determining that the first service robot is a target service robot;
and if not, matching the target service robot at the rear end according to the service field, and establishing connection with the target service robot.
In this embodiment, a front-end robot and a rear-end service robot can maintain connection, during connection, after determining a service field of session data, a first service robot at a rear end to which the front-end robot is currently connected is acquired, that is, the service robot currently connected to the front-end robot is acquired, and then it is determined whether the first service robot is matched with the service field, if the first service robot is matched with the service field, matching and connection of the service robot do not need to be performed again, at this time, it is determined that the first service robot is a target service robot, time consumed by frequently matching the service robot is avoided, if the first service robot is not matched with the service field, the target service robot at the rear end is matched according to the service field, and connection with the target service robot is established, thereby improving the utilization rate of resources.
In one embodiment, said establishing a connection with said target business robot comprises:
taking the first service robot as a candidate service robot, and configuring the life cycle of the candidate service robot;
and in the life cycle, if the conversation data of the service field matched with the candidate service robot is not connected, disconnecting the connection with the candidate service robot.
In this embodiment, after the connection with the target service robot is established, in order to improve conversion between different service robots, the first service robot is used as a candidate service robot, and a life cycle of the candidate service robot is configured, and in the life cycle, if there is no connection to the session data of the service domain matched with the candidate service robot, the connection with the candidate service robot is disconnected, so as to avoid resources occupied by the first service robot due to long-time connection, thereby improving the utilization rate of resources.
The embodiment of the application can acquire and process related data based on the artificial intelligence technology, and relates to natural language identification and semantic analysis based on the artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Referring to fig. 2, the present application also provides a human-machine interaction control apparatus for a robot, including:
the data acquisition module 10 is used for acquiring dialogue data acquired by a front-end robot;
a domain identification module 20, configured to identify an intention of the dialog data according to a natural language processing algorithm, and determine a business domain of the dialog data according to the intention;
the data forwarding module 30 is configured to match a target service robot at a rear end according to the service field, and forward the session data to the target service robot;
the answer obtaining module 40 is configured to obtain answer data of the session data, where the answer data is obtained by analyzing semantics of the session data and matching the semantics with the target service robot;
and the answer output module 50 is configured to output the answer data to reply the dialogue data.
In one embodiment, the data forwarding module 30 further includes a conversion unit, configured to perform:
judging the data type of the dialogue data;
if the data type is a text type, forwarding the original text of the dialogue data to the target business robot;
if the data type is a non-text type, converting the dialogue data into text type dialogue data, and forwarding the text type dialogue data to the target service robot,
in one embodiment, the domain identification module 20 further comprises a determining unit for performing:
identifying a plurality of intents contained in the dialogue data according to a natural language processing algorithm;
determining a plurality of fields to be selected contained in the dialogue data according to the intention;
counting the corpus quantity of each to-be-selected field; the corpus quantity is the corpus quantity contained in the intention corresponding to the field to be selected in the dialogue data;
and selecting the field to be selected, the corpus quantity of which meets the preset value, and determining the field to be the service field of the dialogue data.
In one embodiment, the domain identification module 20 further comprises a selection unit for performing:
determining a plurality of fields to be selected contained in the dialogue data according to the intention;
outputting options corresponding to the fields to be selected;
and receiving a selection instruction of any option, and determining the to-be-selected field corresponding to the selected option as the service field of the dialogue data.
In one embodiment, the human-machine interaction control device of the robot further comprises an updating module for executing:
counting feedback information of the user on the answer data;
counting the accuracy of each service robot according to the feedback information;
receiving update information of any service robot with accuracy rate lower than a preset value;
and sending the updating information to the corresponding service robot, and controlling the corresponding service robot to update.
In one embodiment, the data forwarding module 30 further includes a connection unit, configured to perform:
acquiring a first service robot currently connected with the front-end robot;
judging whether the first service robot is matched with the service field or not;
if so, determining that the first service robot is a target service robot;
and if not, matching the target service robot at the rear end according to the service field, and establishing connection with the target service robot.
In one embodiment, the data forwarding module 30 further includes a cycle unit, configured to perform:
taking the first service robot as a candidate service robot, and configuring the life cycle of the candidate service robot;
and in the life cycle, if the conversation data of the service field matched with the candidate service robot is not connected, disconnecting the connection with the candidate service robot.
As described above, it is understood that the components of the human-machine interaction control device for a robot proposed in the present application can implement the functions of any one of the above-described human-machine interaction control methods for a robot.
Referring to fig. 3, a computer device, which may be a mobile terminal and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer equipment comprises a processor, a memory, a network interface, a display device and an input device which are connected through a system bus. Wherein, the network interface of the computer equipment is used for communicating with an external terminal through network connection. The input means of the computer device is for receiving input from a user. The computer designed processor is used to provide computational and control capabilities. The memory of the computer device includes a storage medium. The storage medium stores an operating system, a computer program, and a database. The database of the computer device is used for storing data. The computer program is executed by a processor to implement a method for human-machine interaction control of a robot.
The processor executes the man-machine interaction control method of the robot, and the method comprises the following steps: collecting dialogue data based on a front-end robot; recognizing the intention of the dialogue data according to a natural language processing algorithm, and determining the service field of the dialogue data according to the intention; matching a target service robot at the rear end according to the service field, and forwarding the dialogue data to the target service robot; acquiring answer data of the dialogue data, wherein the answer data is obtained by analyzing the semantics of the dialogue data and then matching the semantics with the target business robot; and outputting the answer data to reply to the dialogue data.
The computer equipment provides a man-machine conversation control method for a conversation robot to carry out conversation data shunting technology based on different fields, a front-end robot is configured at the front end, conversation data is obtained based on the front-end robot, the conversation data is to-be-replied conversation data, the intention of the conversation data is identified according to a natural language processing algorithm, words, short sentences and question sentences contained in the conversation data are identified, the intention of the words, short sentences and question sentences contained in the conversation data is judged, so that the intention of the conversation data is judged, the service field of the conversation data is determined according to the intention, a plurality of rear-end service robots are linked with the front-end robot, after the service field of the conversation data is obtained, the corresponding target service robot is matched according to the service field, and the conversation data is forwarded to the target service robot, the service robot is used for identifying, analyzing and matching the dialogue data in the service field, the target service robot identifies the semantics of the dialogue data and matches the preset answers to obtain answer data matched with the dialogue data, then the target service robot forwards the answer data to the front-end robot, the front-end robot obtains the answer data of the dialogue data, the front-end robot outputs the answer data to reply the dialogue data to realize the decoupling of the front-end robot and the rear-end service robot, the service field to which the intention of the dialogue data belongs is identified by the front-end robot and is automatically accessed to different service robots at the rear end, and the service robot in the specific service field identifies and matches answers to the dialogue data in the specific service field, so that the accuracy of the dialogue data can be improved, and 1 front-end robot image is used, the back end is linked with a plurality of service robots for supporting, the service robots do not need to be frequently jumped, the phenomenon that the service robots are switched for a plurality of times in the conversation process is avoided, and therefore the efficiency of man-machine conversation reply is improved.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, the computer program, when executed by the processor, implementing a human-machine interaction control method for a robot, including the steps of: collecting dialogue data based on a front-end robot; recognizing the intention of the dialogue data according to a natural language processing algorithm, and determining the service field of the dialogue data according to the intention; matching a target service robot at the rear end according to the service field, and forwarding the dialogue data to the target service robot; acquiring answer data of the dialogue data, wherein the answer data is obtained by analyzing the semantics of the dialogue data and then matching the semantics with the target business robot; and outputting the answer data to reply to the dialogue data.
The computer readable storage medium provides a man-machine conversation control method for a conversation robot to perform conversation data shunting technology based on different fields, a front-end robot is configured at the front end, conversation data is obtained based on the front-end robot, the conversation data is to-be-replied conversation data, the intention of the conversation data is identified according to a natural language processing algorithm, words, short sentences and question sentences contained in the conversation data are identified, the intention of the words, short sentences and question sentences contained in the conversation data is judged, so that the intention of the conversation data is judged, the service field of the conversation data is determined according to the intention, a plurality of back-end service robots are linked with the front-end robot, after the service field of the conversation data is obtained, the corresponding target service robot is matched according to the service field, and the conversation data is forwarded to the target service robot, the service robot is used for identifying, analyzing and matching the dialogue data in the service field, the target service robot identifies the semantics of the dialogue data and matches the preset answers to obtain answer data matched with the dialogue data, then the target service robot forwards the answer data to the front-end robot, the front-end robot obtains the answer data of the dialogue data, the front-end robot outputs the answer data to reply the dialogue data to realize the decoupling of the front-end robot and the rear-end service robot, the service field to which the intention of the dialogue data belongs is identified by the front-end robot and is automatically accessed to different service robots at the rear end, and the service robot in the specific service field identifies and matches answers to the dialogue data in the specific service field, so that the accuracy of the dialogue data can be improved, and 1 front-end robot image is used, the back end is linked with a plurality of service robots for supporting, the service robots do not need to be frequently jumped, the phenomenon that the service robots are switched for a plurality of times in the conversation process is avoided, and therefore the efficiency of man-machine conversation reply is improved.
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 provided herein and used in the embodiments may include non-volatile and/or volatile memory.
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-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application and is not intended to limit the scope of the present application.
All the equivalent structures or equivalent processes performed by using the contents of the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields, are included in the scope of protection of the present application.
Claims (10)
1. A human-machine interaction control method for a robot, comprising:
acquiring dialogue data collected by a front-end robot;
recognizing the intention of the dialogue data according to a natural language processing algorithm, and determining the service field of the dialogue data according to the intention;
matching a target service robot at the rear end according to the service field, and forwarding the dialogue data to the target service robot;
acquiring answer data of the dialogue data, wherein the answer data is obtained by analyzing the semantics of the dialogue data and then matching the semantics with the target business robot;
and outputting the answer data to reply to the dialogue data.
2. The human-machine conversation control method of a robot according to claim 1, wherein said forwarding the conversation data to the target business robot comprises:
judging the data type of the dialogue data;
if the data type is a text type, forwarding the original text of the dialogue data to the target business robot;
and if the data type is a non-text type, converting the dialogue data into text type dialogue data, and forwarding the text type dialogue data to the target service robot.
3. The human-machine interaction control method for a robot according to claim 1, wherein the recognizing the intention of the interaction data according to a natural language processing algorithm, and determining the business field of the interaction data according to the intention comprises:
identifying a plurality of intents contained in the dialogue data according to a natural language processing algorithm;
determining a plurality of fields to be selected contained in the dialogue data according to the intention;
counting the corpus quantity of each to-be-selected field; the corpus quantity is the corpus quantity contained in the intention corresponding to the field to be selected in the dialogue data;
and selecting the field to be selected, the corpus quantity of which meets the preset value, and determining the field to be the service field of the dialogue data.
4. The human-computer interaction control method for a robot according to claim 1, wherein the determining a business area of the interaction data according to the intention comprises:
determining a plurality of fields to be selected contained in the dialogue data according to the intention;
outputting options corresponding to the fields to be selected;
and receiving a selection instruction of any option, and determining the to-be-selected field corresponding to the selected option as the service field of the dialogue data.
5. The human-machine interaction control method for a robot according to claim 1, wherein after outputting the answer data to reply to the interaction data, the method further comprises:
counting feedback information of the user on the answer data;
counting the accuracy of each service robot according to the feedback information;
receiving update information of any service robot with accuracy rate lower than a preset value;
and sending the updating information to the corresponding service robot, and controlling the corresponding service robot to update.
6. The human-computer interaction control method of a robot according to claim 1, wherein the matching of the target service robot at the back end according to the service domain comprises:
acquiring a first service robot currently connected with the front-end robot;
judging whether the first service robot is matched with the service field or not;
if so, determining that the first service robot is a target service robot;
and if not, matching the target service robot at the rear end according to the service field, and establishing connection with the target service robot.
7. The human-machine interaction control method for a robot according to claim 6, wherein the establishing of the connection with the target service robot is followed by:
taking the first service robot as a candidate service robot, and configuring the life cycle of the candidate service robot;
and in the life cycle, if the conversation data of the service field matched with the candidate service robot is not connected, disconnecting the connection with the candidate service robot.
8. A human-machine interaction control device for a robot, comprising:
the data acquisition module is used for acquiring dialogue data;
the domain identification module is used for identifying the intention of the dialogue data according to a natural language processing algorithm and determining the service domain of the dialogue data according to the intention;
the data forwarding module is used for matching a target service robot at the rear end according to the service field and forwarding the dialogue data to the target service robot;
the answer obtaining module is used for obtaining answer data of the dialogue data, and the answer data is obtained by analyzing the semantics of the dialogue data and then matching the semantics with the target business robot;
and the answer output module is used for outputting the answer data so as to reply the dialogue data.
9. A computer device comprising a memory and a processor, said memory storing a computer program, characterized in that said processor, when executing said computer program, implements the steps of a human-machine interaction control method of a robot according to any one 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 human-machine interaction control method of a robot according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110874814.8A CN113626568A (en) | 2021-07-30 | 2021-07-30 | Man-machine conversation control method and device for robot, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110874814.8A CN113626568A (en) | 2021-07-30 | 2021-07-30 | Man-machine conversation control method and device for robot, computer equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113626568A true CN113626568A (en) | 2021-11-09 |
Family
ID=78381890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110874814.8A Pending CN113626568A (en) | 2021-07-30 | 2021-07-30 | Man-machine conversation control method and device for robot, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113626568A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115545043A (en) * | 2022-11-29 | 2022-12-30 | 城云科技（中国）有限公司 | Entity and relation parallel extraction model and construction method, device and application thereof |
| CN115599900A (en) * | 2022-12-12 | 2023-01-13 | 深圳市人马互动科技有限公司（Cn） | Distribution processing method of ambiguous user input and related device |
| CN117519488A (en) * | 2024-01-05 | 2024-02-06 | 四川中电启明星信息技术有限公司 | Dialogue method and dialogue system of dialogue robot |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108427722A (en) * | 2018-02-09 | 2018-08-21 | 卫盈联信息技术（深圳）有限公司 | intelligent interactive method, electronic device and storage medium |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| CN111046132A (en) * | 2019-10-25 | 2020-04-21 | 众安信息技术服务有限公司 | Customer service question and answer processing method and system for retrieving multiple rounds of conversations |
| US20200320133A1 (en) * | 2019-04-05 | 2020-10-08 | Jade Global, Inc. | AI Routing Framework For Multi-Domain Chatbots |
| CN111783439A (en) * | 2020-06-28 | 2020-10-16 | 平安普惠企业管理有限公司 | Man-machine interaction dialogue processing method and device, computer equipment and storage medium |
| CN112035632A (en) * | 2020-08-21 | 2020-12-04 | 惠州市德赛西威汽车电子股份有限公司 | Preferred distribution method and system suitable for multi-conversation robot collaboration task |
-
2021
- 2021-07-30 CN CN202110874814.8A patent/CN113626568A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108427722A (en) * | 2018-02-09 | 2018-08-21 | 卫盈联信息技术（深圳）有限公司 | intelligent interactive method, electronic device and storage medium |
| US20200320133A1 (en) * | 2019-04-05 | 2020-10-08 | Jade Global, Inc. | AI Routing Framework For Multi-Domain Chatbots |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| CN111046132A (en) * | 2019-10-25 | 2020-04-21 | 众安信息技术服务有限公司 | Customer service question and answer processing method and system for retrieving multiple rounds of conversations |
| CN111783439A (en) * | 2020-06-28 | 2020-10-16 | 平安普惠企业管理有限公司 | Man-machine interaction dialogue processing method and device, computer equipment and storage medium |
| CN112035632A (en) * | 2020-08-21 | 2020-12-04 | 惠州市德赛西威汽车电子股份有限公司 | Preferred distribution method and system suitable for multi-conversation robot collaboration task |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115545043A (en) * | 2022-11-29 | 2022-12-30 | 城云科技（中国）有限公司 | Entity and relation parallel extraction model and construction method, device and application thereof |
| CN115545043B (en) * | 2022-11-29 | 2023-04-07 | 城云科技（中国）有限公司 | Entity and relation parallel extraction model and construction method, device and application thereof |
| CN115599900A (en) * | 2022-12-12 | 2023-01-13 | 深圳市人马互动科技有限公司（Cn） | Distribution processing method of ambiguous user input and related device |
| CN117519488A (en) * | 2024-01-05 | 2024-02-06 | 四川中电启明星信息技术有限公司 | Dialogue method and dialogue system of dialogue robot |
| CN117519488B (en) * | 2024-01-05 | 2024-03-29 | 四川中电启明星信息技术有限公司 | Dialogue method and dialogue system of dialogue robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113626568A (en) | Man-machine conversation control method and device for robot, computer equipment and medium | |
| CN107957992B (en) | Automatic processing method and system for user feedback information | |
| CN111241260A (en) | Data processing method, device and equipment based on human-computer interaction and storage medium | |
| CN112035640A (en) | Refined question-answering method based on intelligent question-answering robot, storage medium and intelligent equipment | |
| CN106503046B (en) | Interaction method and system based on intelligent robot | |
| CN108074571A (en) | Sound control method, system and the storage medium of augmented reality equipment | |
| CN111858890B (en) | Consultation method based on robot, consultation robot, computer equipment and medium | |
| CN113840040B (en) | Man-machine cooperation outbound method, device, equipment and storage medium | |
| CN113157371A (en) | Manual customer service switching method and device, storage medium and computer equipment | |
| CN114120978A (en) | Emotion recognition model training and voice interaction method, device, equipment and medium | |
| CN111858874B (en) | Dialogue service processing method, device, equipment and computer readable storage medium | |
| CN113806503A (en) | Dialog fusion method, device and equipment | |
| CN113064980A (en) | Intelligent question and answer method and device, computer equipment and storage medium | |
| CN112579031A (en) | Voice interaction method and system and electronic equipment | |
| CN115186080A (en) | Intelligent question-answering data processing method, system, computer equipment and medium | |
| CN110417635B (en) | Automatic information reply method, device and equipment | |
| CN110929014B (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN110931002B (en) | Man-machine interaction method, device, computer equipment and storage medium | |
| CN113591463A (en) | Intention recognition method and device, electronic equipment and storage medium | |
| CN117709336A (en) | Online customer service response method and device and terminal equipment | |
| CN117456995A (en) | Interactive method and system of pension service robot | |
| CN113111157B (en) | Question-answer processing method, device, computer equipment and storage medium | |
| CN114238606A (en) | Intelligent voice customer service robot conversation management method and device | |
| CN111552785A (en) | Method and device for updating database of human-computer interaction system, computer equipment and medium | |
| CN113282708B (en) | Method and device for replying to robot dialog, computer 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211109 |