CN113486166A - Method, device and equipment for constructing intelligent customer service robot and storage medium - Google Patents
Method, device and equipment for constructing intelligent customer service robot and storage medium Download PDFInfo
- Publication number
- CN113486166A CN113486166A CN202110845373.9A CN202110845373A CN113486166A CN 113486166 A CN113486166 A CN 113486166A CN 202110845373 A CN202110845373 A CN 202110845373A CN 113486166 A CN113486166 A CN 113486166A
- Authority
- CN
- China
- Prior art keywords
- information
- customer service
- dialogue
- service robot
- intelligent customer
- 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.)
- Granted
Links
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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04845—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Manipulator (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method for constructing an intelligent customer service robot, which comprises the following steps: acquiring construction information of the intelligent customer service robot, wherein the construction information comprises intention information and answering information corresponding to each conversation node in a conversation process set by a user; screening a target dialogue model from a preset dialogue model library according to the construction information; generating training data according to the construction information; training the target dialogue model based on the training data; and constructing the intelligent customer service robot based on the trained target dialogue model. Therefore, the method can automatically complete the construction of the intelligent customer service robot based on the construction information, can automatically complete the complicated processes of construction, training and the like of the dialogue model, packages the complicated processes and does not show the complicated processes to the user, thereby providing the construction method of the intelligent customer service robot with simple construction process and easy operation, and being more beneficial to the wide popularization of the intelligent customer service robot technology. The invention also relates to the technical field of block chains.
Description
Technical Field
The invention relates to the technical field of voice semantics, in particular to a method and a device for constructing an intelligent customer service robot, computer equipment and a storage medium.
Background
With the development of artificial intelligence technology, more and more intelligent robots are put into practical application to replace manual work to improve work efficiency. An intelligent service robot is a typical application form. The intelligent customer service robot generally needs to provide intelligent customer service for users through multiple rounds of automatic dialog responses. In each round of automatic conversation, a natural language understanding module is generally required to analyze the conversation information input by the user, so as to recognize the user intention in the conversation information, and then make a corresponding response according to the intention of the user. For example, in one round of automatic conversation, the natural language understanding module recognizes that the user intends to buy about 5k of notebook computers, and then makes a corresponding response to the model of the notebook computer with the price of about 5k for each computer brand.
However, limited by the technical framework of the current intelligent customer service robot, the use threshold of the intelligent customer service robot is always high, so that the intelligent customer service robot technology cannot be widely popularized and used. For example, the automatic conversation contents of the intelligent customer service robots in different fields usually have great differences, so when an intelligent customer service robot is constructed to ensure the actual use effect of the intelligent customer service robot, a user is usually required to have certain development capability to perform customized development on the intelligent customer service robot, and for example, sufficient training data is also required to complete training on the intelligent customer service robot when an intelligent customer service robot is constructed, which is obviously unrealistic for some users (such as small and medium enterprises) in small and medium scales. It can be seen that the current intelligent customer service robot has a complex and tedious construction process, which is not conducive to the wide popularization of the intelligent customer service robot technology.
Disclosure of Invention
The invention aims to solve the technical problem that the existing intelligent customer service robot is complex and fussy in construction process and is not beneficial to the wide popularization of the intelligent customer service robot technology.
In order to solve the technical problem, a first aspect of the present invention discloses a method for constructing an intelligent customer service robot, including:
acquiring construction information of the intelligent customer service robot, wherein the construction information comprises intention information and answering information corresponding to each conversation node in a conversation process set by a user;
screening a target dialogue model from a preset dialogue model library according to the construction information;
generating training data according to the construction information;
training the target dialog model based on the training data;
constructing an intelligent customer service robot based on the trained target dialogue model;
and the intelligent customer service robot is used for realizing the automation of the conversation process according to the intention information and the answering information in the construction information.
The second aspect of the present invention discloses a construction apparatus for an intelligent customer service robot, the apparatus comprising:
the intelligent customer service robot system comprises an acquisition module, a judgment module and a display module, wherein the acquisition module is used for acquiring construction information of the intelligent customer service robot, and the construction information comprises intention information and answering information which are set by a user and correspond to each conversation node in a conversation process;
the screening module is used for screening a target conversation model from a preset conversation model library according to the construction information;
the generating module is used for generating training data according to the construction information;
a training module to train the target dialog model based on the training data;
the building module is used for building the intelligent customer service robot based on the trained target dialogue model;
and the intelligent customer service robot is used for realizing the automation of the conversation process according to the intention information and the answering information in the construction information.
A third aspect of the present invention discloses a computer apparatus, comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor calls the executable program code stored in the memory to execute part or all of the steps in the construction method of the intelligent customer service robot disclosed by the first aspect of the invention.
The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions, and when the computer instructions are called, the computer instructions are used to execute part or all of the steps in the method for constructing the intelligent customer service robot disclosed in the first aspect of the present invention.
In the embodiment of the invention, the construction information of the intelligent customer service robot is obtained, the target dialogue model is screened out from the preset dialogue model library according to the construction information, the training data is generated according to the construction information, the target dialogue model is trained based on the training data, and finally the intelligent customer service robot is constructed based on the trained target dialogue model, so that the construction of the intelligent customer service robot can be automatically completed based on the construction information, the complicated processes of construction, training and the like of the dialogue model can be automatically completed, the complicated processes are packaged and are not displayed to a user any more, and the construction method of the intelligent customer service robot with simple construction process and easy operation can be provided, and the wide popularization of the intelligent customer service robot technology is facilitated.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for constructing an intelligent customer service robot according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a construction apparatus of an intelligent customer service robot according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a computer device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer storage medium according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, article, or article that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or article.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention discloses a construction method, a device, computer equipment and a storage medium of an intelligent customer service robot, which are used for acquiring construction information of the intelligent customer service robot, screening a target dialogue model from a preset dialogue model library according to the construction information, generating training data according to the construction information, training the target dialogue model based on the training data, and finally constructing the intelligent customer service robot based on the trained target dialogue model, so that the construction of the intelligent customer service robot can be automatically completed based on the construction information, the complicated processes of construction, training and the like of the dialogue model can be automatically completed, the complicated processes are packaged and are not displayed to a user, and the construction method of the intelligent customer service robot with simple construction process and easy operation can be provided, and the wide popularization of the intelligent customer service robot technology is facilitated. The following are detailed below.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for constructing an intelligent customer service robot according to an embodiment of the present invention. As shown in fig. 1, the construction method of the intelligent customer service robot may include the following operations:
101. and acquiring construction information of the intelligent customer service robot, wherein the construction information comprises intention information and answering information corresponding to each conversation node in a conversation process set by a user.
In step 101, a storyline editing interface may be provided to the user at the front end to obtain the construction information of the intelligent customer service robot. Specifically, a user can complete drawing of a storyline in a storyline editing interface through dragging, adding, deleting, modifying, editing a box and the like. The user needs to draw the dialogue nodes of the story line according to the dialogue flow in the actual business scene, and edits intention information and answering information corresponding to each dialogue node. After the user finishes editing the story line, the construction information of the intelligent customer service robot can be generated according to the story line. E.g., the following dialog flow: the user: "i want to know the latest notebook computer" intelligent customer service robot: "recently popular notebook computers are: wonderful 14, associative air14, associative pro14, etc. ", user: "i want to know a luxurious configuration of 14", the intelligent customer service robot: "the CPU of the large wonderful 14 is dragon R7 or dragon R9, and the graphics card is GTX2060 or GTX1660 or GTX 1650". In a story line drawn by the user according to the conversation process, there are two conversation nodes in total, where the intention information corresponding to the first conversation node is "i want to know the latest popular notebook computer", and the answer information is "the latest popular notebook computer: the intention information corresponding to the second dialogue node is "i want to know the configuration of a large and wonderful program 14", the answer information is "the CPU of the large and wonderful program 14 is dragon R7 or dragon R9", and the video card is GTX2060 or GTX1660 or GTX1650 ".
102. And screening out a target dialogue model from a preset dialogue model library according to the construction information.
In the step 102, common natural language recognition models can be pre-stored in the dialogue model library, for example, the dialogue model library can include a bidirectional two-layer LSTM + seq2seq model, a bert model, an N-gram model, an NNLM model, and the like. In practical application, different natural language recognition models usually have certain differences in recognition effects on different conversation contents, so that an appropriate model can be screened from a conversation model library according to actual conversation contents to construct an intelligent customer service robot (a specific screening process is described later), and thus the recognition effect of the intelligent customer service robot on the conversation contents can be ensured.
103. And generating training data according to the construction information.
In the step 103, training data of the target dialogue model is generated according to the dialogue content in the construction information, and then the training data is used for training the target dialogue model, so that the target dialogue model has the capability of recognizing the dialogue content in the construction information, and the constructed intelligent customer service robot can automatically complete the dialogue process. Optionally, when the training data is generated, the training data may be amplified by using a data enhancement algorithm (a specific amplification process is described later), so that it is beneficial to ensure that enough training data is available for training the target dialogue model, ensure the training effect of the target dialogue model, and solve the problem of lack of training sample data of users of medium and small scales.
104. Training the target dialog model based on the training data.
105. Constructing an intelligent customer service robot based on the trained target dialogue model; and the intelligent customer service robot is used for realizing the automation of the conversation process according to the intention information and the answering information in the construction information.
After the training of the target dialogue model is completed, corresponding service interfaces can be generated according to the trained target dialogue model, and then the service interfaces are connected in a butt joint mode through a front-end interface, so that the construction of the intelligent customer service robot can be completed, and the intelligent customer service is improved for users. Specifically, when a user needs to consult, the dialogue content needing to consult can be input on the front-end interface, then the front-end interface inputs the dialogue content input by the user to the trained target dialogue model after the user inputs the dialogue content, the target dialogue model returns the corresponding response content to the front end after analyzing the dialogue content input by the user, and finally the returned response content is displayed to the user on the front-end interface, so that the automation of a dialogue process can be completed, and the construction of the intelligent customer service robot is completed. Therefore, in the construction process of the intelligent customer service robot, a user only needs to draw a story line on an operation layer, wherein the user only needs to relate to contents such as simple text editing, frame dragging and the like, does not need to know complex processes such as model construction, training and the like, the complex processes such as model construction, training and the like are all packaged and are not displayed to the user, and the complex processes such as model construction, training and the like can be automatically completed, so that the construction process of the intelligent customer service robot with simple construction can be provided, and small and medium-sized users can freely construct proper intelligent customer service robots according to self business requirements.
Therefore, by implementing the embodiment of the invention, the construction information of the intelligent customer service robot is obtained, the target dialogue model is screened out from the preset dialogue model library according to the construction information, the training data is generated according to the construction information, the target dialogue model is trained based on the training data, and finally the intelligent customer service robot is constructed based on the trained target dialogue model, so that the construction of the intelligent customer service robot can be automatically completed based on the construction information, the complicated processes of the construction, the training and the like of the dialogue model can be automatically completed, the complicated processes are packaged and are not displayed for a user, the construction method of the intelligent customer service robot with simple construction process and easy operation can be provided, and the wide popularization of the intelligent customer service robot technology is facilitated.
In an optional embodiment, the screening out the target dialog model from the preset dialog model library according to the construction information includes:
extracting keywords in the construction information through a preset keyword extraction algorithm;
calculating the corresponding score of each dialogue model in the dialogue model library according to the keyword;
and screening the dialogue models meeting preset grading conditions from the dialogue model library according to the grading of each dialogue model in the dialogue model library to serve as target dialogue models.
In the optional embodiment, the keywords in the construction information can be extracted through a keyword extraction algorithm such as TF-IDF, topic-model, textrank, rake, and the like. For example, the intention information in the construction information is "i want to know the latest popular notebook computer", and the answer information is "the latest popular notebook computer" including: the keywords extracted from the intention information may be "most recent" and "notebook computer", and the keywords extracted from the answer information may be "wonderful 14", "associative air 14" and "associative pro 14". In practical application, different dialog models have certain differences in recognition effects on different keywords, for example, if the recognition effect of a bert model on a keyword of an alphabet type is likely to be better, and the recognition effect on a keyword of a Chinese character type is likely to be poorer, the score of the bert model corresponding to the keyword of the alphabet type can be set to a higher value, and the score of the bert model corresponding to the keyword of the Chinese character type can be set to a lower value. The scores corresponding to each keyword in each dialogue model are then summed to obtain a score corresponding to each dialogue model, and a specific summing process is described later. For example, the total number of the keywords is two, the scores of the keywords "latest hit" and "notebook computer" in the bidirectional two-layer LSTM + seq2seq model are 5 points and 6 points, respectively, and the score of the bidirectional two-layer LSTM + seq2seq model obtained through final calculation is 5+6 points to 11 points. Finally, the target dialogue model is screened out from the dialogue model library according to the grade of each dialogue model in the dialogue model library, for example, the dialogue model with the highest grade in the dialogue model library can be selected as the target dialogue model.
Therefore, by implementing the optional embodiment, the keywords in the construction information are extracted, the scores corresponding to each dialogue model in the dialogue model library are calculated according to the keywords, and finally the target dialogue model is screened out from the dialogue model library according to the scores of each dialogue model in the dialogue model library, so that the appropriate target dialogue model can be screened out from the dialogue model library to construct the intelligent customer service robot, and the finally constructed intelligent customer service robot has a better use effect.
In an optional embodiment, the calculating a score corresponding to each dialog model in the dialog model library according to the keyword includes:
querying a preset scoring table to obtain a score of each keyword in each dialogue model, wherein the scoring table records the score of each keyword in each dialogue model;
and calculating the scores corresponding to the dialogue models according to the scores corresponding to all the keywords corresponding to each dialogue model.
In this alternative embodiment, the preset scoring table may be as follows:
the score corresponding to each keyword in each dialogue model is recorded in the score table, the score corresponding to each keyword in each dialogue model can be obtained by querying the score table, then the score corresponding to each dialogue model can be calculated according to the scores corresponding to all keywords corresponding to each dialogue model, and the specific calculation process is described later. The keyword in the scoring table may be scored in the dialogue model in advance by the developer according to the experience of the developer or the actual usage effect.
Therefore, the optional embodiment is implemented, the score corresponding to each keyword in each dialogue model is obtained by inquiring the preset score table, the score corresponding to each dialogue model is calculated according to the scores corresponding to all the keywords corresponding to each dialogue model, so that the score corresponding to each dialogue model in the dialogue model library can be calculated according to the keywords, a proper target dialogue model can be screened from the dialogue model library according to the score corresponding to each dialogue model, and the construction of the intelligent customer service robot is facilitated.
In an optional embodiment, the calculating the score corresponding to each dialogue model according to the scores corresponding to all the keywords corresponding to each dialogue model includes:
querying a preset keyword weight table to obtain a keyword weight corresponding to each keyword corresponding to each dialogue model;
calculating the weighted sum of scores corresponding to all the keywords corresponding to each dialogue model to serve as the score corresponding to the dialogue model;
and the weight value of the score corresponding to each keyword corresponding to each dialogue model is the weight value of the keyword corresponding to the keyword. In this alternative embodiment, the preset keyword weight table may be shown as the following table:
| keyword | Weight value |
| Latest hot door | 10 |
| Associative air14 | 5 |
| …… | …… |
The weight corresponding to the keyword in the keyword weight table can be preset by a developer according to own experience or actual use effect, for example, the keyword 'latest hit' usually appears in the intention information, correctly identifies the keyword 'latest hit' in the intention information, and plays an important role in correctly replying the consultation of the user for the intelligent customer service robot, so that the keyword 'latest hit' can be set to be a larger value, the identification accuracy of the keyword 'latest hit' by a target dialogue model screened according to the score can be higher, and the use effect of the finally constructed intelligent customer service robot can be better ensured. When the score corresponding to each dialogue model is calculated based on the keyword weight and the score corresponding to each keyword corresponding to each dialogue model, a weighted sum of the keyword weight and the score corresponding to each keyword corresponding to each dialogue model may be calculated as the score of the dialogue model. For example, according to the contents in the score table and the keyword weight table, when the keyword only includes "latest hotword" and "associated air 14", the score of the bi-directional two-layer LSTM + seq2seq model is 8 × 10+8 × 5 — 120, the score of the bert model is 5 × 10+8 × 5 — 90, and the score of the N-gram model is 8 + 10+5 × 5 — 105.
Therefore, the optional embodiment is implemented, the keyword weight value corresponding to each keyword corresponding to each dialogue model is obtained by querying the preset keyword weight value table, and the score corresponding to each dialogue model is calculated based on the keyword weight value corresponding to each keyword corresponding to each dialogue model and the score, so that the calculated score corresponding to each dialogue model is more accurate, a proper target dialogue model can be screened from the dialogue model library according to the score corresponding to each dialogue model, and the construction of the intelligent customer service robot is facilitated.
In an optional embodiment, the generating training data according to the construction information includes:
judging whether the construction information comprises preset data enhancement keywords or not;
and when the construction information is judged to comprise the data enhancement keywords, replacing the data enhancement keywords in the construction information with the expansion keywords corresponding to the data enhancement keywords to generate training data, wherein each data enhancement keyword is preset with at least one corresponding expansion keyword.
For small and medium-sized users, how to obtain enough training sample data when constructing the intelligent customer service robot is an important problem, so that when training data is generated according to construction information, data enhancement can be performed on the training data to realize amplification of the training data, thereby being beneficial to ensuring the sufficiency of the training data. Specifically, the data enhancement keywords in the construction information may be replaced with the extension keywords corresponding to the data enhancement keywords to generate the training data. If the construction information is "associate notebook computer configuration nvidiap10000 around xxxK", wherein "nvidiap 10000" is the data enhancement keyword, the data enhancement keyword "nvidiap 10000" is replaced by the expansion keywords "nvidia 6000" and "nividiaRTX 4000", so that the training data "associate notebook computer configuration nvidia 6000 around xxxK" and "associate notebook computer configuration nividiaRTX4000 around xxxK" can be obtained, and thus the training data is amplified. The data enhancement keywords can be preset by a user.
Therefore, when the optional embodiment is implemented, the training data is generated by replacing the data enhancement keywords in the construction information with the extension keywords corresponding to the data enhancement keywords when the training data is generated according to the construction information, so that the training data can be expanded, sufficient training data can be favorably ensured to train the target dialogue model, and the intelligent customer service robot can be successfully constructed.
In an optional embodiment, the method further comprises:
acquiring construction adjustment information of the intelligent customer service robot, wherein the construction adjustment information comprises intention information and answering information corresponding to a conversation node to be newly added in a conversation process;
generating construction adjustment training data based on the construction adjustment information;
and training the target dialogue model in the intelligent customer service robot again based on the construction adjustment training data so as to add the dialogue nodes newly added in the construction adjustment information into the dialogue process realized by the intelligent customer service robot.
After the intelligent customer service robot is built, the user can adjust the story line, and new conversation nodes are continuously added into the story line. Specifically, a storyline adjustment interface can be provided for the user at the front end, and the user can input intention information and answer information corresponding to the newly added conversation node in the storyline adjustment interface, so that acquisition of the constructed adjustment information can be realized. And finally, the newly generated construction adjustment training data is used for training the target dialogue model again, so that the target dialogue model has the capability of recognizing dialogue contents in the construction adjustment information, and the intelligent customer service robot can automatically complete the newly added dialogue nodes. For example, the number of session nodes that can be realized by the robot is only 2, and if a new session node is to be added, the story line needs to be adjusted, the training data needs to be generated again, and the model needs to be trained again, so that the model has the capability of recognizing the content of the new session node. The original dialogue model is trained according to the information of the first two dialogue nodes, so the original dialogue model does not usually have the capacity of identifying the content of a new dialogue node, and if a new node is added, the original dialogue model needs to be trained again to enable the dialogue model to have the capacity of identifying the content of the new dialogue node.
Therefore, by implementing the optional embodiment, after the intelligent customer service robot is built, the building adjustment information of the intelligent customer service robot is obtained, then the building adjustment training data is generated based on the building adjustment information, and finally the target dialogue model in the intelligent customer service robot is trained again based on the building adjustment training data, so that the target dialogue model has the capability of recognizing dialogue contents in the building adjustment information, the newly added function of dialogue nodes can be realized, the built intelligent customer service robot is more flexible in application, and can better adapt to more application scenes.
In an optional embodiment, the obtaining of the construction adjustment information of the intelligent customer service robot includes:
acquiring historical dialogue information of the intelligent customer service robot;
judging whether the historical dialogue information has no response dialogue information;
when the no-response dialogue information exists in the historical dialogue information, pushing the no-response dialogue information to a preset management terminal corresponding to the intelligent customer service robot;
receiving correct response information corresponding to the non-response dialog information returned by the management terminal, wherein the correct response information is correct response information made by a user of the management terminal according to the non-response dialog information;
and taking the non-response dialogue information and the correct response information as intention information and response information corresponding to the dialogue node to be added in the dialogue process so as to obtain the construction adjustment information of the intelligent customer service robot.
After the construction of the intelligent service robot is completed, the dialogue information (i.e., no-response dialogue information) that the intelligent service robot cannot normally and automatically respond to can be extracted from the dialogue information (i.e., historical dialogue information) generated by the intelligent service robot in actual use. Then, the dialog messages that the intelligent customer service robots cannot normally and automatically reply are pushed to a preset management terminal (such as a personal computer of a developer), a user (such as the developer) of the management terminal manually replies the dialog messages that the intelligent customer service robots cannot normally and automatically reply and returns corresponding correct response messages, and finally the no-response dialog messages and the correct response messages are used as intention messages and corresponding response messages corresponding to dialog nodes to be added in the dialog process so as to obtain construction adjustment messages. Therefore, the conversation process of the intelligent customer service robot can be adjusted according to the no-response conversation information of the intelligent customer service robot, so that the automatic improvement of the conversation process can be realized, and the use effect of the intelligent customer service robot is improved. In the historical dialogue information of the intelligent customer service robot, normal dialogue information usually exists in a form of one question and one answer between the robot and a user, if two or more continuous dialogue information sent by the user appears, the dialogue information is shown to be possibly the dialogue information which cannot be automatically answered normally by the intelligent customer service robot, and at the moment, the dialogue information can be extracted as the no-answer dialogue information.
Therefore, the optional embodiment is implemented, the no-response dialogue information is extracted from the historical dialogue information of the intelligent customer service robot, then the no-response dialogue information is manually responded to form correct response information corresponding to the no-response dialogue information, and finally the no-response dialogue information and the correct response information are used as intention information and response information corresponding to the dialogue node to be newly added in the dialogue process to obtain the constructed adjustment information, so that the dialogue process of the intelligent customer service robot can be adjusted according to the no-response dialogue information of the intelligent customer service robot, the automatic improvement of the dialogue process is realized, and the use effect of the intelligent customer service robot is improved.
Optionally, it is also possible: and uploading the construction information of the intelligent customer service robot of the construction method of the intelligent customer service robot to a block chain.
Specifically, the construction information of the intelligent customer service robot is obtained by operating the construction method of the intelligent customer service robot, and is used for recording the construction conditions of the intelligent customer service robot, such as intention information and answer information contained in the construction information, description information of the target dialogue model, training data, and the like. The construction information of the intelligent customer service robot is uploaded to the block chain, so that the safety and the just and transparency of the intelligent customer service robot to users can be guaranteed. The user can download the construction information of the intelligent customer service robot from the blockchain so as to verify whether the construction information of the intelligent customer service robot of the construction method of the intelligent customer service robot is tampered. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a construction apparatus of an intelligent customer service robot according to an embodiment of the present invention. As shown in fig. 2, the construction apparatus of the intelligent customer service robot may include:
an obtaining module 201, configured to obtain construction information of the intelligent customer service robot, where the construction information includes intention information and response information corresponding to each conversation node in a conversation process set by a user;
the screening module 202 is configured to screen a target conversation model from a preset conversation model library according to the construction information;
a generating module 203, configured to generate training data according to the construction information;
a training module 204, configured to train the target dialog model based on the training data;
a building module 205, configured to build an intelligent customer service robot based on the trained target dialogue model;
and the intelligent customer service robot is used for realizing the automation of the conversation process according to the intention information and the answering information in the construction information.
In an optional embodiment, the specific manner for the screening module 202 to screen the target dialog model from the preset dialog model library according to the construction information is as follows:
extracting keywords in the construction information through a preset keyword extraction algorithm;
calculating the corresponding score of each dialogue model in the dialogue model library according to the keyword;
and screening the dialogue models meeting preset grading conditions from the dialogue model library according to the grading of each dialogue model in the dialogue model library to serve as target dialogue models.
In an optional embodiment, the specific way for the screening module 202 to calculate the score corresponding to each dialogue model in the dialogue model library according to the keyword is as follows:
querying a preset scoring table to obtain a score of each keyword in each dialogue model, wherein the scoring table records the score of each keyword in each dialogue model;
and calculating the scores corresponding to the dialogue models according to the scores corresponding to all the keywords corresponding to each dialogue model.
In an optional embodiment, the specific way for the screening module 202 to calculate the score corresponding to each dialogue model according to the scores corresponding to all the keywords corresponding to each dialogue model is as follows:
querying a preset keyword weight table to obtain a keyword weight corresponding to each keyword corresponding to each dialogue model;
calculating the weighted sum of scores corresponding to all the keywords corresponding to each dialogue model to serve as the score corresponding to the dialogue model;
and the weight value of the score corresponding to each keyword corresponding to each dialogue model is the weight value of the keyword corresponding to the keyword. In an optional embodiment, a specific manner for the generating module 203 to generate the training data according to the construction information is as follows:
judging whether the construction information comprises preset data enhancement keywords or not;
and when the construction information is judged to comprise the data enhancement keywords, replacing the data enhancement keywords in the construction information with the expansion keywords corresponding to the data enhancement keywords to generate training data, wherein each data enhancement keyword is preset with at least one corresponding expansion keyword.
In an optional embodiment, the obtaining module 201 is further configured to obtain construction adjustment information of the intelligent customer service robot, where the construction adjustment information includes intention information and response information corresponding to a dialog node to be newly added in a dialog process;
the generating module 203 is further configured to generate construction adjustment training data based on the construction adjustment information;
the training module 204 is further configured to train the target session model in the intelligent customer service robot again based on the construction adjustment training data, so as to add a new session node in the construction adjustment information to a session flow implemented by the intelligent customer service robot.
In an optional embodiment, the specific manner for the obtaining module 201 to obtain the construction adjustment information of the intelligent customer service robot is as follows:
acquiring historical dialogue information of the intelligent customer service robot;
judging whether the historical dialogue information has no response dialogue information;
when the no-response dialogue information exists in the historical dialogue information, pushing the no-response dialogue information to a preset management terminal corresponding to the intelligent customer service robot;
receiving correct response information corresponding to the non-response dialog information returned by the management terminal, wherein the correct response information is correct response information made by a user of the management terminal according to the non-response dialog information;
and taking the non-response dialogue information and the correct response information as intention information and response information corresponding to the dialogue node to be added in the dialogue process so as to obtain the construction adjustment information of the intelligent customer service robot.
For the specific description of the construction apparatus of the intelligent customer service robot, reference may be made to the specific description of the construction method of the intelligent customer service robot, and for avoiding repetition, details are not repeated here.
EXAMPLE III
Referring to fig. 3, fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown in fig. 3, the computer apparatus may include:
a memory 301 storing executable program code;
a processor 302 connected to the memory 301;
the processor 302 calls the executable program code stored in the memory 301 to execute the steps in the method for constructing the intelligent customer service robot disclosed in the embodiment of the present invention.
Example four
Referring to fig. 4, an embodiment of the present invention discloses a computer storage medium 401, where the computer storage medium 401 stores computer instructions, and the computer instructions are used to execute steps in a method for constructing an intelligent customer service robot disclosed in an embodiment of the present invention when the computer instructions are called.
The above-described embodiments of the apparatus are merely illustrative, and the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above detailed description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on such understanding, the above technical solutions may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, where the storage medium includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc-Read-Only Memory (CD-ROM), or other disk memories, CD-ROMs, or other magnetic disks, A tape memory, or any other medium readable by a computer that can be used to carry or store data.
Finally, it should be noted that: the construction method, apparatus, computer device and storage medium for an intelligent customer service robot disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used for illustrating the technical solutions of the present invention, not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for constructing an intelligent customer service robot is characterized by comprising the following steps:
acquiring construction information of the intelligent customer service robot, wherein the construction information comprises intention information and answering information corresponding to each conversation node in a conversation process set by a user;
screening a target dialogue model from a preset dialogue model library according to the construction information;
generating training data according to the construction information;
training the target dialog model based on the training data;
constructing an intelligent customer service robot based on the trained target dialogue model;
and the intelligent customer service robot is used for realizing the automation of the conversation process according to the intention information and the answering information in the construction information.
2. The method for constructing an intelligent customer service robot according to claim 1, wherein the step of screening out the target dialogue model from a preset dialogue model library according to the construction information comprises the following steps:
extracting keywords in the construction information through a preset keyword extraction algorithm;
calculating the corresponding score of each dialogue model in the dialogue model library according to the keyword;
and screening the dialogue models meeting preset grading conditions from the dialogue model library according to the grading of each dialogue model in the dialogue model library to serve as target dialogue models.
3. The method for constructing an intelligent customer service robot according to claim 2, wherein the calculating a score corresponding to each dialogue model in the dialogue model library according to the keyword comprises:
querying a preset scoring table to obtain a score of each keyword in each dialogue model, wherein the scoring table records the score of each keyword in each dialogue model;
and calculating the scores corresponding to the dialogue models according to the scores corresponding to all the keywords corresponding to each dialogue model.
4. The method for constructing an intelligent customer service robot according to claim 3, wherein the calculating scores corresponding to each dialogue model according to the scores corresponding to all keywords corresponding to the dialogue model comprises:
querying a preset keyword weight table to obtain a keyword weight corresponding to each keyword corresponding to each dialogue model;
calculating the weighted sum of scores corresponding to all the keywords corresponding to each dialogue model to serve as the score corresponding to the dialogue model;
and the weight value of the score corresponding to each keyword corresponding to each dialogue model is the weight value of the keyword corresponding to the keyword.
5. The method for constructing an intelligent customer service robot according to any one of claims 1-4, wherein the generating training data according to the construction information comprises:
judging whether the construction information comprises preset data enhancement keywords or not;
and when the construction information is judged to comprise the data enhancement keywords, replacing the data enhancement keywords in the construction information with the expansion keywords corresponding to the data enhancement keywords to generate training data, wherein each data enhancement keyword is preset with at least one corresponding expansion keyword.
6. The method of constructing an intelligent customer service robot according to any one of claims 1-4, wherein the method further comprises:
acquiring construction adjustment information of the intelligent customer service robot, wherein the construction adjustment information comprises intention information and answering information corresponding to a conversation node to be newly added in a conversation process;
generating construction adjustment training data based on the construction adjustment information;
and training the target dialogue model in the intelligent customer service robot again based on the construction adjustment training data so as to add the dialogue nodes newly added in the construction adjustment information into the dialogue process realized by the intelligent customer service robot.
7. The method of claim 6, wherein the obtaining of the configuration adjustment information of the intelligent customer service robot comprises:
acquiring historical dialogue information of the intelligent customer service robot;
judging whether the historical dialogue information has no response dialogue information;
when the no-response dialogue information exists in the historical dialogue information, pushing the no-response dialogue information to a preset management terminal corresponding to the intelligent customer service robot;
receiving correct response information corresponding to the non-response dialog information returned by the management terminal, wherein the correct response information is correct response information made by a user of the management terminal according to the non-response dialog information;
and taking the non-response dialogue information and the correct response information as intention information and response information corresponding to the dialogue node to be added in the dialogue process so as to obtain the construction adjustment information of the intelligent customer service robot.
8. An apparatus for constructing an intelligent customer service robot, the apparatus comprising:
the intelligent customer service robot system comprises an acquisition module, a judgment module and a display module, wherein the acquisition module is used for acquiring construction information of the intelligent customer service robot, and the construction information comprises intention information and answering information which are set by a user and correspond to each conversation node in a conversation process;
the screening module is used for screening a target conversation model from a preset conversation model library according to the construction information;
the generating module is used for generating training data according to the construction information;
a training module to train the target dialog model based on the training data;
the building module is used for building the intelligent customer service robot based on the trained target dialogue model;
and the intelligent customer service robot is used for realizing the automation of the conversation process according to the intention information and the answering information in the construction information.
9. A computer device, characterized in that the computer device comprises:
a memory storing executable program code;
a processor coupled to the memory;
the processor calls the executable program code stored in the memory to execute the construction method of the intelligent customer service robot according to any one of claims 1-7.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out a method of constructing an intelligent customer service robot according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110845373.9A CN113486166B (en) | 2021-07-26 | 2021-07-26 | Construction method, device and equipment of intelligent customer service robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110845373.9A CN113486166B (en) | 2021-07-26 | 2021-07-26 | Construction method, device and equipment of intelligent customer service robot and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113486166A true CN113486166A (en) | 2021-10-08 |
| CN113486166B CN113486166B (en) | 2023-09-05 |
Family
ID=77943770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110845373.9A Active CN113486166B (en) | 2021-07-26 | 2021-07-26 | Construction method, device and equipment of intelligent customer service robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113486166B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116303979A (en) * | 2023-05-18 | 2023-06-23 | 北京及时语智能科技有限公司 | Intelligent customer service dialogue model construction method and system |
| CN117370535A (en) * | 2023-12-05 | 2024-01-09 | 粤港澳大湾区数字经济研究院(福田) | Training method of medical dialogue model, medical query method, device and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472035A (en) * | 2019-08-26 | 2019-11-19 | 杭州城市大数据运营有限公司 | A kind of intelligent response method, apparatus, computer equipment and storage medium |
| CN111400465A (en) * | 2020-02-25 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Generation method and device of customer service robot, electronic equipment and medium |
| WO2020148355A1 (en) * | 2019-01-17 | 2020-07-23 | Koninklijke Philips N.V. | A system for multi-perspective discourse within a dialog |
-
2021
- 2021-07-26 CN CN202110845373.9A patent/CN113486166B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020148355A1 (en) * | 2019-01-17 | 2020-07-23 | Koninklijke Philips N.V. | A system for multi-perspective discourse within a dialog |
| CN110472035A (en) * | 2019-08-26 | 2019-11-19 | 杭州城市大数据运营有限公司 | A kind of intelligent response method, apparatus, computer equipment and storage medium |
| CN111400465A (en) * | 2020-02-25 | 2020-07-10 | 支付宝(杭州)信息技术有限公司 | Generation method and device of customer service robot, electronic equipment and medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116303979A (en) * | 2023-05-18 | 2023-06-23 | 北京及时语智能科技有限公司 | Intelligent customer service dialogue model construction method and system |
| CN117370535A (en) * | 2023-12-05 | 2024-01-09 | 粤港澳大湾区数字经济研究院(福田) | Training method of medical dialogue model, medical query method, device and equipment |
| CN117370535B (en) * | 2023-12-05 | 2024-04-16 | 粤港澳大湾区数字经济研究院(福田) | Training method of medical dialogue model, medical query method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113486166B (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287479B (en) | Named entity recognition method, electronic device and storage medium | |
| JP6799574B2 (en) | Method and device for determining satisfaction with voice dialogue | |
| CN109360550B (en) | Testing method, device, equipment and storage medium of voice interaction system | |
| CN104598445B (en) | Automatically request-answering system and method | |
| CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
| CN106534548B (en) | Voice error correction method and device | |
| WO2022095380A1 (en) | Ai-based virtual interaction model generation method and apparatus, computer device and storage medium | |
| CN101645088B (en) | Determine the method for auxiliary lexicon, device and the input method system that need to load | |
| CN110781668B (en) | Text information type identification method and device | |
| CN111625632A (en) | Question-answer pair recommendation method, device, equipment and storage medium | |
| US20140046876A1 (en) | System and method of providing a computer-generated response | |
| CN109284502B (en) | Text similarity calculation method and device, electronic equipment and storage medium | |
| CN112836691A (en) | Intelligent interviewing method and device | |
| CN107071193A (en) | The method and apparatus of interactive answering system accessing user | |
| CN113486166A (en) | Method, device and equipment for constructing intelligent customer service robot and storage medium | |
| US20220138770A1 (en) | Method and apparatus for analyzing sales conversation based on voice recognition | |
| CN116303949B (en) | Dialogue processing method, dialogue processing system, storage medium and terminal | |
| CN109582788A (en) | Comment spam training, recognition methods, device, equipment and readable storage medium storing program for executing | |
| CN112699658A (en) | Text comparison method and related device | |
| CN112699645A (en) | Corpus labeling method, apparatus and device | |
| CN111259124A (en) | Dialogue management method, device, system and storage medium | |
| CN113342948A (en) | Intelligent question and answer method and device | |
| CN113032520A (en) | Information analysis method and device, electronic equipment and computer readable storage medium | |
| CN113297365A (en) | User intention determination method, device, equipment and storage medium | |
| WO2021135322A1 (en) | Automatic question setting method, apparatus and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |