CN115905187B - Intelligent proposition system oriented to cloud computing engineering technician authentication - Google Patents
Intelligent proposition system oriented to cloud computing engineering technician authentication Download PDFInfo
- Publication number
- CN115905187B CN115905187B CN202310121790.8A CN202310121790A CN115905187B CN 115905187 B CN115905187 B CN 115905187B CN 202310121790 A CN202310121790 A CN 202310121790A CN 115905187 B CN115905187 B CN 115905187B
- Authority
- CN
- China
- Prior art keywords
- reply
- user
- real
- module
- chat robot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012360 testing method Methods 0.000 claims abstract description 52
- 230000008451 emotion Effects 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000003058 natural language processing Methods 0.000 claims description 6
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent proposition system oriented to cloud computing engineering technician authentication, which comprises a cloud computing engineering technical question bank, a group paper module, a test paper difficulty output module, a duplicate checking module, a user feedback module, an exchange module and an intention recognition module. According to the invention, the knowledge graph of the pre-constructed historical proposition data is utilized when propositions are generated, so that when a user searches related historical propositions, the user can walk upstream of the constructed knowledge graph to find a plurality of historical propositions related to the new propositions, and compared with the conventional keyword search, the semantic search is fully utilized to search, so that the search efficiency is higher; the proposition feedback information of the user can be obtained, and meanwhile, the chat willingness of the chat robot can be increased by judging the rationality of the real-time reply of the chat robot in the chat process of the robot and the user; and the chat robot is subjected to diversity training and emotion expression evaluation, so that the chat robot is more personified when chatting with a user.
Description
Technical Field
The invention relates to the technical field of propositions, in particular to an intelligent propositions system oriented to cloud computing engineering technician authentication.
Background
Cloud computing engineering technicians refer to engineering technicians engaged in cloud computing technology research, cloud system construction, deployment, operation and maintenance, cloud resource management, applications and services. Cloud computing technology plays an increasingly important role in modern society, economy and life, and particularly plays an increasingly important role in various fields such as big data application, human-computer intelligent, intelligent home, logistics transportation, government affairs handling, medical service and the like. Personnel in the field have huge employment market and have wide employment prospect, so that an intelligent proposition system facing the authentication of cloud computing engineering technicians needs to be designed. However, the existing related proposition system lacks an intelligent means when searching the historical propositions, for example, a knowledge graph tool in the existing artificial intelligence field is not used, so that the searching efficiency is low.
For example, chinese patent 202010856601.8 discloses a method and a system for analyzing and processing propositions based on deep learning, which combine a history examination proposition outline and history hot point propositions information to determine propositions corresponding to the same type of propositions, so as to obtain and display corresponding prediction propositions information, thereby forming a reliable test paper quickly and accurately, and being convenient for comprehensively checking the learning effect of students. However, the proposition system has the following disadvantages: when proposing related exams, for example, the proposition system determines the propositions of the same type from the historical propositions data or searches the propositions again, the propositions are generally searched in a keyword searching mode, and the searching mode ignores semantic information, so that the searching efficiency is low and the intellectualization is insufficient during searching. In addition, when the proposition system is opened to users, feedback information of the users needs to be obtained, and the existing proposition system has only proposition functions and cannot communicate with the users.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides an intelligent proposition system oriented to cloud computing engineering technical personnel authentication so as to overcome the technical problems existing in the related art.
For this purpose, the invention adopts the following specific technical scheme:
an intelligent proposition system oriented to cloud computing engineering technician authentication comprises a cloud computing engineering technical question bank, a group paper module, a test paper difficulty output module, a duplicate checking module, a user feedback module, an exchange module and an intention recognition module;
the cloud computing engineering technical question bank is used for constructing an examination question bank according to national professional technical skill standards of cloud computing engineering technicians, respectively establishing sub question banks for each cloud computing engineering technical examination grade, simultaneously storing the examination questions in the corresponding sub question banks, setting four difficulty areas in each sub question bank, and setting the questions in the corresponding difficulty areas to have corresponding difficulty scores;
the test paper group module is used for automatically or manually selecting test questions of the cloud computing engineering technical question bank to form test papers, and selecting a certain number of test questions according to the set total difficulty score when automatically selecting the test questions of the cloud computing engineering technical question bank, namely the total sum of the difficulty scores of each test question is equal to the total difficulty score of the test papers;
the test paper difficulty output module is used for automatically calculating the difficulty score of the test paper and displaying the difficulty score to a user after manually selecting the test paper formed by the cloud computing engineering technical problem library;
the duplicate checking module is used for determining the same type propositions in the test questions of the propositions from the historical propositions data and realizing duplicate checking processing of the propositions;
the user feedback module is used for acquiring feedback information of the user after using the proposition system, setting a user satisfaction degree scoring function and guiding the user to perform satisfaction degree scoring;
the communication module is used for communicating with a user through the robot and acquiring proposition feedback information of the user;
the intention recognition module is used for recognizing the feedback information of the user in the user feedback module and the communication module to obtain the actual intention of the user.
Further, after the test paper is formed by automatically or manually selecting the test questions of the cloud computing engineering technical question bank, the total score of the test paper is a determined value, the question score of each test question is a determined value, and the total score of all the test questions is equal to the total score of the test paper.
Further, before the same type of propositions in the test questions of the propositions are determined from the historical propositions, the historical propositions are processed by utilizing a knowledge graph and a natural language processing technology.
Further, the processing of the historical proposition data by using the knowledge graph and the natural language processing technology comprises the following steps:
constructing a knowledge graph of historical propositional data based on the Neo4j graph database;
each historical proposition data is expressed as a graph node on the knowledge graph, and the graph nodes are connected by combining metadata information;
if the user inquires about the relevant historical propositions of any new propositions, the user can walk upstream of the constructed knowledge graph to find a plurality of historical propositions related to the new propositions.
Further, the graph nodes on the knowledge graph further comprise knowledge documents, URLs, topics and experience training related to historical propositions.
Further, the communication module comprises a chat robot module, a reply rationality evaluation module, a diversity judgment module and an emotion ability evaluation module:
the chat robot module is used for timely communicating with the user through the chat robot when the user needs to exchange feedback, and inputting the exchange feedback information in a voice or text mode when the user exchanges feedback;
the reply rationality evaluation module is used for comparing the real-time reply of the chat robot with the reference reply when the chat robot replies the communication feedback information of the user, and judging whether the real-time reply of the chat robot has rationality or not;
the diversity judging module is used for judging the diversity of real-time replies of the chat robot;
the emotion capacity evaluation module is used for evaluating emotion accuracy of real-time replies of the chat robot.
Further, the comparing the real-time reply of the chat robot with the reference reply to determine whether the real-time reply of the chat robot has reasonability includes the following steps:
acquiring Word vectors of each Word in the real-time reply and the reference reply through Word2Vec Word vectors;
presetting a similarity reference score, calculating a similarity score between the real-time reply and the reference reply of the chat robot, if the similarity score is greater than or equal to the similarity reference score, returning the chat robot in real time to a reasonable reply, and if the similarity score is less than the similarity reference score, returning the chat robot in real time to an unreasonable reply;
when the similarity score between the real-time reply and the reference reply of the chat robot is calculated, after each word in the reference reply is converted into a word vector, the word vector of each word in the real-time reply is matched through a cosine function:
in the method, in the process of the invention,
is->
Respectively reference replies and real-time replies;
carrying out bidirectional greedy matching on the real-time reply and the reference reply of the chat robot to obtain a similarity score between the real-time reply and the reference reply of the chat robot:
in the method, in the process of the invention,
is->
The reference replies and the real-time replies are respectively.
Further, when the diversity judgment is performed on the real-time reply of the chat robot, the number of single words and double words in the real-time reply of the chat robot is calculated, and the sentences in the real-time reply are scaled.
Further, when the emotion accuracy evaluation is carried out on the real-time reply of the chat robot, a reply data set with emotion marking is constructed, emotion reflected in the reply data set is identified by using a Bi-LSTM classifier, and corresponding marking is carried out at the same time;
predicting the real-time reply of the chat robot by using the Bi-LSTM classifier, and calculating whether the emotion types of the reference reply and the real-time reply are consistent or not to obtain the emotion expression consistency of the chat robot.
Further, the user feedback module and the feedback information of the user in the communication module are identified, when the actual intention of the user is obtained, the feedback information is input into an intention identification model for intention identification, and the intention identification model is trained by a training set consisting of training text content and intention identification results;
when the training text content is constructed, randomly replacing entity words in the training text content with homonyms or similar words, and adding the replaced results into the training text content again;
and if the feedback information of the user comprises voice information, converting the voice information into text information.
The beneficial effects of the invention are as follows:
(1) According to the intelligent proposition system oriented to cloud computing engineering technician authentication, by utilizing the knowledge graph of the pre-constructed historical proposition data when propositions are performed, when a user searches related historical propositions, the user can walk on the upstream of the constructed knowledge graph to find a plurality of historical propositions related to the new propositions, and compared with conventional keyword searching, semantics are fully utilized for searching, so that the searching efficiency is higher.
(2) According to the invention, through acquiring the feedback information of the user after using the proposition system and communicating with the user through the robot, the proposition feedback information of the user is acquired, so that the problems, questions, suggestions and the like when the user uses the proposition system can be acquired, the intention recognition is carried out on the feedback information, and the intention in the feedback of the user is further known; in the chat process of the robot and the user, the rationality of real-time reply of the chat robot is judged, so that the chat willingness of the chat robot can be increased; and the chat robot is subjected to diversity training and emotion expression evaluation, so that the chat robot is more personified when chatting with a user.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a functional block diagram of an intelligent proposition system oriented to cloud computing engineering technician authentication according to an embodiment of the present invention.
In the figure:
1. cloud computing engineering technical question bank; 2. a winding module; 3. the test paper difficulty output module; 4. a weight checking module; 5. a user feedback module; 6. an exchange module; 7. an intention recognition module.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used to illustrate the embodiments and, together with the description, serve to explain the principles of the embodiments, and with reference to these descriptions, one skilled in the art will recognize other possible implementations and advantages of the present invention, wherein elements are not drawn to scale, and like reference numerals are generally used to designate like elements.
According to the embodiment of the invention, an intelligent proposition system oriented to cloud computing engineering technician authentication is provided.
Referring to the drawings and the specific embodiments, as shown in fig. 1, the intelligent proposition system for cloud computing engineering technician authentication according to the embodiment of the invention comprises a cloud computing engineering technical problem library 1, a group paper module 2, a test paper difficulty output module 3, a check and replay module 4, a user feedback module 5, an exchange module 6 and an intention recognition module 7;
the cloud computing engineering technical question bank 1 is used for constructing an examination question bank according to national professional technical skill standards of cloud computing engineering technicians, respectively establishing a sub question bank for each cloud computing engineering technical examination grade, simultaneously storing the examination questions in the corresponding sub question bank, and setting four difficulty areas (the difficulty values are one-minute difficulty, two-minute difficulty, three-minute difficulty and four-minute difficulty) in each sub question bank, wherein the questions in the corresponding difficulty areas have corresponding difficulty scores;
the paper assembly module 2 is used for automatically or manually selecting the questions of the cloud computing engineering technical question bank to form the paper, and selecting a certain number of the questions according to the set total difficulty score when automatically selecting the questions of the cloud computing engineering technical question bank, namely, the total sum of the difficulty scores of each question is equal to the total difficulty score of the paper;
in one embodiment, after the test questions of the cloud computing engineering technical question library are automatically or manually selected to form the test paper, the total score of the test paper is a determined value, the question score of each test question is a determined value, and the total score of all the test questions is equal to the total score of the test paper.
The test paper difficulty output module 3 is used for automatically calculating the difficulty score of the test paper and displaying the difficulty score to a user after manually selecting the test paper formed by the cloud computing engineering technical problem library;
the searching and repeating module 4 is used for determining the same types of propositions in the test questions of the propositions from the historical propositions data and realizing searching and repeating processing of the propositions;
in one embodiment, before the same type of propositions in the test questions of the propositions are determined from the historical propositions data, the historical propositions data are processed by using a knowledge graph and a natural language processing technology.
In one embodiment, the processing of the historical proposition data using knowledge graph and natural language processing techniques includes the steps of:
constructing a knowledge graph of historical propositional data based on the Neo4j graph database;
each historical proposition data is expressed as a graph node on the knowledge graph, and the graph nodes are connected by combining metadata information;
if the user inquires about the relevant historical propositions of any new propositions, the user can walk upstream of the constructed knowledge graph to find a plurality of historical propositions related to the new propositions. Neo4j is an open source NoSql graph database implemented by Java that provides complete database features including ACID transaction support, cluster support, backup and failover, etc. Neo4j supports the function of searching the shortest path and all paths as long as the input start-stop node can get the desired result.
In one embodiment, the graph nodes on the knowledge graph further comprise knowledge documents, URLs (uniform resource locators), topics, experience training and the like related to historical propositions.
The user feedback module 5 is used for acquiring feedback information of the user after using the proposition system, setting a user satisfaction degree scoring function and guiding the user to perform satisfaction degree scoring;
the communication module 6 is used for communicating with a user through the robot to acquire proposition feedback information of the user;
in one embodiment, the communication module includes a chat robot module, a reply rationality evaluation module, a diversity judgment module, and an emotion ability evaluation module:
the chat robot module is used for timely communicating with the user through the chat robot when the user needs to exchange feedback, and inputting the exchange feedback information in a voice or text mode when the user exchanges feedback;
the reply rationality evaluation module is used for comparing the real-time reply of the chat robot with the reference reply when the chat robot replies the communication feedback information of the user, and judging whether the real-time reply of the chat robot has rationality or not;
the diversity judging module is used for judging the diversity of real-time replies of the chat robot;
the emotion capacity evaluation module is used for evaluating emotion accuracy of real-time replies of the chat robot.
In one embodiment, the comparing the real-time reply to the chat robot with the reference reply to determine whether the real-time reply of the chat robot is reasonable includes the following steps:
acquiring Word vectors of each Word in the real-time reply and the reference reply through Word2Vec Word vectors;
presetting a similarity reference score, calculating a similarity score between the real-time reply and the reference reply of the chat robot, if the similarity score is greater than or equal to the similarity reference score, returning the chat robot in real time to a reasonable reply, and if the similarity score is less than the similarity reference score, returning the chat robot in real time to an unreasonable reply;
when the similarity score between the real-time reply and the reference reply of the chat robot is calculated, after each word in the reference reply is converted into a word vector, the word vector of each word in the real-time reply is matched through a cosine function:
in the method, in the process of the invention,
is->
Respectively reference replies and real-time replies;
carrying out bidirectional greedy matching on the real-time reply and the reference reply of the chat robot to obtain a similarity score between the real-time reply and the reference reply of the chat robot:
in the method, in the process of the invention,
is->
The reference replies and the real-time replies are respectively. The higher the similarity score is, the more reasonable the real-time reply of the chat robot is, and besides the cosine function matching mode, the method can also be used for representing by a word moving distance method and a sentence moving similarity method. The invention can increase the chat wish with the chat robot by judging the rationality of the real-time reply of the chat robot in the chat process of the robot and the user.
Word2Vec is a method for converting words into vectors, and in the process of obtaining Word vectors of each Word in real-time replies and reference replies through Word2Vec Word vectors, jieba Word segmentation can be adopted to segment the real-time replies and the reference replies.
In one embodiment, when the diversity judgment is performed on the real-time reply of the chat robot, the number of single words (unigram) and double words (big-ram) in the real-time reply of the chat robot is calculated, and the sentences in the real-time reply are scaled.
In one embodiment, the method for performing diversity judgment on the real-time reply of the chat robot further includes an entropy measurement method, and performing entropy value calculation on the real-time reply of the chat robot:
in the method, in the process of the invention,
for real-time reply +_>
For the number of words in real-time reply, +.>
The probability is generated for each word in the real-time reply.
In one embodiment, when the emotion accuracy evaluation is performed on the real-time reply of the chat robot, a reply data set with emotion marking is constructed, emotion reflected in the reply data set is identified by using a Bi-LSTM classifier, and corresponding marking is performed at the same time;
predicting the real-time reply of the chat robot by using the Bi-LSTM classifier, and calculating whether the emotion types of the reference reply and the real-time reply are consistent or not to obtain the emotion expression consistency of the chat robot. The Bi-LSTM is an extension of the LSTM model, bi-LSTM uses a double-layer LSTM layer, and in the conventional recurrent neural network model and the LSTM model, information can only propagate forward, so that the state of time t only depends on text information before time t, and in order to make each moment more completely contain the context information, bi-LSTM composed of LSTM neurons and a Bi-directional recurrent neural network (BiRNN) model can be used to capture the context information, that is, the Bi-LSTM model treats all inputs equally.
The intention recognition module 7 is configured to recognize feedback information of the user in the user feedback module 5 and the communication module 6, and obtain an actual intention of the user.
In one embodiment, the identifying the feedback information of the user in the user feedback module and the communication module, when obtaining the actual intention of the user, inputting the feedback information into an intention identifying model for intention identification, wherein the intention identifying model is trained by a training set consisting of training text content and intention identifying results;
when the training text content is constructed, randomly replacing entity words in the training text content with homonyms or similar words, and adding the replaced results into the training text content again;
and if the feedback information of the user comprises voice information, converting the voice information into text information.
In converting speech information to text information, speech recognition is required, and the goal of speech recognition technology is to convert the lexical content in human speech into computer-readable input. The voice recognition comprises three basic units of feature extraction, pattern matching, reference pattern library and the like; the voice information to be recognized is converted into an electric signal and then added to the input end of voice recognition, after pretreatment, a voice model is established according to the voice characteristics of a person, the input voice information is analyzed, the required characteristics are extracted, and a voice recognition template is established;
according to the voice recognition model, comparing the input voice information with the voice recognition template, finding a series of optimal voice recognition templates matched with the input voice information, and giving a recognition result according to the definition of the voice recognition templates.
In summary, according to the intelligent proposition system oriented to cloud computing engineering technician authentication, by utilizing the knowledge graph of the pre-constructed historical proposition data when propositions are generated, when a user searches for related historical propositions, the user can walk upstream of the constructed knowledge graph to find a plurality of historical propositions related to the new propositions, and compared with conventional keyword searching, the intelligent propositions system fully utilizes semantics to search, so that the searching efficiency is higher. According to the invention, through acquiring the feedback information of the user after using the proposition system and communicating with the user through the robot, the proposition feedback information of the user is acquired, so that the problems, questions, suggestions and the like when the user uses the proposition system can be acquired, the intention recognition is carried out on the feedback information, and the intention in the feedback of the user is further known; in the chat process of the robot and the user, the rationality of real-time reply of the chat robot is judged, so that the chat willingness of the chat robot can be increased; and the chat robot is subjected to diversity training and emotion expression evaluation, so that the chat robot is more personified when chatting with a user.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (4)
1. An intelligent proposition system oriented to cloud computing engineering technician authentication is characterized by comprising a cloud computing engineering technical question bank, a group paper module, a test paper difficulty output module, a duplicate checking module, a user feedback module, an exchange module and an intention recognition module;
the cloud computing engineering technical question bank is used for constructing an examination question bank according to national professional technical skill standards of cloud computing engineering technicians, respectively establishing sub question banks for each cloud computing engineering technical examination grade, simultaneously storing the examination questions in the corresponding sub question banks, setting four difficulty areas in each sub question bank, and setting the questions in the corresponding difficulty areas to have corresponding difficulty scores;
the test paper group module is used for automatically or manually selecting test questions of the cloud computing engineering technical question bank to form test papers, and selecting a certain number of test questions according to the set total difficulty score when automatically selecting the test questions of the cloud computing engineering technical question bank, namely the total sum of the difficulty scores of each test question is equal to the total difficulty score of the test papers;
the test paper difficulty output module is used for automatically calculating the difficulty score of the test paper and displaying the difficulty score to a user after manually selecting the test paper formed by the cloud computing engineering technical problem library;
the duplicate checking module is used for determining the same type propositions in the test questions of the propositions from the historical propositions data and realizing duplicate checking processing of the propositions;
the user feedback module is used for acquiring feedback information of the user after using the proposition system, setting a user satisfaction degree scoring function and guiding the user to perform satisfaction degree scoring;
the communication module is used for communicating with a user through the robot and acquiring proposition feedback information of the user;
the intention recognition module is used for recognizing the feedback information of the user in the user feedback module and the communication module to obtain the actual intention of the user;
before the same type propositions in the test questions of the propositions are determined from the historical propositions data, the historical propositions data are processed by utilizing a knowledge graph and natural language processing technology;
the method for processing the historical proposition data by utilizing the knowledge graph and natural language processing technology comprises the following steps:
constructing a knowledge graph of historical propositional data based on the Neo4j graph database;
each historical proposition data is expressed as a graph node on the knowledge graph, and the graph nodes are connected by combining metadata information;
if the user inquires about the relevant historical propositions of any new propositions, the user can walk on the upstream of the constructed knowledge graph to find a plurality of historical propositions related to the new propositions;
the communication module comprises a chat robot module, a reply rationality evaluation module, a diversity judgment module and an emotion ability evaluation module:
the chat robot module is used for timely communicating with the user through the chat robot when the user needs to exchange feedback, and inputting the exchange feedback information in a voice or text mode when the user exchanges feedback;
the reply rationality evaluation module is used for comparing the real-time reply of the chat robot with the reference reply when the chat robot replies the communication feedback information of the user, and judging whether the real-time reply of the chat robot has rationality or not;
the diversity judging module is used for judging the diversity of real-time replies of the chat robot; when the real-time reply of the chat robot is subjected to diversity judgment, the number of single words and double words in the real-time reply of the chat robot is calculated, and sentences in the real-time reply are scaled;
the emotion capacity evaluation module is used for evaluating emotion accuracy of real-time replies of the chat robot;
the comparison of the real-time reply of the chat robot with the reference reply, and the judgment of whether the real-time reply of the chat robot has rationality comprises the following steps:
acquiring Word vectors of each Word in the real-time reply and the reference reply through Word2Vec Word vectors;
presetting a similarity reference score, calculating a similarity score between the real-time reply and the reference reply of the chat robot, if the similarity score is greater than or equal to the similarity reference score, returning the chat robot in real time to a reasonable reply, and if the similarity score is less than the similarity reference score, returning the chat robot in real time to an unreasonable reply;
when the similarity score between the real-time reply and the reference reply of the chat robot is calculated, after each word in the reference reply is converted into a word vector, the word vector of each word in the real-time reply is matched through a cosine function:
in the method, in the process of the invention,
is->
Respectively reference replies and real-time replies;
carrying out bidirectional greedy matching on the real-time reply and the reference reply of the chat robot to obtain a similarity score between the real-time reply and the reference reply of the chat robot:
in the method, in the process of the invention,
is->
Respectively reference replies and real-time replies;
when the emotion accuracy evaluation is carried out on the real-time reply of the chat robot, a reply data set with emotion marking is constructed, emotion reflected in the reply data set is identified by using a Bi-LSTM classifier, and corresponding marking is carried out at the same time;
predicting the real-time reply of the chat robot by using the Bi-LSTM classifier, and calculating whether the emotion types of the reference reply and the real-time reply are consistent or not to obtain the emotion expression consistency of the chat robot.
2. The intelligent proposition system for cloud computing engineering personnel authentication according to claim 1, wherein after the test papers are formed by automatically or manually selecting the questions of the cloud computing engineering technical question bank, the total score of the test papers is a determined value, the question score of each test paper is a determined value, and the total score of all the test papers is equal to the total score of the test papers.
3. The intelligent proposition system for cloud computing engineering technician authentication of claim 1, wherein the graph nodes on the knowledge graph further comprise knowledge documents, URLs, topics and experience training related to historical propositions.
4. The intelligent proposition system for cloud computing engineering technician authentication according to claim 1, wherein the user feedback module and the feedback information of the user in the communication module are identified, when the actual intention of the user is obtained, the feedback information is input into an intention recognition model for intention recognition, and the intention recognition model is trained by a training set consisting of training text content and intention recognition results;
when the training text content is constructed, randomly replacing entity words in the training text content with homonyms or similar words, and adding the replaced results into the training text content again;
and if the feedback information of the user comprises voice information, converting the voice information into text information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310121790.8A CN115905187B (en) | 2023-02-16 | 2023-02-16 | Intelligent proposition system oriented to cloud computing engineering technician authentication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310121790.8A CN115905187B (en) | 2023-02-16 | 2023-02-16 | Intelligent proposition system oriented to cloud computing engineering technician authentication |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115905187A CN115905187A (en) | 2023-04-04 |
| CN115905187B true CN115905187B (en) | 2023-05-30 |
Family
ID=85744707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310121790.8A Active CN115905187B (en) | 2023-02-16 | 2023-02-16 | Intelligent proposition system oriented to cloud computing engineering technician authentication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115905187B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117373658B (en) * | 2023-12-08 | 2024-03-08 | 北京回龙观医院(北京心理危机研究与干预中心) | Data processing-based auxiliary diagnosis and treatment system and method for depression |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574241A (en) * | 2015-02-03 | 2015-04-29 | 陈飞鸣 | Online education assessment system and method |
| CN110135551B (en) * | 2019-05-15 | 2020-07-21 | 西南交通大学 | Robot chatting method based on word vector and recurrent neural network |
| CN112131407A (en) * | 2020-09-29 | 2020-12-25 | 四川宇德中创信息科技有限公司 | Intelligent paper making system and method based on knowledge graph |
-
2023
- 2023-02-16 CN CN202310121790.8A patent/CN115905187B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115905187A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110377911B (en) | Method and device for identifying intention under dialog framework | |
| CN110096570B (en) | Intention identification method and device applied to intelligent customer service robot | |
| CN112231447B (en) | Method and system for extracting Chinese document events | |
| CN109271506A (en) | A kind of construction method of the field of power communication knowledge mapping question answering system based on deep learning | |
| CN110347787B (en) | Interview method and device based on AI auxiliary interview scene and terminal equipment | |
| CN111414461B (en) | Intelligent question-answering method and system fusing knowledge base and user modeling | |
| CN110222163A (en) | A kind of intelligent answer method and system merging CNN and two-way LSTM | |
| CN109388700A (en) | Intention identification method and system | |
| CN113505200B (en) | Sentence-level Chinese event detection method combined with document key information | |
| CN112307164A (en) | Information recommendation method and device, computer equipment and storage medium | |
| CN110175229A (en) | A kind of method and system carrying out online training based on natural language | |
| CN111222330B (en) | Chinese event detection method and system | |
| CN113536784B (en) | Text processing method, device, computer equipment and storage medium | |
| CN110717021A (en) | Input text and related device for obtaining artificial intelligence interview | |
| CN114648016A (en) | Event argument extraction method based on event element interaction and tag semantic enhancement | |
| CN112579666A (en) | Intelligent question-answering system and method and related equipment | |
| CN114818717A (en) | Chinese named entity recognition method and system fusing vocabulary and syntax information | |
| Sujana et al. | Rumor detection on Twitter using multiloss hierarchical BiLSTM with an attenuation factor | |
| CN112100212A (en) | Case scenario extraction method based on machine learning and rule matching | |
| CN115905187B (en) | Intelligent proposition system oriented to cloud computing engineering technician authentication | |
| TW202034207A (en) | Dialogue system using intention detection ensemble learning and method thereof | |
| CN115577080A (en) | Question reply matching method, system, server and storage medium | |
| CN114756678A (en) | Unknown intention text identification method and device | |
| CN117828024A (en) | Plug-in retrieval method, device, storage medium and equipment | |
| Ye et al. | A sentiment based non-factoid question-answering framework |
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 |